Commit
•
dba3569
1
Parent(s):
a065fb4
llama v0
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +15 -0
- checkpoint-100/config.json +3 -0
- checkpoint-100/generation_config.json +3 -0
- checkpoint-100/model-00001-of-00004.safetensors +3 -0
- checkpoint-100/model-00002-of-00004.safetensors +3 -0
- checkpoint-100/model-00003-of-00004.safetensors +3 -0
- checkpoint-100/model-00004-of-00004.safetensors +3 -0
- checkpoint-100/model.safetensors.index.json +3 -0
- checkpoint-100/optimizer.pt +3 -0
- checkpoint-100/rng_state.pth +3 -0
- checkpoint-100/scheduler.pt +3 -0
- checkpoint-100/special_tokens_map.json +3 -0
- checkpoint-100/tokenizer.json +3 -0
- checkpoint-100/tokenizer_config.json +3 -0
- checkpoint-100/trainer_state.json +823 -0
- checkpoint-100/training_args.bin +3 -0
- checkpoint-200/config.json +3 -0
- checkpoint-200/generation_config.json +3 -0
- checkpoint-200/model-00001-of-00004.safetensors +3 -0
- checkpoint-200/model-00002-of-00004.safetensors +3 -0
- checkpoint-200/model-00003-of-00004.safetensors +3 -0
- checkpoint-200/model-00004-of-00004.safetensors +3 -0
- checkpoint-200/model.safetensors.index.json +3 -0
- checkpoint-200/optimizer.pt +3 -0
- checkpoint-200/rng_state.pth +3 -0
- checkpoint-200/scheduler.pt +3 -0
- checkpoint-200/special_tokens_map.json +3 -0
- checkpoint-200/tokenizer.json +3 -0
- checkpoint-200/tokenizer_config.json +3 -0
- checkpoint-200/trainer_state.json +1613 -0
- checkpoint-200/training_args.bin +3 -0
- checkpoint-300/config.json +3 -0
- checkpoint-300/generation_config.json +3 -0
- checkpoint-300/model-00001-of-00004.safetensors +3 -0
- checkpoint-300/model-00002-of-00004.safetensors +3 -0
- checkpoint-300/model-00003-of-00004.safetensors +3 -0
- checkpoint-300/model-00004-of-00004.safetensors +3 -0
- checkpoint-300/model.safetensors.index.json +3 -0
- checkpoint-300/optimizer.pt +3 -0
- checkpoint-300/rng_state.pth +3 -0
- checkpoint-300/scheduler.pt +3 -0
- checkpoint-300/special_tokens_map.json +3 -0
- checkpoint-300/tokenizer.json +3 -0
- checkpoint-300/tokenizer_config.json +3 -0
- checkpoint-300/trainer_state.json +2403 -0
- checkpoint-300/training_args.bin +3 -0
- checkpoint-308/config.json +3 -0
- checkpoint-308/generation_config.json +3 -0
- checkpoint-308/model-00001-of-00004.safetensors +3 -0
- checkpoint-308/model-00002-of-00004.safetensors +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,18 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
. filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
config.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
special_tokens_map.json filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
checkpoint-308 filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
generation_config.json filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
checkpoint-100 filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
tokenizer_config.json filter=lfs diff=lfs merge=lfs -text
|
| 46 |
+
checkpoint-200 filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
checkpoint-300 filter=lfs diff=lfs merge=lfs -text
|
| 48 |
+
model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 49 |
+
model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 50 |
+
model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
|
checkpoint-100/config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8b621112eddc9da772fae3f70d672f4d949cc5cb1d580f135d66b3836598c1a
|
| 3 |
+
size 915
|
checkpoint-100/generation_config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7327788370b7783e29852cf19b4a1f40cd31af5962c94bba76c336d491b4169
|
| 3 |
+
size 184
|
checkpoint-100/model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a62275b83768b450eaceec040629b66fcc8362137aba5e874d5334c846ac7646
|
| 3 |
+
size 4976698672
|
checkpoint-100/model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb5b0664bdb88ef83ded2a10b6b37a3517a9db7e0039a688e7351577a3a3a2ed
|
| 3 |
+
size 4999802720
|
checkpoint-100/model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8726c320884ad49027dbafeaa3db55a378cf5b1b286b3a02bfa6075988cd760b
|
| 3 |
+
size 4915916176
|
checkpoint-100/model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4dc1f3d37eb965816560312e02d7a7aaac58b22e1978650cb76b59aaa1ab86df
|
| 3 |
+
size 1168138808
|
checkpoint-100/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:146776fce3f6db1103aa6f249e65ee5544c5923ce6f971b092eee79aa6e5d37b
|
| 3 |
+
size 23950
|
checkpoint-100/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e14320965875e72c6d9efb454e3129b26c88bee6e66cda297c6d78702a4f79a
|
| 3 |
+
size 32121299754
|
checkpoint-100/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c26b481b9cb8c27b6ce66e286d7b2720e0aefc60735ac6e7640899dd50d4bf55
|
| 3 |
+
size 14244
|
checkpoint-100/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:190d296d912b9aa1e1918db9af8ef09674f2d36d1e112918274e76c09503d1c5
|
| 3 |
+
size 1064
|
checkpoint-100/special_tokens_map.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b1835caa5b4d70acaa210fa222b0036f1882f9525c4660fd4810fb3e1e40ff8
|
| 3 |
+
size 325
|
checkpoint-100/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79e3e522635f3171300913bb421464a87de6222182a0570b9b2ccba2a964b2b4
|
| 3 |
+
size 9085657
|
checkpoint-100/tokenizer_config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:05d0de6d831b5940c3f2eae4e495b9f77612cbb05b5804846733ab617f0dfe9b
|
| 3 |
+
size 55380
|
checkpoint-100/trainer_state.json
ADDED
|
@@ -0,0 +1,823 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.3246753246753247,
|
| 5 |
+
"eval_steps": 10,
|
| 6 |
+
"global_step": 100,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.003246753246753247,
|
| 13 |
+
"grad_norm": 16.375,
|
| 14 |
+
"learning_rate": 4.0000000000000003e-07,
|
| 15 |
+
"loss": 1.4017,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.006493506493506494,
|
| 20 |
+
"grad_norm": 16.25,
|
| 21 |
+
"learning_rate": 8.000000000000001e-07,
|
| 22 |
+
"loss": 1.4229,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.00974025974025974,
|
| 27 |
+
"grad_norm": 16.75,
|
| 28 |
+
"learning_rate": 1.2000000000000002e-06,
|
| 29 |
+
"loss": 1.4112,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.012987012987012988,
|
| 34 |
+
"grad_norm": 16.5,
|
| 35 |
+
"learning_rate": 1.6000000000000001e-06,
|
| 36 |
+
"loss": 1.3959,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.016233766233766232,
|
| 41 |
+
"grad_norm": 16.125,
|
| 42 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 43 |
+
"loss": 1.3789,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.01948051948051948,
|
| 48 |
+
"grad_norm": 14.4375,
|
| 49 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 50 |
+
"loss": 1.3618,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.022727272727272728,
|
| 55 |
+
"grad_norm": 10.1875,
|
| 56 |
+
"learning_rate": 2.8000000000000003e-06,
|
| 57 |
+
"loss": 1.3214,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.025974025974025976,
|
| 62 |
+
"grad_norm": 7.4375,
|
| 63 |
+
"learning_rate": 3.2000000000000003e-06,
|
| 64 |
+
"loss": 1.2885,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.02922077922077922,
|
| 69 |
+
"grad_norm": 6.28125,
|
| 70 |
+
"learning_rate": 3.6000000000000003e-06,
|
| 71 |
+
"loss": 1.2436,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.032467532467532464,
|
| 76 |
+
"grad_norm": 5.75,
|
| 77 |
+
"learning_rate": 4.000000000000001e-06,
|
| 78 |
+
"loss": 1.2269,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.032467532467532464,
|
| 83 |
+
"eval_loss": 1.1976113319396973,
|
| 84 |
+
"eval_model_preparation_time": 0.0003,
|
| 85 |
+
"eval_runtime": 175.0273,
|
| 86 |
+
"eval_samples_per_second": 11.878,
|
| 87 |
+
"eval_steps_per_second": 1.485,
|
| 88 |
+
"step": 10
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.03571428571428571,
|
| 92 |
+
"grad_norm": 5.375,
|
| 93 |
+
"learning_rate": 4.4e-06,
|
| 94 |
+
"loss": 1.1925,
|
| 95 |
+
"step": 11
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.03896103896103896,
|
| 99 |
+
"grad_norm": 5.125,
|
| 100 |
+
"learning_rate": 4.800000000000001e-06,
|
| 101 |
+
"loss": 1.1307,
|
| 102 |
+
"step": 12
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.04220779220779221,
|
| 106 |
+
"grad_norm": 5.125,
|
| 107 |
+
"learning_rate": 5.2e-06,
|
| 108 |
+
"loss": 1.0778,
|
| 109 |
+
"step": 13
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.045454545454545456,
|
| 113 |
+
"grad_norm": 5.0625,
|
| 114 |
+
"learning_rate": 5.600000000000001e-06,
|
| 115 |
+
"loss": 1.0067,
|
| 116 |
+
"step": 14
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.048701298701298704,
|
| 120 |
+
"grad_norm": 5.75,
|
| 121 |
+
"learning_rate": 6e-06,
|
| 122 |
+
"loss": 0.9668,
|
| 123 |
+
"step": 15
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.05194805194805195,
|
| 127 |
+
"grad_norm": 5.15625,
|
| 128 |
+
"learning_rate": 6.4000000000000006e-06,
|
| 129 |
+
"loss": 0.875,
|
| 130 |
+
"step": 16
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.05519480519480519,
|
| 134 |
+
"grad_norm": 4.875,
|
| 135 |
+
"learning_rate": 6.800000000000001e-06,
|
| 136 |
+
"loss": 0.8297,
|
| 137 |
+
"step": 17
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.05844155844155844,
|
| 141 |
+
"grad_norm": 4.5625,
|
| 142 |
+
"learning_rate": 7.2000000000000005e-06,
|
| 143 |
+
"loss": 0.7703,
|
| 144 |
+
"step": 18
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.06168831168831169,
|
| 148 |
+
"grad_norm": 3.90625,
|
| 149 |
+
"learning_rate": 7.600000000000001e-06,
|
| 150 |
+
"loss": 0.7327,
|
| 151 |
+
"step": 19
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.06493506493506493,
|
| 155 |
+
"grad_norm": 2.78125,
|
| 156 |
+
"learning_rate": 8.000000000000001e-06,
|
| 157 |
+
"loss": 0.6672,
|
| 158 |
+
"step": 20
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.06493506493506493,
|
| 162 |
+
"eval_loss": 0.6521233320236206,
|
| 163 |
+
"eval_model_preparation_time": 0.0003,
|
| 164 |
+
"eval_runtime": 174.999,
|
| 165 |
+
"eval_samples_per_second": 11.88,
|
| 166 |
+
"eval_steps_per_second": 1.486,
|
| 167 |
+
"step": 20
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.06818181818181818,
|
| 171 |
+
"grad_norm": 2.140625,
|
| 172 |
+
"learning_rate": 8.400000000000001e-06,
|
| 173 |
+
"loss": 0.6507,
|
| 174 |
+
"step": 21
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.07142857142857142,
|
| 178 |
+
"grad_norm": 1.828125,
|
| 179 |
+
"learning_rate": 8.8e-06,
|
| 180 |
+
"loss": 0.6215,
|
| 181 |
+
"step": 22
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.07467532467532467,
|
| 185 |
+
"grad_norm": 1.5546875,
|
| 186 |
+
"learning_rate": 9.200000000000002e-06,
|
| 187 |
+
"loss": 0.5992,
|
| 188 |
+
"step": 23
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.07792207792207792,
|
| 192 |
+
"grad_norm": 1.4453125,
|
| 193 |
+
"learning_rate": 9.600000000000001e-06,
|
| 194 |
+
"loss": 0.5748,
|
| 195 |
+
"step": 24
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.08116883116883117,
|
| 199 |
+
"grad_norm": 1.328125,
|
| 200 |
+
"learning_rate": 1e-05,
|
| 201 |
+
"loss": 0.5572,
|
| 202 |
+
"step": 25
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.08441558441558442,
|
| 206 |
+
"grad_norm": 1.4765625,
|
| 207 |
+
"learning_rate": 1.04e-05,
|
| 208 |
+
"loss": 0.542,
|
| 209 |
+
"step": 26
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.08766233766233766,
|
| 213 |
+
"grad_norm": 1.1171875,
|
| 214 |
+
"learning_rate": 1.0800000000000002e-05,
|
| 215 |
+
"loss": 0.5317,
|
| 216 |
+
"step": 27
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.09090909090909091,
|
| 220 |
+
"grad_norm": 0.90625,
|
| 221 |
+
"learning_rate": 1.1200000000000001e-05,
|
| 222 |
+
"loss": 0.5173,
|
| 223 |
+
"step": 28
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 0.09415584415584416,
|
| 227 |
+
"grad_norm": 0.83984375,
|
| 228 |
+
"learning_rate": 1.16e-05,
|
| 229 |
+
"loss": 0.4892,
|
| 230 |
+
"step": 29
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.09740259740259741,
|
| 234 |
+
"grad_norm": 0.828125,
|
| 235 |
+
"learning_rate": 1.2e-05,
|
| 236 |
+
"loss": 0.491,
|
| 237 |
+
"step": 30
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.09740259740259741,
|
| 241 |
+
"eval_loss": 0.48583006858825684,
|
| 242 |
+
"eval_model_preparation_time": 0.0003,
|
| 243 |
+
"eval_runtime": 174.9705,
|
| 244 |
+
"eval_samples_per_second": 11.882,
|
| 245 |
+
"eval_steps_per_second": 1.486,
|
| 246 |
+
"step": 30
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.10064935064935066,
|
| 250 |
+
"grad_norm": 0.8359375,
|
| 251 |
+
"learning_rate": 1.2400000000000002e-05,
|
| 252 |
+
"loss": 0.4852,
|
| 253 |
+
"step": 31
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.1038961038961039,
|
| 257 |
+
"grad_norm": 1.0078125,
|
| 258 |
+
"learning_rate": 1.2800000000000001e-05,
|
| 259 |
+
"loss": 0.4749,
|
| 260 |
+
"step": 32
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.10714285714285714,
|
| 264 |
+
"grad_norm": 0.99609375,
|
| 265 |
+
"learning_rate": 1.3200000000000002e-05,
|
| 266 |
+
"loss": 0.467,
|
| 267 |
+
"step": 33
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.11038961038961038,
|
| 271 |
+
"grad_norm": 0.734375,
|
| 272 |
+
"learning_rate": 1.3600000000000002e-05,
|
| 273 |
+
"loss": 0.4545,
|
| 274 |
+
"step": 34
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.11363636363636363,
|
| 278 |
+
"grad_norm": 0.69140625,
|
| 279 |
+
"learning_rate": 1.4e-05,
|
| 280 |
+
"loss": 0.4609,
|
| 281 |
+
"step": 35
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.11688311688311688,
|
| 285 |
+
"grad_norm": 0.69921875,
|
| 286 |
+
"learning_rate": 1.4400000000000001e-05,
|
| 287 |
+
"loss": 0.4497,
|
| 288 |
+
"step": 36
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.12012987012987013,
|
| 292 |
+
"grad_norm": 0.703125,
|
| 293 |
+
"learning_rate": 1.48e-05,
|
| 294 |
+
"loss": 0.4607,
|
| 295 |
+
"step": 37
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.12337662337662338,
|
| 299 |
+
"grad_norm": 0.6328125,
|
| 300 |
+
"learning_rate": 1.5200000000000002e-05,
|
| 301 |
+
"loss": 0.443,
|
| 302 |
+
"step": 38
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.1266233766233766,
|
| 306 |
+
"grad_norm": 0.65234375,
|
| 307 |
+
"learning_rate": 1.5600000000000003e-05,
|
| 308 |
+
"loss": 0.4428,
|
| 309 |
+
"step": 39
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.12987012987012986,
|
| 313 |
+
"grad_norm": 0.640625,
|
| 314 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 315 |
+
"loss": 0.435,
|
| 316 |
+
"step": 40
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.12987012987012986,
|
| 320 |
+
"eval_loss": 0.4367639422416687,
|
| 321 |
+
"eval_model_preparation_time": 0.0003,
|
| 322 |
+
"eval_runtime": 175.0177,
|
| 323 |
+
"eval_samples_per_second": 11.879,
|
| 324 |
+
"eval_steps_per_second": 1.486,
|
| 325 |
+
"step": 40
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.1331168831168831,
|
| 329 |
+
"grad_norm": 0.671875,
|
| 330 |
+
"learning_rate": 1.64e-05,
|
| 331 |
+
"loss": 0.438,
|
| 332 |
+
"step": 41
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.13636363636363635,
|
| 336 |
+
"grad_norm": 0.6484375,
|
| 337 |
+
"learning_rate": 1.6800000000000002e-05,
|
| 338 |
+
"loss": 0.4392,
|
| 339 |
+
"step": 42
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.1396103896103896,
|
| 343 |
+
"grad_norm": 0.65234375,
|
| 344 |
+
"learning_rate": 1.72e-05,
|
| 345 |
+
"loss": 0.435,
|
| 346 |
+
"step": 43
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.14285714285714285,
|
| 350 |
+
"grad_norm": 0.62109375,
|
| 351 |
+
"learning_rate": 1.76e-05,
|
| 352 |
+
"loss": 0.4356,
|
| 353 |
+
"step": 44
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.1461038961038961,
|
| 357 |
+
"grad_norm": 0.6171875,
|
| 358 |
+
"learning_rate": 1.8e-05,
|
| 359 |
+
"loss": 0.4172,
|
| 360 |
+
"step": 45
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.14935064935064934,
|
| 364 |
+
"grad_norm": 0.6015625,
|
| 365 |
+
"learning_rate": 1.8400000000000003e-05,
|
| 366 |
+
"loss": 0.4162,
|
| 367 |
+
"step": 46
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.1525974025974026,
|
| 371 |
+
"grad_norm": 0.609375,
|
| 372 |
+
"learning_rate": 1.88e-05,
|
| 373 |
+
"loss": 0.418,
|
| 374 |
+
"step": 47
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.15584415584415584,
|
| 378 |
+
"grad_norm": 0.6328125,
|
| 379 |
+
"learning_rate": 1.9200000000000003e-05,
|
| 380 |
+
"loss": 0.4177,
|
| 381 |
+
"step": 48
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.1590909090909091,
|
| 385 |
+
"grad_norm": 0.6171875,
|
| 386 |
+
"learning_rate": 1.9600000000000002e-05,
|
| 387 |
+
"loss": 0.4064,
|
| 388 |
+
"step": 49
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.16233766233766234,
|
| 392 |
+
"grad_norm": 0.62890625,
|
| 393 |
+
"learning_rate": 2e-05,
|
| 394 |
+
"loss": 0.4078,
|
| 395 |
+
"step": 50
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.16233766233766234,
|
| 399 |
+
"eval_loss": 0.4077843129634857,
|
| 400 |
+
"eval_model_preparation_time": 0.0003,
|
| 401 |
+
"eval_runtime": 174.8482,
|
| 402 |
+
"eval_samples_per_second": 11.89,
|
| 403 |
+
"eval_steps_per_second": 1.487,
|
| 404 |
+
"step": 50
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.16558441558441558,
|
| 408 |
+
"grad_norm": 0.61328125,
|
| 409 |
+
"learning_rate": 1.9999258647132645e-05,
|
| 410 |
+
"loss": 0.4057,
|
| 411 |
+
"step": 51
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.16883116883116883,
|
| 415 |
+
"grad_norm": 0.62890625,
|
| 416 |
+
"learning_rate": 1.9997034698451396e-05,
|
| 417 |
+
"loss": 0.4172,
|
| 418 |
+
"step": 52
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.17207792207792208,
|
| 422 |
+
"grad_norm": 0.61328125,
|
| 423 |
+
"learning_rate": 1.9993328483702393e-05,
|
| 424 |
+
"loss": 0.4082,
|
| 425 |
+
"step": 53
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.17532467532467533,
|
| 429 |
+
"grad_norm": 0.59375,
|
| 430 |
+
"learning_rate": 1.998814055240823e-05,
|
| 431 |
+
"loss": 0.3973,
|
| 432 |
+
"step": 54
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.17857142857142858,
|
| 436 |
+
"grad_norm": 0.59375,
|
| 437 |
+
"learning_rate": 1.998147167378645e-05,
|
| 438 |
+
"loss": 0.3969,
|
| 439 |
+
"step": 55
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.18181818181818182,
|
| 443 |
+
"grad_norm": 0.609375,
|
| 444 |
+
"learning_rate": 1.9973322836635517e-05,
|
| 445 |
+
"loss": 0.4032,
|
| 446 |
+
"step": 56
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.18506493506493507,
|
| 450 |
+
"grad_norm": 0.5859375,
|
| 451 |
+
"learning_rate": 1.9963695249188185e-05,
|
| 452 |
+
"loss": 0.3956,
|
| 453 |
+
"step": 57
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.18831168831168832,
|
| 457 |
+
"grad_norm": 0.57421875,
|
| 458 |
+
"learning_rate": 1.995259033893236e-05,
|
| 459 |
+
"loss": 0.3952,
|
| 460 |
+
"step": 58
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.19155844155844157,
|
| 464 |
+
"grad_norm": 0.59765625,
|
| 465 |
+
"learning_rate": 1.9940009752399462e-05,
|
| 466 |
+
"loss": 0.3905,
|
| 467 |
+
"step": 59
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.19480519480519481,
|
| 471 |
+
"grad_norm": 0.60546875,
|
| 472 |
+
"learning_rate": 1.9925955354920265e-05,
|
| 473 |
+
"loss": 0.3822,
|
| 474 |
+
"step": 60
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.19480519480519481,
|
| 478 |
+
"eval_loss": 0.38575297594070435,
|
| 479 |
+
"eval_model_preparation_time": 0.0003,
|
| 480 |
+
"eval_runtime": 174.9122,
|
| 481 |
+
"eval_samples_per_second": 11.886,
|
| 482 |
+
"eval_steps_per_second": 1.486,
|
| 483 |
+
"step": 60
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.19805194805194806,
|
| 487 |
+
"grad_norm": 0.5859375,
|
| 488 |
+
"learning_rate": 1.9910429230348348e-05,
|
| 489 |
+
"loss": 0.3976,
|
| 490 |
+
"step": 61
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.2012987012987013,
|
| 494 |
+
"grad_norm": 0.578125,
|
| 495 |
+
"learning_rate": 1.9893433680751105e-05,
|
| 496 |
+
"loss": 0.3714,
|
| 497 |
+
"step": 62
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 0.20454545454545456,
|
| 501 |
+
"grad_norm": 0.5859375,
|
| 502 |
+
"learning_rate": 1.9874971226068417e-05,
|
| 503 |
+
"loss": 0.3739,
|
| 504 |
+
"step": 63
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.2077922077922078,
|
| 508 |
+
"grad_norm": 0.5859375,
|
| 509 |
+
"learning_rate": 1.985504460373903e-05,
|
| 510 |
+
"loss": 0.3907,
|
| 511 |
+
"step": 64
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 0.21103896103896103,
|
| 515 |
+
"grad_norm": 0.609375,
|
| 516 |
+
"learning_rate": 1.983365676829466e-05,
|
| 517 |
+
"loss": 0.3803,
|
| 518 |
+
"step": 65
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.21428571428571427,
|
| 522 |
+
"grad_norm": 0.59765625,
|
| 523 |
+
"learning_rate": 1.9810810890921943e-05,
|
| 524 |
+
"loss": 0.3902,
|
| 525 |
+
"step": 66
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.21753246753246752,
|
| 529 |
+
"grad_norm": 0.578125,
|
| 530 |
+
"learning_rate": 1.9786510358992213e-05,
|
| 531 |
+
"loss": 0.3744,
|
| 532 |
+
"step": 67
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.22077922077922077,
|
| 536 |
+
"grad_norm": 0.56640625,
|
| 537 |
+
"learning_rate": 1.9760758775559275e-05,
|
| 538 |
+
"loss": 0.3668,
|
| 539 |
+
"step": 68
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.22402597402597402,
|
| 543 |
+
"grad_norm": 0.625,
|
| 544 |
+
"learning_rate": 1.9733559958825167e-05,
|
| 545 |
+
"loss": 0.3755,
|
| 546 |
+
"step": 69
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.22727272727272727,
|
| 550 |
+
"grad_norm": 0.60546875,
|
| 551 |
+
"learning_rate": 1.9704917941574053e-05,
|
| 552 |
+
"loss": 0.3733,
|
| 553 |
+
"step": 70
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.22727272727272727,
|
| 557 |
+
"eval_loss": 0.3694484233856201,
|
| 558 |
+
"eval_model_preparation_time": 0.0003,
|
| 559 |
+
"eval_runtime": 174.9363,
|
| 560 |
+
"eval_samples_per_second": 11.884,
|
| 561 |
+
"eval_steps_per_second": 1.486,
|
| 562 |
+
"step": 70
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.2305194805194805,
|
| 566 |
+
"grad_norm": 0.6015625,
|
| 567 |
+
"learning_rate": 1.9674836970574253e-05,
|
| 568 |
+
"loss": 0.3676,
|
| 569 |
+
"step": 71
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.23376623376623376,
|
| 573 |
+
"grad_norm": 0.60546875,
|
| 574 |
+
"learning_rate": 1.9643321505948588e-05,
|
| 575 |
+
"loss": 0.3721,
|
| 576 |
+
"step": 72
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.237012987012987,
|
| 580 |
+
"grad_norm": 0.60546875,
|
| 581 |
+
"learning_rate": 1.9610376220513067e-05,
|
| 582 |
+
"loss": 0.3558,
|
| 583 |
+
"step": 73
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.24025974025974026,
|
| 587 |
+
"grad_norm": 0.625,
|
| 588 |
+
"learning_rate": 1.957600599908406e-05,
|
| 589 |
+
"loss": 0.357,
|
| 590 |
+
"step": 74
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.2435064935064935,
|
| 594 |
+
"grad_norm": 0.66015625,
|
| 595 |
+
"learning_rate": 1.954021593775401e-05,
|
| 596 |
+
"loss": 0.3608,
|
| 597 |
+
"step": 75
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.24675324675324675,
|
| 601 |
+
"grad_norm": 0.59375,
|
| 602 |
+
"learning_rate": 1.9503011343135828e-05,
|
| 603 |
+
"loss": 0.3513,
|
| 604 |
+
"step": 76
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.25,
|
| 608 |
+
"grad_norm": 0.609375,
|
| 609 |
+
"learning_rate": 1.9464397731576093e-05,
|
| 610 |
+
"loss": 0.3693,
|
| 611 |
+
"step": 77
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.2532467532467532,
|
| 615 |
+
"grad_norm": 0.59375,
|
| 616 |
+
"learning_rate": 1.9424380828337146e-05,
|
| 617 |
+
"loss": 0.3605,
|
| 618 |
+
"step": 78
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.2564935064935065,
|
| 622 |
+
"grad_norm": 0.6171875,
|
| 623 |
+
"learning_rate": 1.938296656674817e-05,
|
| 624 |
+
"loss": 0.3553,
|
| 625 |
+
"step": 79
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.2597402597402597,
|
| 629 |
+
"grad_norm": 0.671875,
|
| 630 |
+
"learning_rate": 1.9340161087325483e-05,
|
| 631 |
+
"loss": 0.3721,
|
| 632 |
+
"step": 80
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.2597402597402597,
|
| 636 |
+
"eval_loss": 0.3553767800331116,
|
| 637 |
+
"eval_model_preparation_time": 0.0003,
|
| 638 |
+
"eval_runtime": 175.0277,
|
| 639 |
+
"eval_samples_per_second": 11.878,
|
| 640 |
+
"eval_steps_per_second": 1.485,
|
| 641 |
+
"step": 80
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.262987012987013,
|
| 645 |
+
"grad_norm": 0.609375,
|
| 646 |
+
"learning_rate": 1.9295970736862063e-05,
|
| 647 |
+
"loss": 0.3597,
|
| 648 |
+
"step": 81
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.2662337662337662,
|
| 652 |
+
"grad_norm": 0.65625,
|
| 653 |
+
"learning_rate": 1.9250402067486523e-05,
|
| 654 |
+
"loss": 0.3527,
|
| 655 |
+
"step": 82
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.2694805194805195,
|
| 659 |
+
"grad_norm": 0.61328125,
|
| 660 |
+
"learning_rate": 1.9203461835691596e-05,
|
| 661 |
+
"loss": 0.3528,
|
| 662 |
+
"step": 83
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.2727272727272727,
|
| 666 |
+
"grad_norm": 0.6640625,
|
| 667 |
+
"learning_rate": 1.9155157001332374e-05,
|
| 668 |
+
"loss": 0.356,
|
| 669 |
+
"step": 84
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.275974025974026,
|
| 673 |
+
"grad_norm": 0.6171875,
|
| 674 |
+
"learning_rate": 1.9105494726594344e-05,
|
| 675 |
+
"loss": 0.3556,
|
| 676 |
+
"step": 85
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.2792207792207792,
|
| 680 |
+
"grad_norm": 0.6171875,
|
| 681 |
+
"learning_rate": 1.905448237493147e-05,
|
| 682 |
+
"loss": 0.3473,
|
| 683 |
+
"step": 86
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.2824675324675325,
|
| 687 |
+
"grad_norm": 0.5859375,
|
| 688 |
+
"learning_rate": 1.9002127509974376e-05,
|
| 689 |
+
"loss": 0.3441,
|
| 690 |
+
"step": 87
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.2857142857142857,
|
| 694 |
+
"grad_norm": 0.6171875,
|
| 695 |
+
"learning_rate": 1.894843789440892e-05,
|
| 696 |
+
"loss": 0.3492,
|
| 697 |
+
"step": 88
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.288961038961039,
|
| 701 |
+
"grad_norm": 0.6328125,
|
| 702 |
+
"learning_rate": 1.889342148882519e-05,
|
| 703 |
+
"loss": 0.3338,
|
| 704 |
+
"step": 89
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.2922077922077922,
|
| 708 |
+
"grad_norm": 0.67578125,
|
| 709 |
+
"learning_rate": 1.8837086450537195e-05,
|
| 710 |
+
"loss": 0.3347,
|
| 711 |
+
"step": 90
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.2922077922077922,
|
| 715 |
+
"eval_loss": 0.34332525730133057,
|
| 716 |
+
"eval_model_preparation_time": 0.0003,
|
| 717 |
+
"eval_runtime": 174.9257,
|
| 718 |
+
"eval_samples_per_second": 11.885,
|
| 719 |
+
"eval_steps_per_second": 1.486,
|
| 720 |
+
"step": 90
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.29545454545454547,
|
| 724 |
+
"grad_norm": 0.6328125,
|
| 725 |
+
"learning_rate": 1.877944113237336e-05,
|
| 726 |
+
"loss": 0.3438,
|
| 727 |
+
"step": 91
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.2987012987012987,
|
| 731 |
+
"grad_norm": 0.6328125,
|
| 732 |
+
"learning_rate": 1.872049408143808e-05,
|
| 733 |
+
"loss": 0.3505,
|
| 734 |
+
"step": 92
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.30194805194805197,
|
| 738 |
+
"grad_norm": 0.6328125,
|
| 739 |
+
"learning_rate": 1.866025403784439e-05,
|
| 740 |
+
"loss": 0.3362,
|
| 741 |
+
"step": 93
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.3051948051948052,
|
| 745 |
+
"grad_norm": 0.640625,
|
| 746 |
+
"learning_rate": 1.8598729933418102e-05,
|
| 747 |
+
"loss": 0.337,
|
| 748 |
+
"step": 94
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 0.30844155844155846,
|
| 752 |
+
"grad_norm": 0.64453125,
|
| 753 |
+
"learning_rate": 1.8535930890373467e-05,
|
| 754 |
+
"loss": 0.3324,
|
| 755 |
+
"step": 95
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 0.3116883116883117,
|
| 759 |
+
"grad_norm": 0.6875,
|
| 760 |
+
"learning_rate": 1.8471866219960604e-05,
|
| 761 |
+
"loss": 0.3461,
|
| 762 |
+
"step": 96
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.31493506493506496,
|
| 766 |
+
"grad_norm": 0.6328125,
|
| 767 |
+
"learning_rate": 1.840654542108494e-05,
|
| 768 |
+
"loss": 0.3318,
|
| 769 |
+
"step": 97
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 0.3181818181818182,
|
| 773 |
+
"grad_norm": 0.62109375,
|
| 774 |
+
"learning_rate": 1.833997817889878e-05,
|
| 775 |
+
"loss": 0.3335,
|
| 776 |
+
"step": 98
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 0.32142857142857145,
|
| 780 |
+
"grad_norm": 0.61328125,
|
| 781 |
+
"learning_rate": 1.82721743633653e-05,
|
| 782 |
+
"loss": 0.3291,
|
| 783 |
+
"step": 99
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.3246753246753247,
|
| 787 |
+
"grad_norm": 0.6171875,
|
| 788 |
+
"learning_rate": 1.820314402779511e-05,
|
| 789 |
+
"loss": 0.3324,
|
| 790 |
+
"step": 100
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.3246753246753247,
|
| 794 |
+
"eval_loss": 0.33332687616348267,
|
| 795 |
+
"eval_model_preparation_time": 0.0003,
|
| 796 |
+
"eval_runtime": 174.9506,
|
| 797 |
+
"eval_samples_per_second": 11.883,
|
| 798 |
+
"eval_steps_per_second": 1.486,
|
| 799 |
+
"step": 100
|
| 800 |
+
}
|
| 801 |
+
],
|
| 802 |
+
"logging_steps": 1,
|
| 803 |
+
"max_steps": 308,
|
| 804 |
+
"num_input_tokens_seen": 0,
|
| 805 |
+
"num_train_epochs": 1,
|
| 806 |
+
"save_steps": 100,
|
| 807 |
+
"stateful_callbacks": {
|
| 808 |
+
"TrainerControl": {
|
| 809 |
+
"args": {
|
| 810 |
+
"should_epoch_stop": false,
|
| 811 |
+
"should_evaluate": false,
|
| 812 |
+
"should_log": false,
|
| 813 |
+
"should_save": true,
|
| 814 |
+
"should_training_stop": false
|
| 815 |
+
},
|
| 816 |
+
"attributes": {}
|
| 817 |
+
}
|
| 818 |
+
},
|
| 819 |
+
"total_flos": 5.902112919650304e+17,
|
| 820 |
+
"train_batch_size": 8,
|
| 821 |
+
"trial_name": null,
|
| 822 |
+
"trial_params": null
|
| 823 |
+
}
|
checkpoint-100/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d09f69be12f7ef607f0a1508435a517f5277e3160e5d6a59346e619fcbaa3592
|
| 3 |
+
size 5176
|
checkpoint-200/config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8b621112eddc9da772fae3f70d672f4d949cc5cb1d580f135d66b3836598c1a
|
| 3 |
+
size 915
|
checkpoint-200/generation_config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7327788370b7783e29852cf19b4a1f40cd31af5962c94bba76c336d491b4169
|
| 3 |
+
size 184
|
checkpoint-200/model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f60fb798be6dc6cc800be220165509b7026f9d04bd5a45d6fae8c0cf42cbf3dd
|
| 3 |
+
size 4976698672
|
checkpoint-200/model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1161b03770b7cceaea53010a7c38cae4279bc7ba02d9c0f3584d7574226c2f1
|
| 3 |
+
size 4999802720
|
checkpoint-200/model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:591b6342c93199d69b2d7dbe15e08a0975ac4bdcc33b07e0b5b542e8b6443413
|
| 3 |
+
size 4915916176
|
checkpoint-200/model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ee9a2f97c92c6b4160444f1a13d52f249d6116c60b9952ae9ad61c992f57f53
|
| 3 |
+
size 1168138808
|
checkpoint-200/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:146776fce3f6db1103aa6f249e65ee5544c5923ce6f971b092eee79aa6e5d37b
|
| 3 |
+
size 23950
|
checkpoint-200/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:025f20483fbcef43f00f5dd8acbb4ab663455020f9b7ec9b2086cfadf235d021
|
| 3 |
+
size 32121299754
|
checkpoint-200/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aad5da87704f9496a4cad943d2aa8988a987b1e77b57fa4a28ff4c89ee480ac0
|
| 3 |
+
size 14244
|
checkpoint-200/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4565f7ec171134b011efb3a86c834a370c710414c88a26b6961aac2a0ed0d92d
|
| 3 |
+
size 1064
|
checkpoint-200/special_tokens_map.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b1835caa5b4d70acaa210fa222b0036f1882f9525c4660fd4810fb3e1e40ff8
|
| 3 |
+
size 325
|
checkpoint-200/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79e3e522635f3171300913bb421464a87de6222182a0570b9b2ccba2a964b2b4
|
| 3 |
+
size 9085657
|
checkpoint-200/tokenizer_config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:05d0de6d831b5940c3f2eae4e495b9f77612cbb05b5804846733ab617f0dfe9b
|
| 3 |
+
size 55380
|
checkpoint-200/trainer_state.json
ADDED
|
@@ -0,0 +1,1613 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.6493506493506493,
|
| 5 |
+
"eval_steps": 10,
|
| 6 |
+
"global_step": 200,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.003246753246753247,
|
| 13 |
+
"grad_norm": 16.375,
|
| 14 |
+
"learning_rate": 4.0000000000000003e-07,
|
| 15 |
+
"loss": 1.4017,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.006493506493506494,
|
| 20 |
+
"grad_norm": 16.25,
|
| 21 |
+
"learning_rate": 8.000000000000001e-07,
|
| 22 |
+
"loss": 1.4229,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.00974025974025974,
|
| 27 |
+
"grad_norm": 16.75,
|
| 28 |
+
"learning_rate": 1.2000000000000002e-06,
|
| 29 |
+
"loss": 1.4112,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.012987012987012988,
|
| 34 |
+
"grad_norm": 16.5,
|
| 35 |
+
"learning_rate": 1.6000000000000001e-06,
|
| 36 |
+
"loss": 1.3959,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.016233766233766232,
|
| 41 |
+
"grad_norm": 16.125,
|
| 42 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 43 |
+
"loss": 1.3789,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.01948051948051948,
|
| 48 |
+
"grad_norm": 14.4375,
|
| 49 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 50 |
+
"loss": 1.3618,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.022727272727272728,
|
| 55 |
+
"grad_norm": 10.1875,
|
| 56 |
+
"learning_rate": 2.8000000000000003e-06,
|
| 57 |
+
"loss": 1.3214,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.025974025974025976,
|
| 62 |
+
"grad_norm": 7.4375,
|
| 63 |
+
"learning_rate": 3.2000000000000003e-06,
|
| 64 |
+
"loss": 1.2885,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.02922077922077922,
|
| 69 |
+
"grad_norm": 6.28125,
|
| 70 |
+
"learning_rate": 3.6000000000000003e-06,
|
| 71 |
+
"loss": 1.2436,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.032467532467532464,
|
| 76 |
+
"grad_norm": 5.75,
|
| 77 |
+
"learning_rate": 4.000000000000001e-06,
|
| 78 |
+
"loss": 1.2269,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.032467532467532464,
|
| 83 |
+
"eval_loss": 1.1976113319396973,
|
| 84 |
+
"eval_model_preparation_time": 0.0003,
|
| 85 |
+
"eval_runtime": 175.0273,
|
| 86 |
+
"eval_samples_per_second": 11.878,
|
| 87 |
+
"eval_steps_per_second": 1.485,
|
| 88 |
+
"step": 10
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.03571428571428571,
|
| 92 |
+
"grad_norm": 5.375,
|
| 93 |
+
"learning_rate": 4.4e-06,
|
| 94 |
+
"loss": 1.1925,
|
| 95 |
+
"step": 11
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.03896103896103896,
|
| 99 |
+
"grad_norm": 5.125,
|
| 100 |
+
"learning_rate": 4.800000000000001e-06,
|
| 101 |
+
"loss": 1.1307,
|
| 102 |
+
"step": 12
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.04220779220779221,
|
| 106 |
+
"grad_norm": 5.125,
|
| 107 |
+
"learning_rate": 5.2e-06,
|
| 108 |
+
"loss": 1.0778,
|
| 109 |
+
"step": 13
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.045454545454545456,
|
| 113 |
+
"grad_norm": 5.0625,
|
| 114 |
+
"learning_rate": 5.600000000000001e-06,
|
| 115 |
+
"loss": 1.0067,
|
| 116 |
+
"step": 14
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.048701298701298704,
|
| 120 |
+
"grad_norm": 5.75,
|
| 121 |
+
"learning_rate": 6e-06,
|
| 122 |
+
"loss": 0.9668,
|
| 123 |
+
"step": 15
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.05194805194805195,
|
| 127 |
+
"grad_norm": 5.15625,
|
| 128 |
+
"learning_rate": 6.4000000000000006e-06,
|
| 129 |
+
"loss": 0.875,
|
| 130 |
+
"step": 16
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.05519480519480519,
|
| 134 |
+
"grad_norm": 4.875,
|
| 135 |
+
"learning_rate": 6.800000000000001e-06,
|
| 136 |
+
"loss": 0.8297,
|
| 137 |
+
"step": 17
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.05844155844155844,
|
| 141 |
+
"grad_norm": 4.5625,
|
| 142 |
+
"learning_rate": 7.2000000000000005e-06,
|
| 143 |
+
"loss": 0.7703,
|
| 144 |
+
"step": 18
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.06168831168831169,
|
| 148 |
+
"grad_norm": 3.90625,
|
| 149 |
+
"learning_rate": 7.600000000000001e-06,
|
| 150 |
+
"loss": 0.7327,
|
| 151 |
+
"step": 19
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.06493506493506493,
|
| 155 |
+
"grad_norm": 2.78125,
|
| 156 |
+
"learning_rate": 8.000000000000001e-06,
|
| 157 |
+
"loss": 0.6672,
|
| 158 |
+
"step": 20
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.06493506493506493,
|
| 162 |
+
"eval_loss": 0.6521233320236206,
|
| 163 |
+
"eval_model_preparation_time": 0.0003,
|
| 164 |
+
"eval_runtime": 174.999,
|
| 165 |
+
"eval_samples_per_second": 11.88,
|
| 166 |
+
"eval_steps_per_second": 1.486,
|
| 167 |
+
"step": 20
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.06818181818181818,
|
| 171 |
+
"grad_norm": 2.140625,
|
| 172 |
+
"learning_rate": 8.400000000000001e-06,
|
| 173 |
+
"loss": 0.6507,
|
| 174 |
+
"step": 21
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.07142857142857142,
|
| 178 |
+
"grad_norm": 1.828125,
|
| 179 |
+
"learning_rate": 8.8e-06,
|
| 180 |
+
"loss": 0.6215,
|
| 181 |
+
"step": 22
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.07467532467532467,
|
| 185 |
+
"grad_norm": 1.5546875,
|
| 186 |
+
"learning_rate": 9.200000000000002e-06,
|
| 187 |
+
"loss": 0.5992,
|
| 188 |
+
"step": 23
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.07792207792207792,
|
| 192 |
+
"grad_norm": 1.4453125,
|
| 193 |
+
"learning_rate": 9.600000000000001e-06,
|
| 194 |
+
"loss": 0.5748,
|
| 195 |
+
"step": 24
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.08116883116883117,
|
| 199 |
+
"grad_norm": 1.328125,
|
| 200 |
+
"learning_rate": 1e-05,
|
| 201 |
+
"loss": 0.5572,
|
| 202 |
+
"step": 25
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.08441558441558442,
|
| 206 |
+
"grad_norm": 1.4765625,
|
| 207 |
+
"learning_rate": 1.04e-05,
|
| 208 |
+
"loss": 0.542,
|
| 209 |
+
"step": 26
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.08766233766233766,
|
| 213 |
+
"grad_norm": 1.1171875,
|
| 214 |
+
"learning_rate": 1.0800000000000002e-05,
|
| 215 |
+
"loss": 0.5317,
|
| 216 |
+
"step": 27
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.09090909090909091,
|
| 220 |
+
"grad_norm": 0.90625,
|
| 221 |
+
"learning_rate": 1.1200000000000001e-05,
|
| 222 |
+
"loss": 0.5173,
|
| 223 |
+
"step": 28
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 0.09415584415584416,
|
| 227 |
+
"grad_norm": 0.83984375,
|
| 228 |
+
"learning_rate": 1.16e-05,
|
| 229 |
+
"loss": 0.4892,
|
| 230 |
+
"step": 29
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.09740259740259741,
|
| 234 |
+
"grad_norm": 0.828125,
|
| 235 |
+
"learning_rate": 1.2e-05,
|
| 236 |
+
"loss": 0.491,
|
| 237 |
+
"step": 30
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.09740259740259741,
|
| 241 |
+
"eval_loss": 0.48583006858825684,
|
| 242 |
+
"eval_model_preparation_time": 0.0003,
|
| 243 |
+
"eval_runtime": 174.9705,
|
| 244 |
+
"eval_samples_per_second": 11.882,
|
| 245 |
+
"eval_steps_per_second": 1.486,
|
| 246 |
+
"step": 30
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.10064935064935066,
|
| 250 |
+
"grad_norm": 0.8359375,
|
| 251 |
+
"learning_rate": 1.2400000000000002e-05,
|
| 252 |
+
"loss": 0.4852,
|
| 253 |
+
"step": 31
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.1038961038961039,
|
| 257 |
+
"grad_norm": 1.0078125,
|
| 258 |
+
"learning_rate": 1.2800000000000001e-05,
|
| 259 |
+
"loss": 0.4749,
|
| 260 |
+
"step": 32
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.10714285714285714,
|
| 264 |
+
"grad_norm": 0.99609375,
|
| 265 |
+
"learning_rate": 1.3200000000000002e-05,
|
| 266 |
+
"loss": 0.467,
|
| 267 |
+
"step": 33
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.11038961038961038,
|
| 271 |
+
"grad_norm": 0.734375,
|
| 272 |
+
"learning_rate": 1.3600000000000002e-05,
|
| 273 |
+
"loss": 0.4545,
|
| 274 |
+
"step": 34
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.11363636363636363,
|
| 278 |
+
"grad_norm": 0.69140625,
|
| 279 |
+
"learning_rate": 1.4e-05,
|
| 280 |
+
"loss": 0.4609,
|
| 281 |
+
"step": 35
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.11688311688311688,
|
| 285 |
+
"grad_norm": 0.69921875,
|
| 286 |
+
"learning_rate": 1.4400000000000001e-05,
|
| 287 |
+
"loss": 0.4497,
|
| 288 |
+
"step": 36
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.12012987012987013,
|
| 292 |
+
"grad_norm": 0.703125,
|
| 293 |
+
"learning_rate": 1.48e-05,
|
| 294 |
+
"loss": 0.4607,
|
| 295 |
+
"step": 37
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.12337662337662338,
|
| 299 |
+
"grad_norm": 0.6328125,
|
| 300 |
+
"learning_rate": 1.5200000000000002e-05,
|
| 301 |
+
"loss": 0.443,
|
| 302 |
+
"step": 38
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.1266233766233766,
|
| 306 |
+
"grad_norm": 0.65234375,
|
| 307 |
+
"learning_rate": 1.5600000000000003e-05,
|
| 308 |
+
"loss": 0.4428,
|
| 309 |
+
"step": 39
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.12987012987012986,
|
| 313 |
+
"grad_norm": 0.640625,
|
| 314 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 315 |
+
"loss": 0.435,
|
| 316 |
+
"step": 40
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.12987012987012986,
|
| 320 |
+
"eval_loss": 0.4367639422416687,
|
| 321 |
+
"eval_model_preparation_time": 0.0003,
|
| 322 |
+
"eval_runtime": 175.0177,
|
| 323 |
+
"eval_samples_per_second": 11.879,
|
| 324 |
+
"eval_steps_per_second": 1.486,
|
| 325 |
+
"step": 40
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.1331168831168831,
|
| 329 |
+
"grad_norm": 0.671875,
|
| 330 |
+
"learning_rate": 1.64e-05,
|
| 331 |
+
"loss": 0.438,
|
| 332 |
+
"step": 41
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.13636363636363635,
|
| 336 |
+
"grad_norm": 0.6484375,
|
| 337 |
+
"learning_rate": 1.6800000000000002e-05,
|
| 338 |
+
"loss": 0.4392,
|
| 339 |
+
"step": 42
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.1396103896103896,
|
| 343 |
+
"grad_norm": 0.65234375,
|
| 344 |
+
"learning_rate": 1.72e-05,
|
| 345 |
+
"loss": 0.435,
|
| 346 |
+
"step": 43
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.14285714285714285,
|
| 350 |
+
"grad_norm": 0.62109375,
|
| 351 |
+
"learning_rate": 1.76e-05,
|
| 352 |
+
"loss": 0.4356,
|
| 353 |
+
"step": 44
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.1461038961038961,
|
| 357 |
+
"grad_norm": 0.6171875,
|
| 358 |
+
"learning_rate": 1.8e-05,
|
| 359 |
+
"loss": 0.4172,
|
| 360 |
+
"step": 45
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.14935064935064934,
|
| 364 |
+
"grad_norm": 0.6015625,
|
| 365 |
+
"learning_rate": 1.8400000000000003e-05,
|
| 366 |
+
"loss": 0.4162,
|
| 367 |
+
"step": 46
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.1525974025974026,
|
| 371 |
+
"grad_norm": 0.609375,
|
| 372 |
+
"learning_rate": 1.88e-05,
|
| 373 |
+
"loss": 0.418,
|
| 374 |
+
"step": 47
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.15584415584415584,
|
| 378 |
+
"grad_norm": 0.6328125,
|
| 379 |
+
"learning_rate": 1.9200000000000003e-05,
|
| 380 |
+
"loss": 0.4177,
|
| 381 |
+
"step": 48
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.1590909090909091,
|
| 385 |
+
"grad_norm": 0.6171875,
|
| 386 |
+
"learning_rate": 1.9600000000000002e-05,
|
| 387 |
+
"loss": 0.4064,
|
| 388 |
+
"step": 49
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.16233766233766234,
|
| 392 |
+
"grad_norm": 0.62890625,
|
| 393 |
+
"learning_rate": 2e-05,
|
| 394 |
+
"loss": 0.4078,
|
| 395 |
+
"step": 50
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.16233766233766234,
|
| 399 |
+
"eval_loss": 0.4077843129634857,
|
| 400 |
+
"eval_model_preparation_time": 0.0003,
|
| 401 |
+
"eval_runtime": 174.8482,
|
| 402 |
+
"eval_samples_per_second": 11.89,
|
| 403 |
+
"eval_steps_per_second": 1.487,
|
| 404 |
+
"step": 50
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.16558441558441558,
|
| 408 |
+
"grad_norm": 0.61328125,
|
| 409 |
+
"learning_rate": 1.9999258647132645e-05,
|
| 410 |
+
"loss": 0.4057,
|
| 411 |
+
"step": 51
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.16883116883116883,
|
| 415 |
+
"grad_norm": 0.62890625,
|
| 416 |
+
"learning_rate": 1.9997034698451396e-05,
|
| 417 |
+
"loss": 0.4172,
|
| 418 |
+
"step": 52
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.17207792207792208,
|
| 422 |
+
"grad_norm": 0.61328125,
|
| 423 |
+
"learning_rate": 1.9993328483702393e-05,
|
| 424 |
+
"loss": 0.4082,
|
| 425 |
+
"step": 53
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.17532467532467533,
|
| 429 |
+
"grad_norm": 0.59375,
|
| 430 |
+
"learning_rate": 1.998814055240823e-05,
|
| 431 |
+
"loss": 0.3973,
|
| 432 |
+
"step": 54
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.17857142857142858,
|
| 436 |
+
"grad_norm": 0.59375,
|
| 437 |
+
"learning_rate": 1.998147167378645e-05,
|
| 438 |
+
"loss": 0.3969,
|
| 439 |
+
"step": 55
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.18181818181818182,
|
| 443 |
+
"grad_norm": 0.609375,
|
| 444 |
+
"learning_rate": 1.9973322836635517e-05,
|
| 445 |
+
"loss": 0.4032,
|
| 446 |
+
"step": 56
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.18506493506493507,
|
| 450 |
+
"grad_norm": 0.5859375,
|
| 451 |
+
"learning_rate": 1.9963695249188185e-05,
|
| 452 |
+
"loss": 0.3956,
|
| 453 |
+
"step": 57
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.18831168831168832,
|
| 457 |
+
"grad_norm": 0.57421875,
|
| 458 |
+
"learning_rate": 1.995259033893236e-05,
|
| 459 |
+
"loss": 0.3952,
|
| 460 |
+
"step": 58
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.19155844155844157,
|
| 464 |
+
"grad_norm": 0.59765625,
|
| 465 |
+
"learning_rate": 1.9940009752399462e-05,
|
| 466 |
+
"loss": 0.3905,
|
| 467 |
+
"step": 59
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.19480519480519481,
|
| 471 |
+
"grad_norm": 0.60546875,
|
| 472 |
+
"learning_rate": 1.9925955354920265e-05,
|
| 473 |
+
"loss": 0.3822,
|
| 474 |
+
"step": 60
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.19480519480519481,
|
| 478 |
+
"eval_loss": 0.38575297594070435,
|
| 479 |
+
"eval_model_preparation_time": 0.0003,
|
| 480 |
+
"eval_runtime": 174.9122,
|
| 481 |
+
"eval_samples_per_second": 11.886,
|
| 482 |
+
"eval_steps_per_second": 1.486,
|
| 483 |
+
"step": 60
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.19805194805194806,
|
| 487 |
+
"grad_norm": 0.5859375,
|
| 488 |
+
"learning_rate": 1.9910429230348348e-05,
|
| 489 |
+
"loss": 0.3976,
|
| 490 |
+
"step": 61
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.2012987012987013,
|
| 494 |
+
"grad_norm": 0.578125,
|
| 495 |
+
"learning_rate": 1.9893433680751105e-05,
|
| 496 |
+
"loss": 0.3714,
|
| 497 |
+
"step": 62
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 0.20454545454545456,
|
| 501 |
+
"grad_norm": 0.5859375,
|
| 502 |
+
"learning_rate": 1.9874971226068417e-05,
|
| 503 |
+
"loss": 0.3739,
|
| 504 |
+
"step": 63
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.2077922077922078,
|
| 508 |
+
"grad_norm": 0.5859375,
|
| 509 |
+
"learning_rate": 1.985504460373903e-05,
|
| 510 |
+
"loss": 0.3907,
|
| 511 |
+
"step": 64
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 0.21103896103896103,
|
| 515 |
+
"grad_norm": 0.609375,
|
| 516 |
+
"learning_rate": 1.983365676829466e-05,
|
| 517 |
+
"loss": 0.3803,
|
| 518 |
+
"step": 65
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.21428571428571427,
|
| 522 |
+
"grad_norm": 0.59765625,
|
| 523 |
+
"learning_rate": 1.9810810890921943e-05,
|
| 524 |
+
"loss": 0.3902,
|
| 525 |
+
"step": 66
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.21753246753246752,
|
| 529 |
+
"grad_norm": 0.578125,
|
| 530 |
+
"learning_rate": 1.9786510358992213e-05,
|
| 531 |
+
"loss": 0.3744,
|
| 532 |
+
"step": 67
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.22077922077922077,
|
| 536 |
+
"grad_norm": 0.56640625,
|
| 537 |
+
"learning_rate": 1.9760758775559275e-05,
|
| 538 |
+
"loss": 0.3668,
|
| 539 |
+
"step": 68
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.22402597402597402,
|
| 543 |
+
"grad_norm": 0.625,
|
| 544 |
+
"learning_rate": 1.9733559958825167e-05,
|
| 545 |
+
"loss": 0.3755,
|
| 546 |
+
"step": 69
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.22727272727272727,
|
| 550 |
+
"grad_norm": 0.60546875,
|
| 551 |
+
"learning_rate": 1.9704917941574053e-05,
|
| 552 |
+
"loss": 0.3733,
|
| 553 |
+
"step": 70
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.22727272727272727,
|
| 557 |
+
"eval_loss": 0.3694484233856201,
|
| 558 |
+
"eval_model_preparation_time": 0.0003,
|
| 559 |
+
"eval_runtime": 174.9363,
|
| 560 |
+
"eval_samples_per_second": 11.884,
|
| 561 |
+
"eval_steps_per_second": 1.486,
|
| 562 |
+
"step": 70
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.2305194805194805,
|
| 566 |
+
"grad_norm": 0.6015625,
|
| 567 |
+
"learning_rate": 1.9674836970574253e-05,
|
| 568 |
+
"loss": 0.3676,
|
| 569 |
+
"step": 71
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.23376623376623376,
|
| 573 |
+
"grad_norm": 0.60546875,
|
| 574 |
+
"learning_rate": 1.9643321505948588e-05,
|
| 575 |
+
"loss": 0.3721,
|
| 576 |
+
"step": 72
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.237012987012987,
|
| 580 |
+
"grad_norm": 0.60546875,
|
| 581 |
+
"learning_rate": 1.9610376220513067e-05,
|
| 582 |
+
"loss": 0.3558,
|
| 583 |
+
"step": 73
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.24025974025974026,
|
| 587 |
+
"grad_norm": 0.625,
|
| 588 |
+
"learning_rate": 1.957600599908406e-05,
|
| 589 |
+
"loss": 0.357,
|
| 590 |
+
"step": 74
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.2435064935064935,
|
| 594 |
+
"grad_norm": 0.66015625,
|
| 595 |
+
"learning_rate": 1.954021593775401e-05,
|
| 596 |
+
"loss": 0.3608,
|
| 597 |
+
"step": 75
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.24675324675324675,
|
| 601 |
+
"grad_norm": 0.59375,
|
| 602 |
+
"learning_rate": 1.9503011343135828e-05,
|
| 603 |
+
"loss": 0.3513,
|
| 604 |
+
"step": 76
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.25,
|
| 608 |
+
"grad_norm": 0.609375,
|
| 609 |
+
"learning_rate": 1.9464397731576093e-05,
|
| 610 |
+
"loss": 0.3693,
|
| 611 |
+
"step": 77
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.2532467532467532,
|
| 615 |
+
"grad_norm": 0.59375,
|
| 616 |
+
"learning_rate": 1.9424380828337146e-05,
|
| 617 |
+
"loss": 0.3605,
|
| 618 |
+
"step": 78
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.2564935064935065,
|
| 622 |
+
"grad_norm": 0.6171875,
|
| 623 |
+
"learning_rate": 1.938296656674817e-05,
|
| 624 |
+
"loss": 0.3553,
|
| 625 |
+
"step": 79
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.2597402597402597,
|
| 629 |
+
"grad_norm": 0.671875,
|
| 630 |
+
"learning_rate": 1.9340161087325483e-05,
|
| 631 |
+
"loss": 0.3721,
|
| 632 |
+
"step": 80
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.2597402597402597,
|
| 636 |
+
"eval_loss": 0.3553767800331116,
|
| 637 |
+
"eval_model_preparation_time": 0.0003,
|
| 638 |
+
"eval_runtime": 175.0277,
|
| 639 |
+
"eval_samples_per_second": 11.878,
|
| 640 |
+
"eval_steps_per_second": 1.485,
|
| 641 |
+
"step": 80
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.262987012987013,
|
| 645 |
+
"grad_norm": 0.609375,
|
| 646 |
+
"learning_rate": 1.9295970736862063e-05,
|
| 647 |
+
"loss": 0.3597,
|
| 648 |
+
"step": 81
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.2662337662337662,
|
| 652 |
+
"grad_norm": 0.65625,
|
| 653 |
+
"learning_rate": 1.9250402067486523e-05,
|
| 654 |
+
"loss": 0.3527,
|
| 655 |
+
"step": 82
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.2694805194805195,
|
| 659 |
+
"grad_norm": 0.61328125,
|
| 660 |
+
"learning_rate": 1.9203461835691596e-05,
|
| 661 |
+
"loss": 0.3528,
|
| 662 |
+
"step": 83
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.2727272727272727,
|
| 666 |
+
"grad_norm": 0.6640625,
|
| 667 |
+
"learning_rate": 1.9155157001332374e-05,
|
| 668 |
+
"loss": 0.356,
|
| 669 |
+
"step": 84
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.275974025974026,
|
| 673 |
+
"grad_norm": 0.6171875,
|
| 674 |
+
"learning_rate": 1.9105494726594344e-05,
|
| 675 |
+
"loss": 0.3556,
|
| 676 |
+
"step": 85
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.2792207792207792,
|
| 680 |
+
"grad_norm": 0.6171875,
|
| 681 |
+
"learning_rate": 1.905448237493147e-05,
|
| 682 |
+
"loss": 0.3473,
|
| 683 |
+
"step": 86
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.2824675324675325,
|
| 687 |
+
"grad_norm": 0.5859375,
|
| 688 |
+
"learning_rate": 1.9002127509974376e-05,
|
| 689 |
+
"loss": 0.3441,
|
| 690 |
+
"step": 87
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.2857142857142857,
|
| 694 |
+
"grad_norm": 0.6171875,
|
| 695 |
+
"learning_rate": 1.894843789440892e-05,
|
| 696 |
+
"loss": 0.3492,
|
| 697 |
+
"step": 88
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.288961038961039,
|
| 701 |
+
"grad_norm": 0.6328125,
|
| 702 |
+
"learning_rate": 1.889342148882519e-05,
|
| 703 |
+
"loss": 0.3338,
|
| 704 |
+
"step": 89
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.2922077922077922,
|
| 708 |
+
"grad_norm": 0.67578125,
|
| 709 |
+
"learning_rate": 1.8837086450537195e-05,
|
| 710 |
+
"loss": 0.3347,
|
| 711 |
+
"step": 90
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.2922077922077922,
|
| 715 |
+
"eval_loss": 0.34332525730133057,
|
| 716 |
+
"eval_model_preparation_time": 0.0003,
|
| 717 |
+
"eval_runtime": 174.9257,
|
| 718 |
+
"eval_samples_per_second": 11.885,
|
| 719 |
+
"eval_steps_per_second": 1.486,
|
| 720 |
+
"step": 90
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.29545454545454547,
|
| 724 |
+
"grad_norm": 0.6328125,
|
| 725 |
+
"learning_rate": 1.877944113237336e-05,
|
| 726 |
+
"loss": 0.3438,
|
| 727 |
+
"step": 91
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.2987012987012987,
|
| 731 |
+
"grad_norm": 0.6328125,
|
| 732 |
+
"learning_rate": 1.872049408143808e-05,
|
| 733 |
+
"loss": 0.3505,
|
| 734 |
+
"step": 92
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.30194805194805197,
|
| 738 |
+
"grad_norm": 0.6328125,
|
| 739 |
+
"learning_rate": 1.866025403784439e-05,
|
| 740 |
+
"loss": 0.3362,
|
| 741 |
+
"step": 93
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.3051948051948052,
|
| 745 |
+
"grad_norm": 0.640625,
|
| 746 |
+
"learning_rate": 1.8598729933418102e-05,
|
| 747 |
+
"loss": 0.337,
|
| 748 |
+
"step": 94
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 0.30844155844155846,
|
| 752 |
+
"grad_norm": 0.64453125,
|
| 753 |
+
"learning_rate": 1.8535930890373467e-05,
|
| 754 |
+
"loss": 0.3324,
|
| 755 |
+
"step": 95
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 0.3116883116883117,
|
| 759 |
+
"grad_norm": 0.6875,
|
| 760 |
+
"learning_rate": 1.8471866219960604e-05,
|
| 761 |
+
"loss": 0.3461,
|
| 762 |
+
"step": 96
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.31493506493506496,
|
| 766 |
+
"grad_norm": 0.6328125,
|
| 767 |
+
"learning_rate": 1.840654542108494e-05,
|
| 768 |
+
"loss": 0.3318,
|
| 769 |
+
"step": 97
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 0.3181818181818182,
|
| 773 |
+
"grad_norm": 0.62109375,
|
| 774 |
+
"learning_rate": 1.833997817889878e-05,
|
| 775 |
+
"loss": 0.3335,
|
| 776 |
+
"step": 98
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 0.32142857142857145,
|
| 780 |
+
"grad_norm": 0.61328125,
|
| 781 |
+
"learning_rate": 1.82721743633653e-05,
|
| 782 |
+
"loss": 0.3291,
|
| 783 |
+
"step": 99
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.3246753246753247,
|
| 787 |
+
"grad_norm": 0.6171875,
|
| 788 |
+
"learning_rate": 1.820314402779511e-05,
|
| 789 |
+
"loss": 0.3324,
|
| 790 |
+
"step": 100
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.3246753246753247,
|
| 794 |
+
"eval_loss": 0.33332687616348267,
|
| 795 |
+
"eval_model_preparation_time": 0.0003,
|
| 796 |
+
"eval_runtime": 174.9506,
|
| 797 |
+
"eval_samples_per_second": 11.883,
|
| 798 |
+
"eval_steps_per_second": 1.486,
|
| 799 |
+
"step": 100
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 0.32792207792207795,
|
| 803 |
+
"grad_norm": 0.6328125,
|
| 804 |
+
"learning_rate": 1.8132897407355657e-05,
|
| 805 |
+
"loss": 0.3288,
|
| 806 |
+
"step": 101
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 0.33116883116883117,
|
| 810 |
+
"grad_norm": 0.6484375,
|
| 811 |
+
"learning_rate": 1.806144491755363e-05,
|
| 812 |
+
"loss": 0.3384,
|
| 813 |
+
"step": 102
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.3344155844155844,
|
| 817 |
+
"grad_norm": 0.6328125,
|
| 818 |
+
"learning_rate": 1.798879715269067e-05,
|
| 819 |
+
"loss": 0.3329,
|
| 820 |
+
"step": 103
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 0.33766233766233766,
|
| 824 |
+
"grad_norm": 0.6171875,
|
| 825 |
+
"learning_rate": 1.7914964884292543e-05,
|
| 826 |
+
"loss": 0.3329,
|
| 827 |
+
"step": 104
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 0.3409090909090909,
|
| 831 |
+
"grad_norm": 0.671875,
|
| 832 |
+
"learning_rate": 1.7839959059512016e-05,
|
| 833 |
+
"loss": 0.3335,
|
| 834 |
+
"step": 105
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 0.34415584415584416,
|
| 838 |
+
"grad_norm": 0.609375,
|
| 839 |
+
"learning_rate": 1.7763790799505746e-05,
|
| 840 |
+
"loss": 0.3201,
|
| 841 |
+
"step": 106
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.3474025974025974,
|
| 845 |
+
"grad_norm": 0.6171875,
|
| 846 |
+
"learning_rate": 1.7686471397785322e-05,
|
| 847 |
+
"loss": 0.3327,
|
| 848 |
+
"step": 107
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 0.35064935064935066,
|
| 852 |
+
"grad_norm": 0.640625,
|
| 853 |
+
"learning_rate": 1.760801231854278e-05,
|
| 854 |
+
"loss": 0.3205,
|
| 855 |
+
"step": 108
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.3538961038961039,
|
| 859 |
+
"grad_norm": 0.6328125,
|
| 860 |
+
"learning_rate": 1.7528425194950794e-05,
|
| 861 |
+
"loss": 0.334,
|
| 862 |
+
"step": 109
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 0.35714285714285715,
|
| 866 |
+
"grad_norm": 0.6015625,
|
| 867 |
+
"learning_rate": 1.744772182743782e-05,
|
| 868 |
+
"loss": 0.3165,
|
| 869 |
+
"step": 110
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 0.35714285714285715,
|
| 873 |
+
"eval_loss": 0.32505103945732117,
|
| 874 |
+
"eval_model_preparation_time": 0.0003,
|
| 875 |
+
"eval_runtime": 175.0106,
|
| 876 |
+
"eval_samples_per_second": 11.879,
|
| 877 |
+
"eval_steps_per_second": 1.486,
|
| 878 |
+
"step": 110
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.36038961038961037,
|
| 882 |
+
"grad_norm": 0.62890625,
|
| 883 |
+
"learning_rate": 1.736591418193844e-05,
|
| 884 |
+
"loss": 0.3236,
|
| 885 |
+
"step": 111
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.36363636363636365,
|
| 889 |
+
"grad_norm": 0.63671875,
|
| 890 |
+
"learning_rate": 1.728301438811916e-05,
|
| 891 |
+
"loss": 0.3192,
|
| 892 |
+
"step": 112
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.36688311688311687,
|
| 896 |
+
"grad_norm": 0.6484375,
|
| 897 |
+
"learning_rate": 1.7199034737579962e-05,
|
| 898 |
+
"loss": 0.327,
|
| 899 |
+
"step": 113
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.37012987012987014,
|
| 903 |
+
"grad_norm": 0.62109375,
|
| 904 |
+
"learning_rate": 1.711398768203178e-05,
|
| 905 |
+
"loss": 0.3169,
|
| 906 |
+
"step": 114
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.37337662337662336,
|
| 910 |
+
"grad_norm": 0.625,
|
| 911 |
+
"learning_rate": 1.7027885831450318e-05,
|
| 912 |
+
"loss": 0.3186,
|
| 913 |
+
"step": 115
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.37662337662337664,
|
| 917 |
+
"grad_norm": 0.60546875,
|
| 918 |
+
"learning_rate": 1.6940741952206342e-05,
|
| 919 |
+
"loss": 0.3136,
|
| 920 |
+
"step": 116
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.37987012987012986,
|
| 924 |
+
"grad_norm": 0.62109375,
|
| 925 |
+
"learning_rate": 1.6852568965172794e-05,
|
| 926 |
+
"loss": 0.3184,
|
| 927 |
+
"step": 117
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.38311688311688313,
|
| 931 |
+
"grad_norm": 0.60546875,
|
| 932 |
+
"learning_rate": 1.676337994380903e-05,
|
| 933 |
+
"loss": 0.3114,
|
| 934 |
+
"step": 118
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.38636363636363635,
|
| 938 |
+
"grad_norm": 0.6640625,
|
| 939 |
+
"learning_rate": 1.6673188112222394e-05,
|
| 940 |
+
"loss": 0.3329,
|
| 941 |
+
"step": 119
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.38961038961038963,
|
| 945 |
+
"grad_norm": 0.60546875,
|
| 946 |
+
"learning_rate": 1.658200684320748e-05,
|
| 947 |
+
"loss": 0.3105,
|
| 948 |
+
"step": 120
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.38961038961038963,
|
| 952 |
+
"eval_loss": 0.31796982884407043,
|
| 953 |
+
"eval_model_preparation_time": 0.0003,
|
| 954 |
+
"eval_runtime": 174.9896,
|
| 955 |
+
"eval_samples_per_second": 11.881,
|
| 956 |
+
"eval_steps_per_second": 1.486,
|
| 957 |
+
"step": 120
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.39285714285714285,
|
| 961 |
+
"grad_norm": 0.58203125,
|
| 962 |
+
"learning_rate": 1.6489849656263336e-05,
|
| 963 |
+
"loss": 0.3084,
|
| 964 |
+
"step": 121
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.3961038961038961,
|
| 968 |
+
"grad_norm": 0.57421875,
|
| 969 |
+
"learning_rate": 1.6396730215588913e-05,
|
| 970 |
+
"loss": 0.3124,
|
| 971 |
+
"step": 122
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.39935064935064934,
|
| 975 |
+
"grad_norm": 0.609375,
|
| 976 |
+
"learning_rate": 1.630266232805709e-05,
|
| 977 |
+
"loss": 0.3167,
|
| 978 |
+
"step": 123
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.4025974025974026,
|
| 982 |
+
"grad_norm": 0.6171875,
|
| 983 |
+
"learning_rate": 1.6207659941167485e-05,
|
| 984 |
+
"loss": 0.3084,
|
| 985 |
+
"step": 124
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.40584415584415584,
|
| 989 |
+
"grad_norm": 0.62890625,
|
| 990 |
+
"learning_rate": 1.6111737140978495e-05,
|
| 991 |
+
"loss": 0.3143,
|
| 992 |
+
"step": 125
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.4090909090909091,
|
| 996 |
+
"grad_norm": 0.6171875,
|
| 997 |
+
"learning_rate": 1.6014908150018703e-05,
|
| 998 |
+
"loss": 0.3173,
|
| 999 |
+
"step": 126
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.41233766233766234,
|
| 1003 |
+
"grad_norm": 0.609375,
|
| 1004 |
+
"learning_rate": 1.591718732517814e-05,
|
| 1005 |
+
"loss": 0.3199,
|
| 1006 |
+
"step": 127
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.4155844155844156,
|
| 1010 |
+
"grad_norm": 0.609375,
|
| 1011 |
+
"learning_rate": 1.581858915557953e-05,
|
| 1012 |
+
"loss": 0.312,
|
| 1013 |
+
"step": 128
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.41883116883116883,
|
| 1017 |
+
"grad_norm": 0.61328125,
|
| 1018 |
+
"learning_rate": 1.571912826043003e-05,
|
| 1019 |
+
"loss": 0.3217,
|
| 1020 |
+
"step": 129
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.42207792207792205,
|
| 1024 |
+
"grad_norm": 0.59765625,
|
| 1025 |
+
"learning_rate": 1.5618819386853607e-05,
|
| 1026 |
+
"loss": 0.3123,
|
| 1027 |
+
"step": 130
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.42207792207792205,
|
| 1031 |
+
"eval_loss": 0.3119741976261139,
|
| 1032 |
+
"eval_model_preparation_time": 0.0003,
|
| 1033 |
+
"eval_runtime": 174.9669,
|
| 1034 |
+
"eval_samples_per_second": 11.882,
|
| 1035 |
+
"eval_steps_per_second": 1.486,
|
| 1036 |
+
"step": 130
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 0.4253246753246753,
|
| 1040 |
+
"grad_norm": 0.61328125,
|
| 1041 |
+
"learning_rate": 1.551767740770446e-05,
|
| 1042 |
+
"loss": 0.3088,
|
| 1043 |
+
"step": 131
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 0.42857142857142855,
|
| 1047 |
+
"grad_norm": 0.578125,
|
| 1048 |
+
"learning_rate": 1.541571731936185e-05,
|
| 1049 |
+
"loss": 0.3084,
|
| 1050 |
+
"step": 132
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 0.4318181818181818,
|
| 1054 |
+
"grad_norm": 0.6328125,
|
| 1055 |
+
"learning_rate": 1.5312954239506536e-05,
|
| 1056 |
+
"loss": 0.3179,
|
| 1057 |
+
"step": 133
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 0.43506493506493504,
|
| 1061 |
+
"grad_norm": 0.60546875,
|
| 1062 |
+
"learning_rate": 1.5209403404879305e-05,
|
| 1063 |
+
"loss": 0.3145,
|
| 1064 |
+
"step": 134
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 0.4383116883116883,
|
| 1068 |
+
"grad_norm": 0.59765625,
|
| 1069 |
+
"learning_rate": 1.5105080169021792e-05,
|
| 1070 |
+
"loss": 0.3045,
|
| 1071 |
+
"step": 135
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 0.44155844155844154,
|
| 1075 |
+
"grad_norm": 0.5859375,
|
| 1076 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 1077 |
+
"loss": 0.314,
|
| 1078 |
+
"step": 136
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 0.4448051948051948,
|
| 1082 |
+
"grad_norm": 0.6484375,
|
| 1083 |
+
"learning_rate": 1.4894178478110856e-05,
|
| 1084 |
+
"loss": 0.2985,
|
| 1085 |
+
"step": 137
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 0.44805194805194803,
|
| 1089 |
+
"grad_norm": 0.58984375,
|
| 1090 |
+
"learning_rate": 1.4787631293572094e-05,
|
| 1091 |
+
"loss": 0.3114,
|
| 1092 |
+
"step": 138
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 0.4512987012987013,
|
| 1096 |
+
"grad_norm": 0.60546875,
|
| 1097 |
+
"learning_rate": 1.4680374244195861e-05,
|
| 1098 |
+
"loss": 0.3129,
|
| 1099 |
+
"step": 139
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 0.45454545454545453,
|
| 1103 |
+
"grad_norm": 0.58984375,
|
| 1104 |
+
"learning_rate": 1.4572423233046386e-05,
|
| 1105 |
+
"loss": 0.3007,
|
| 1106 |
+
"step": 140
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 0.45454545454545453,
|
| 1110 |
+
"eval_loss": 0.30710509419441223,
|
| 1111 |
+
"eval_model_preparation_time": 0.0003,
|
| 1112 |
+
"eval_runtime": 174.9622,
|
| 1113 |
+
"eval_samples_per_second": 11.883,
|
| 1114 |
+
"eval_steps_per_second": 1.486,
|
| 1115 |
+
"step": 140
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.4577922077922078,
|
| 1119 |
+
"grad_norm": 0.58203125,
|
| 1120 |
+
"learning_rate": 1.4463794266081994e-05,
|
| 1121 |
+
"loss": 0.2981,
|
| 1122 |
+
"step": 141
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.461038961038961,
|
| 1126 |
+
"grad_norm": 0.5703125,
|
| 1127 |
+
"learning_rate": 1.4354503449781914e-05,
|
| 1128 |
+
"loss": 0.2974,
|
| 1129 |
+
"step": 142
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.4642857142857143,
|
| 1133 |
+
"grad_norm": 0.5859375,
|
| 1134 |
+
"learning_rate": 1.4244566988758152e-05,
|
| 1135 |
+
"loss": 0.3064,
|
| 1136 |
+
"step": 143
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.4675324675324675,
|
| 1140 |
+
"grad_norm": 0.56640625,
|
| 1141 |
+
"learning_rate": 1.4134001183352833e-05,
|
| 1142 |
+
"loss": 0.298,
|
| 1143 |
+
"step": 144
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.4707792207792208,
|
| 1147 |
+
"grad_norm": 0.5703125,
|
| 1148 |
+
"learning_rate": 1.4022822427221325e-05,
|
| 1149 |
+
"loss": 0.3037,
|
| 1150 |
+
"step": 145
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.474025974025974,
|
| 1154 |
+
"grad_norm": 0.58203125,
|
| 1155 |
+
"learning_rate": 1.391104720490156e-05,
|
| 1156 |
+
"loss": 0.3062,
|
| 1157 |
+
"step": 146
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.4772727272727273,
|
| 1161 |
+
"grad_norm": 0.609375,
|
| 1162 |
+
"learning_rate": 1.3798692089369855e-05,
|
| 1163 |
+
"loss": 0.3019,
|
| 1164 |
+
"step": 147
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.4805194805194805,
|
| 1168 |
+
"grad_norm": 0.61328125,
|
| 1169 |
+
"learning_rate": 1.368577373958362e-05,
|
| 1170 |
+
"loss": 0.3008,
|
| 1171 |
+
"step": 148
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.4837662337662338,
|
| 1175 |
+
"grad_norm": 0.56640625,
|
| 1176 |
+
"learning_rate": 1.3572308898011328e-05,
|
| 1177 |
+
"loss": 0.3055,
|
| 1178 |
+
"step": 149
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.487012987012987,
|
| 1182 |
+
"grad_norm": 0.5859375,
|
| 1183 |
+
"learning_rate": 1.3458314388150115e-05,
|
| 1184 |
+
"loss": 0.2942,
|
| 1185 |
+
"step": 150
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.487012987012987,
|
| 1189 |
+
"eval_loss": 0.30315953493118286,
|
| 1190 |
+
"eval_model_preparation_time": 0.0003,
|
| 1191 |
+
"eval_runtime": 174.9566,
|
| 1192 |
+
"eval_samples_per_second": 11.883,
|
| 1193 |
+
"eval_steps_per_second": 1.486,
|
| 1194 |
+
"step": 150
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 0.4902597402597403,
|
| 1198 |
+
"grad_norm": 0.578125,
|
| 1199 |
+
"learning_rate": 1.3343807112031329e-05,
|
| 1200 |
+
"loss": 0.3097,
|
| 1201 |
+
"step": 151
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 0.4935064935064935,
|
| 1205 |
+
"grad_norm": 0.56640625,
|
| 1206 |
+
"learning_rate": 1.3228804047714462e-05,
|
| 1207 |
+
"loss": 0.3004,
|
| 1208 |
+
"step": 152
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 0.4967532467532468,
|
| 1212 |
+
"grad_norm": 0.58203125,
|
| 1213 |
+
"learning_rate": 1.3113322246769817e-05,
|
| 1214 |
+
"loss": 0.3046,
|
| 1215 |
+
"step": 153
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 0.5,
|
| 1219 |
+
"grad_norm": 0.57421875,
|
| 1220 |
+
"learning_rate": 1.2997378831750242e-05,
|
| 1221 |
+
"loss": 0.2966,
|
| 1222 |
+
"step": 154
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 0.5032467532467533,
|
| 1226 |
+
"grad_norm": 0.5703125,
|
| 1227 |
+
"learning_rate": 1.2880990993652379e-05,
|
| 1228 |
+
"loss": 0.2989,
|
| 1229 |
+
"step": 155
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 0.5064935064935064,
|
| 1233 |
+
"grad_norm": 0.609375,
|
| 1234 |
+
"learning_rate": 1.2764175989367717e-05,
|
| 1235 |
+
"loss": 0.3015,
|
| 1236 |
+
"step": 156
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 0.5097402597402597,
|
| 1240 |
+
"grad_norm": 0.5703125,
|
| 1241 |
+
"learning_rate": 1.2646951139123935e-05,
|
| 1242 |
+
"loss": 0.2976,
|
| 1243 |
+
"step": 157
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 0.512987012987013,
|
| 1247 |
+
"grad_norm": 0.59765625,
|
| 1248 |
+
"learning_rate": 1.2529333823916807e-05,
|
| 1249 |
+
"loss": 0.2919,
|
| 1250 |
+
"step": 158
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 0.5162337662337663,
|
| 1254 |
+
"grad_norm": 0.6328125,
|
| 1255 |
+
"learning_rate": 1.241134148293311e-05,
|
| 1256 |
+
"loss": 0.3041,
|
| 1257 |
+
"step": 159
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 0.5194805194805194,
|
| 1261 |
+
"grad_norm": 0.58984375,
|
| 1262 |
+
"learning_rate": 1.2292991610964902e-05,
|
| 1263 |
+
"loss": 0.3053,
|
| 1264 |
+
"step": 160
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 0.5194805194805194,
|
| 1268 |
+
"eval_loss": 0.3000594675540924,
|
| 1269 |
+
"eval_model_preparation_time": 0.0003,
|
| 1270 |
+
"eval_runtime": 174.9643,
|
| 1271 |
+
"eval_samples_per_second": 11.882,
|
| 1272 |
+
"eval_steps_per_second": 1.486,
|
| 1273 |
+
"step": 160
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.5227272727272727,
|
| 1277 |
+
"grad_norm": 0.5859375,
|
| 1278 |
+
"learning_rate": 1.2174301755815572e-05,
|
| 1279 |
+
"loss": 0.3043,
|
| 1280 |
+
"step": 161
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.525974025974026,
|
| 1284 |
+
"grad_norm": 0.55859375,
|
| 1285 |
+
"learning_rate": 1.2055289515698008e-05,
|
| 1286 |
+
"loss": 0.2988,
|
| 1287 |
+
"step": 162
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.5292207792207793,
|
| 1291 |
+
"grad_norm": 0.5703125,
|
| 1292 |
+
"learning_rate": 1.1935972536625302e-05,
|
| 1293 |
+
"loss": 0.2871,
|
| 1294 |
+
"step": 163
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.5324675324675324,
|
| 1298 |
+
"grad_norm": 0.578125,
|
| 1299 |
+
"learning_rate": 1.1816368509794365e-05,
|
| 1300 |
+
"loss": 0.2985,
|
| 1301 |
+
"step": 164
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.5357142857142857,
|
| 1305 |
+
"grad_norm": 0.609375,
|
| 1306 |
+
"learning_rate": 1.1696495168962848e-05,
|
| 1307 |
+
"loss": 0.3066,
|
| 1308 |
+
"step": 165
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.538961038961039,
|
| 1312 |
+
"grad_norm": 0.57421875,
|
| 1313 |
+
"learning_rate": 1.1576370287819737e-05,
|
| 1314 |
+
"loss": 0.296,
|
| 1315 |
+
"step": 166
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.5422077922077922,
|
| 1319 |
+
"grad_norm": 0.59375,
|
| 1320 |
+
"learning_rate": 1.1456011677350052e-05,
|
| 1321 |
+
"loss": 0.2997,
|
| 1322 |
+
"step": 167
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.5454545454545454,
|
| 1326 |
+
"grad_norm": 0.58984375,
|
| 1327 |
+
"learning_rate": 1.133543718319398e-05,
|
| 1328 |
+
"loss": 0.3011,
|
| 1329 |
+
"step": 168
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.5487012987012987,
|
| 1333 |
+
"grad_norm": 0.5703125,
|
| 1334 |
+
"learning_rate": 1.1214664683000927e-05,
|
| 1335 |
+
"loss": 0.2898,
|
| 1336 |
+
"step": 169
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.551948051948052,
|
| 1340 |
+
"grad_norm": 0.58203125,
|
| 1341 |
+
"learning_rate": 1.1093712083778748e-05,
|
| 1342 |
+
"loss": 0.292,
|
| 1343 |
+
"step": 170
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.551948051948052,
|
| 1347 |
+
"eval_loss": 0.29717138409614563,
|
| 1348 |
+
"eval_model_preparation_time": 0.0003,
|
| 1349 |
+
"eval_runtime": 174.9869,
|
| 1350 |
+
"eval_samples_per_second": 11.881,
|
| 1351 |
+
"eval_steps_per_second": 1.486,
|
| 1352 |
+
"step": 170
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 0.5551948051948052,
|
| 1356 |
+
"grad_norm": 0.578125,
|
| 1357 |
+
"learning_rate": 1.0972597319238692e-05,
|
| 1358 |
+
"loss": 0.2995,
|
| 1359 |
+
"step": 171
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 0.5584415584415584,
|
| 1363 |
+
"grad_norm": 0.58984375,
|
| 1364 |
+
"learning_rate": 1.0851338347136358e-05,
|
| 1365 |
+
"loss": 0.3015,
|
| 1366 |
+
"step": 172
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 0.5616883116883117,
|
| 1370 |
+
"grad_norm": 0.5625,
|
| 1371 |
+
"learning_rate": 1.0729953146609076e-05,
|
| 1372 |
+
"loss": 0.2953,
|
| 1373 |
+
"step": 173
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 0.564935064935065,
|
| 1377 |
+
"grad_norm": 0.55859375,
|
| 1378 |
+
"learning_rate": 1.060845971551014e-05,
|
| 1379 |
+
"loss": 0.3011,
|
| 1380 |
+
"step": 174
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 0.5681818181818182,
|
| 1384 |
+
"grad_norm": 0.58984375,
|
| 1385 |
+
"learning_rate": 1.0486876067740253e-05,
|
| 1386 |
+
"loss": 0.3016,
|
| 1387 |
+
"step": 175
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 0.5714285714285714,
|
| 1391 |
+
"grad_norm": 0.5859375,
|
| 1392 |
+
"learning_rate": 1.0365220230576592e-05,
|
| 1393 |
+
"loss": 0.2953,
|
| 1394 |
+
"step": 176
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 0.5746753246753247,
|
| 1398 |
+
"grad_norm": 0.5625,
|
| 1399 |
+
"learning_rate": 1.0243510241999898e-05,
|
| 1400 |
+
"loss": 0.2948,
|
| 1401 |
+
"step": 177
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 0.577922077922078,
|
| 1405 |
+
"grad_norm": 0.5703125,
|
| 1406 |
+
"learning_rate": 1.0121764148019977e-05,
|
| 1407 |
+
"loss": 0.2958,
|
| 1408 |
+
"step": 178
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 0.5811688311688312,
|
| 1412 |
+
"grad_norm": 0.5546875,
|
| 1413 |
+
"learning_rate": 1e-05,
|
| 1414 |
+
"loss": 0.2829,
|
| 1415 |
+
"step": 179
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"epoch": 0.5844155844155844,
|
| 1419 |
+
"grad_norm": 0.58203125,
|
| 1420 |
+
"learning_rate": 9.878235851980027e-06,
|
| 1421 |
+
"loss": 0.2917,
|
| 1422 |
+
"step": 180
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"epoch": 0.5844155844155844,
|
| 1426 |
+
"eval_loss": 0.29469791054725647,
|
| 1427 |
+
"eval_model_preparation_time": 0.0003,
|
| 1428 |
+
"eval_runtime": 174.9839,
|
| 1429 |
+
"eval_samples_per_second": 11.881,
|
| 1430 |
+
"eval_steps_per_second": 1.486,
|
| 1431 |
+
"step": 180
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.5876623376623377,
|
| 1435 |
+
"grad_norm": 0.59375,
|
| 1436 |
+
"learning_rate": 9.756489758000105e-06,
|
| 1437 |
+
"loss": 0.2994,
|
| 1438 |
+
"step": 181
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.5909090909090909,
|
| 1442 |
+
"grad_norm": 0.57421875,
|
| 1443 |
+
"learning_rate": 9.634779769423412e-06,
|
| 1444 |
+
"loss": 0.3054,
|
| 1445 |
+
"step": 182
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.5941558441558441,
|
| 1449 |
+
"grad_norm": 0.59375,
|
| 1450 |
+
"learning_rate": 9.51312393225975e-06,
|
| 1451 |
+
"loss": 0.2925,
|
| 1452 |
+
"step": 183
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.5974025974025974,
|
| 1456 |
+
"grad_norm": 0.5703125,
|
| 1457 |
+
"learning_rate": 9.391540284489862e-06,
|
| 1458 |
+
"loss": 0.2816,
|
| 1459 |
+
"step": 184
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.6006493506493507,
|
| 1463 |
+
"grad_norm": 0.5390625,
|
| 1464 |
+
"learning_rate": 9.270046853390924e-06,
|
| 1465 |
+
"loss": 0.2856,
|
| 1466 |
+
"step": 185
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.6038961038961039,
|
| 1470 |
+
"grad_norm": 0.5703125,
|
| 1471 |
+
"learning_rate": 9.148661652863644e-06,
|
| 1472 |
+
"loss": 0.2936,
|
| 1473 |
+
"step": 186
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.6071428571428571,
|
| 1477 |
+
"grad_norm": 0.55078125,
|
| 1478 |
+
"learning_rate": 9.02740268076131e-06,
|
| 1479 |
+
"loss": 0.2938,
|
| 1480 |
+
"step": 187
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.6103896103896104,
|
| 1484 |
+
"grad_norm": 0.5859375,
|
| 1485 |
+
"learning_rate": 8.906287916221259e-06,
|
| 1486 |
+
"loss": 0.3017,
|
| 1487 |
+
"step": 188
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.6136363636363636,
|
| 1491 |
+
"grad_norm": 0.578125,
|
| 1492 |
+
"learning_rate": 8.785335316999078e-06,
|
| 1493 |
+
"loss": 0.2957,
|
| 1494 |
+
"step": 189
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.6168831168831169,
|
| 1498 |
+
"grad_norm": 0.58203125,
|
| 1499 |
+
"learning_rate": 8.664562816806022e-06,
|
| 1500 |
+
"loss": 0.2961,
|
| 1501 |
+
"step": 190
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.6168831168831169,
|
| 1505 |
+
"eval_loss": 0.2927069365978241,
|
| 1506 |
+
"eval_model_preparation_time": 0.0003,
|
| 1507 |
+
"eval_runtime": 174.9405,
|
| 1508 |
+
"eval_samples_per_second": 11.884,
|
| 1509 |
+
"eval_steps_per_second": 1.486,
|
| 1510 |
+
"step": 190
|
| 1511 |
+
},
|
| 1512 |
+
{
|
| 1513 |
+
"epoch": 0.6201298701298701,
|
| 1514 |
+
"grad_norm": 0.58203125,
|
| 1515 |
+
"learning_rate": 8.543988322649954e-06,
|
| 1516 |
+
"loss": 0.2915,
|
| 1517 |
+
"step": 191
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 0.6233766233766234,
|
| 1521 |
+
"grad_norm": 0.57421875,
|
| 1522 |
+
"learning_rate": 8.423629712180265e-06,
|
| 1523 |
+
"loss": 0.2875,
|
| 1524 |
+
"step": 192
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 0.6266233766233766,
|
| 1528 |
+
"grad_norm": 0.5703125,
|
| 1529 |
+
"learning_rate": 8.303504831037154e-06,
|
| 1530 |
+
"loss": 0.2979,
|
| 1531 |
+
"step": 193
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 0.6298701298701299,
|
| 1535 |
+
"grad_norm": 0.5703125,
|
| 1536 |
+
"learning_rate": 8.183631490205636e-06,
|
| 1537 |
+
"loss": 0.2891,
|
| 1538 |
+
"step": 194
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 0.6331168831168831,
|
| 1542 |
+
"grad_norm": 0.5703125,
|
| 1543 |
+
"learning_rate": 8.064027463374702e-06,
|
| 1544 |
+
"loss": 0.2796,
|
| 1545 |
+
"step": 195
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 0.6363636363636364,
|
| 1549 |
+
"grad_norm": 0.57421875,
|
| 1550 |
+
"learning_rate": 7.944710484301995e-06,
|
| 1551 |
+
"loss": 0.285,
|
| 1552 |
+
"step": 196
|
| 1553 |
+
},
|
| 1554 |
+
{
|
| 1555 |
+
"epoch": 0.6396103896103896,
|
| 1556 |
+
"grad_norm": 0.58203125,
|
| 1557 |
+
"learning_rate": 7.825698244184432e-06,
|
| 1558 |
+
"loss": 0.295,
|
| 1559 |
+
"step": 197
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 0.6428571428571429,
|
| 1563 |
+
"grad_norm": 0.57421875,
|
| 1564 |
+
"learning_rate": 7.707008389035102e-06,
|
| 1565 |
+
"loss": 0.2962,
|
| 1566 |
+
"step": 198
|
| 1567 |
+
},
|
| 1568 |
+
{
|
| 1569 |
+
"epoch": 0.6461038961038961,
|
| 1570 |
+
"grad_norm": 0.57421875,
|
| 1571 |
+
"learning_rate": 7.588658517066893e-06,
|
| 1572 |
+
"loss": 0.2912,
|
| 1573 |
+
"step": 199
|
| 1574 |
+
},
|
| 1575 |
+
{
|
| 1576 |
+
"epoch": 0.6493506493506493,
|
| 1577 |
+
"grad_norm": 0.57421875,
|
| 1578 |
+
"learning_rate": 7.470666176083193e-06,
|
| 1579 |
+
"loss": 0.2917,
|
| 1580 |
+
"step": 200
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 0.6493506493506493,
|
| 1584 |
+
"eval_loss": 0.2912693917751312,
|
| 1585 |
+
"eval_model_preparation_time": 0.0003,
|
| 1586 |
+
"eval_runtime": 174.9875,
|
| 1587 |
+
"eval_samples_per_second": 11.881,
|
| 1588 |
+
"eval_steps_per_second": 1.486,
|
| 1589 |
+
"step": 200
|
| 1590 |
+
}
|
| 1591 |
+
],
|
| 1592 |
+
"logging_steps": 1,
|
| 1593 |
+
"max_steps": 308,
|
| 1594 |
+
"num_input_tokens_seen": 0,
|
| 1595 |
+
"num_train_epochs": 1,
|
| 1596 |
+
"save_steps": 100,
|
| 1597 |
+
"stateful_callbacks": {
|
| 1598 |
+
"TrainerControl": {
|
| 1599 |
+
"args": {
|
| 1600 |
+
"should_epoch_stop": false,
|
| 1601 |
+
"should_evaluate": false,
|
| 1602 |
+
"should_log": false,
|
| 1603 |
+
"should_save": true,
|
| 1604 |
+
"should_training_stop": false
|
| 1605 |
+
},
|
| 1606 |
+
"attributes": {}
|
| 1607 |
+
}
|
| 1608 |
+
},
|
| 1609 |
+
"total_flos": 1.1804225839300608e+18,
|
| 1610 |
+
"train_batch_size": 8,
|
| 1611 |
+
"trial_name": null,
|
| 1612 |
+
"trial_params": null
|
| 1613 |
+
}
|
checkpoint-200/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d09f69be12f7ef607f0a1508435a517f5277e3160e5d6a59346e619fcbaa3592
|
| 3 |
+
size 5176
|
checkpoint-300/config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8b621112eddc9da772fae3f70d672f4d949cc5cb1d580f135d66b3836598c1a
|
| 3 |
+
size 915
|
checkpoint-300/generation_config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7327788370b7783e29852cf19b4a1f40cd31af5962c94bba76c336d491b4169
|
| 3 |
+
size 184
|
checkpoint-300/model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29a3907a94d16ee63bb35418803792e2e7faf7479e9a0ba6c5b6faf863b4007d
|
| 3 |
+
size 4976698672
|
checkpoint-300/model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ed5d4c274155ab7efb36612cbbb7e548c1b6b6fdb0e8ef136061e0c5b26b129
|
| 3 |
+
size 4999802720
|
checkpoint-300/model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b06c1356e06091e7d05ca40b62cd7a438c1abb71c6e182bd479804b9bf04e4e2
|
| 3 |
+
size 4915916176
|
checkpoint-300/model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eeb6b9ac5806653b828e732fba12471ef3f300d4d9daa99da11f1cf958f76402
|
| 3 |
+
size 1168138808
|
checkpoint-300/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:146776fce3f6db1103aa6f249e65ee5544c5923ce6f971b092eee79aa6e5d37b
|
| 3 |
+
size 23950
|
checkpoint-300/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee6d30131aec5e4206a28344f043ab4470213fc7de969421738254b908eb6f93
|
| 3 |
+
size 32121299754
|
checkpoint-300/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:374644995be79c967030295cf4e5929f6a33d3b1197b8855bc39718b44686552
|
| 3 |
+
size 14244
|
checkpoint-300/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:892afc48e852cff639a2b1d3faa9e143f11c0af53826ffadf88b7d4e636251cb
|
| 3 |
+
size 1064
|
checkpoint-300/special_tokens_map.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b1835caa5b4d70acaa210fa222b0036f1882f9525c4660fd4810fb3e1e40ff8
|
| 3 |
+
size 325
|
checkpoint-300/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79e3e522635f3171300913bb421464a87de6222182a0570b9b2ccba2a964b2b4
|
| 3 |
+
size 9085657
|
checkpoint-300/tokenizer_config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:05d0de6d831b5940c3f2eae4e495b9f77612cbb05b5804846733ab617f0dfe9b
|
| 3 |
+
size 55380
|
checkpoint-300/trainer_state.json
ADDED
|
@@ -0,0 +1,2403 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.974025974025974,
|
| 5 |
+
"eval_steps": 10,
|
| 6 |
+
"global_step": 300,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.003246753246753247,
|
| 13 |
+
"grad_norm": 16.375,
|
| 14 |
+
"learning_rate": 4.0000000000000003e-07,
|
| 15 |
+
"loss": 1.4017,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.006493506493506494,
|
| 20 |
+
"grad_norm": 16.25,
|
| 21 |
+
"learning_rate": 8.000000000000001e-07,
|
| 22 |
+
"loss": 1.4229,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.00974025974025974,
|
| 27 |
+
"grad_norm": 16.75,
|
| 28 |
+
"learning_rate": 1.2000000000000002e-06,
|
| 29 |
+
"loss": 1.4112,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.012987012987012988,
|
| 34 |
+
"grad_norm": 16.5,
|
| 35 |
+
"learning_rate": 1.6000000000000001e-06,
|
| 36 |
+
"loss": 1.3959,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.016233766233766232,
|
| 41 |
+
"grad_norm": 16.125,
|
| 42 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 43 |
+
"loss": 1.3789,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.01948051948051948,
|
| 48 |
+
"grad_norm": 14.4375,
|
| 49 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 50 |
+
"loss": 1.3618,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.022727272727272728,
|
| 55 |
+
"grad_norm": 10.1875,
|
| 56 |
+
"learning_rate": 2.8000000000000003e-06,
|
| 57 |
+
"loss": 1.3214,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.025974025974025976,
|
| 62 |
+
"grad_norm": 7.4375,
|
| 63 |
+
"learning_rate": 3.2000000000000003e-06,
|
| 64 |
+
"loss": 1.2885,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.02922077922077922,
|
| 69 |
+
"grad_norm": 6.28125,
|
| 70 |
+
"learning_rate": 3.6000000000000003e-06,
|
| 71 |
+
"loss": 1.2436,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.032467532467532464,
|
| 76 |
+
"grad_norm": 5.75,
|
| 77 |
+
"learning_rate": 4.000000000000001e-06,
|
| 78 |
+
"loss": 1.2269,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.032467532467532464,
|
| 83 |
+
"eval_loss": 1.1976113319396973,
|
| 84 |
+
"eval_model_preparation_time": 0.0003,
|
| 85 |
+
"eval_runtime": 175.0273,
|
| 86 |
+
"eval_samples_per_second": 11.878,
|
| 87 |
+
"eval_steps_per_second": 1.485,
|
| 88 |
+
"step": 10
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.03571428571428571,
|
| 92 |
+
"grad_norm": 5.375,
|
| 93 |
+
"learning_rate": 4.4e-06,
|
| 94 |
+
"loss": 1.1925,
|
| 95 |
+
"step": 11
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.03896103896103896,
|
| 99 |
+
"grad_norm": 5.125,
|
| 100 |
+
"learning_rate": 4.800000000000001e-06,
|
| 101 |
+
"loss": 1.1307,
|
| 102 |
+
"step": 12
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.04220779220779221,
|
| 106 |
+
"grad_norm": 5.125,
|
| 107 |
+
"learning_rate": 5.2e-06,
|
| 108 |
+
"loss": 1.0778,
|
| 109 |
+
"step": 13
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.045454545454545456,
|
| 113 |
+
"grad_norm": 5.0625,
|
| 114 |
+
"learning_rate": 5.600000000000001e-06,
|
| 115 |
+
"loss": 1.0067,
|
| 116 |
+
"step": 14
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.048701298701298704,
|
| 120 |
+
"grad_norm": 5.75,
|
| 121 |
+
"learning_rate": 6e-06,
|
| 122 |
+
"loss": 0.9668,
|
| 123 |
+
"step": 15
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.05194805194805195,
|
| 127 |
+
"grad_norm": 5.15625,
|
| 128 |
+
"learning_rate": 6.4000000000000006e-06,
|
| 129 |
+
"loss": 0.875,
|
| 130 |
+
"step": 16
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.05519480519480519,
|
| 134 |
+
"grad_norm": 4.875,
|
| 135 |
+
"learning_rate": 6.800000000000001e-06,
|
| 136 |
+
"loss": 0.8297,
|
| 137 |
+
"step": 17
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.05844155844155844,
|
| 141 |
+
"grad_norm": 4.5625,
|
| 142 |
+
"learning_rate": 7.2000000000000005e-06,
|
| 143 |
+
"loss": 0.7703,
|
| 144 |
+
"step": 18
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.06168831168831169,
|
| 148 |
+
"grad_norm": 3.90625,
|
| 149 |
+
"learning_rate": 7.600000000000001e-06,
|
| 150 |
+
"loss": 0.7327,
|
| 151 |
+
"step": 19
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.06493506493506493,
|
| 155 |
+
"grad_norm": 2.78125,
|
| 156 |
+
"learning_rate": 8.000000000000001e-06,
|
| 157 |
+
"loss": 0.6672,
|
| 158 |
+
"step": 20
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.06493506493506493,
|
| 162 |
+
"eval_loss": 0.6521233320236206,
|
| 163 |
+
"eval_model_preparation_time": 0.0003,
|
| 164 |
+
"eval_runtime": 174.999,
|
| 165 |
+
"eval_samples_per_second": 11.88,
|
| 166 |
+
"eval_steps_per_second": 1.486,
|
| 167 |
+
"step": 20
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.06818181818181818,
|
| 171 |
+
"grad_norm": 2.140625,
|
| 172 |
+
"learning_rate": 8.400000000000001e-06,
|
| 173 |
+
"loss": 0.6507,
|
| 174 |
+
"step": 21
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.07142857142857142,
|
| 178 |
+
"grad_norm": 1.828125,
|
| 179 |
+
"learning_rate": 8.8e-06,
|
| 180 |
+
"loss": 0.6215,
|
| 181 |
+
"step": 22
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.07467532467532467,
|
| 185 |
+
"grad_norm": 1.5546875,
|
| 186 |
+
"learning_rate": 9.200000000000002e-06,
|
| 187 |
+
"loss": 0.5992,
|
| 188 |
+
"step": 23
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.07792207792207792,
|
| 192 |
+
"grad_norm": 1.4453125,
|
| 193 |
+
"learning_rate": 9.600000000000001e-06,
|
| 194 |
+
"loss": 0.5748,
|
| 195 |
+
"step": 24
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.08116883116883117,
|
| 199 |
+
"grad_norm": 1.328125,
|
| 200 |
+
"learning_rate": 1e-05,
|
| 201 |
+
"loss": 0.5572,
|
| 202 |
+
"step": 25
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.08441558441558442,
|
| 206 |
+
"grad_norm": 1.4765625,
|
| 207 |
+
"learning_rate": 1.04e-05,
|
| 208 |
+
"loss": 0.542,
|
| 209 |
+
"step": 26
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.08766233766233766,
|
| 213 |
+
"grad_norm": 1.1171875,
|
| 214 |
+
"learning_rate": 1.0800000000000002e-05,
|
| 215 |
+
"loss": 0.5317,
|
| 216 |
+
"step": 27
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.09090909090909091,
|
| 220 |
+
"grad_norm": 0.90625,
|
| 221 |
+
"learning_rate": 1.1200000000000001e-05,
|
| 222 |
+
"loss": 0.5173,
|
| 223 |
+
"step": 28
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 0.09415584415584416,
|
| 227 |
+
"grad_norm": 0.83984375,
|
| 228 |
+
"learning_rate": 1.16e-05,
|
| 229 |
+
"loss": 0.4892,
|
| 230 |
+
"step": 29
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.09740259740259741,
|
| 234 |
+
"grad_norm": 0.828125,
|
| 235 |
+
"learning_rate": 1.2e-05,
|
| 236 |
+
"loss": 0.491,
|
| 237 |
+
"step": 30
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.09740259740259741,
|
| 241 |
+
"eval_loss": 0.48583006858825684,
|
| 242 |
+
"eval_model_preparation_time": 0.0003,
|
| 243 |
+
"eval_runtime": 174.9705,
|
| 244 |
+
"eval_samples_per_second": 11.882,
|
| 245 |
+
"eval_steps_per_second": 1.486,
|
| 246 |
+
"step": 30
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.10064935064935066,
|
| 250 |
+
"grad_norm": 0.8359375,
|
| 251 |
+
"learning_rate": 1.2400000000000002e-05,
|
| 252 |
+
"loss": 0.4852,
|
| 253 |
+
"step": 31
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.1038961038961039,
|
| 257 |
+
"grad_norm": 1.0078125,
|
| 258 |
+
"learning_rate": 1.2800000000000001e-05,
|
| 259 |
+
"loss": 0.4749,
|
| 260 |
+
"step": 32
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.10714285714285714,
|
| 264 |
+
"grad_norm": 0.99609375,
|
| 265 |
+
"learning_rate": 1.3200000000000002e-05,
|
| 266 |
+
"loss": 0.467,
|
| 267 |
+
"step": 33
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.11038961038961038,
|
| 271 |
+
"grad_norm": 0.734375,
|
| 272 |
+
"learning_rate": 1.3600000000000002e-05,
|
| 273 |
+
"loss": 0.4545,
|
| 274 |
+
"step": 34
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.11363636363636363,
|
| 278 |
+
"grad_norm": 0.69140625,
|
| 279 |
+
"learning_rate": 1.4e-05,
|
| 280 |
+
"loss": 0.4609,
|
| 281 |
+
"step": 35
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.11688311688311688,
|
| 285 |
+
"grad_norm": 0.69921875,
|
| 286 |
+
"learning_rate": 1.4400000000000001e-05,
|
| 287 |
+
"loss": 0.4497,
|
| 288 |
+
"step": 36
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.12012987012987013,
|
| 292 |
+
"grad_norm": 0.703125,
|
| 293 |
+
"learning_rate": 1.48e-05,
|
| 294 |
+
"loss": 0.4607,
|
| 295 |
+
"step": 37
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.12337662337662338,
|
| 299 |
+
"grad_norm": 0.6328125,
|
| 300 |
+
"learning_rate": 1.5200000000000002e-05,
|
| 301 |
+
"loss": 0.443,
|
| 302 |
+
"step": 38
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.1266233766233766,
|
| 306 |
+
"grad_norm": 0.65234375,
|
| 307 |
+
"learning_rate": 1.5600000000000003e-05,
|
| 308 |
+
"loss": 0.4428,
|
| 309 |
+
"step": 39
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.12987012987012986,
|
| 313 |
+
"grad_norm": 0.640625,
|
| 314 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 315 |
+
"loss": 0.435,
|
| 316 |
+
"step": 40
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.12987012987012986,
|
| 320 |
+
"eval_loss": 0.4367639422416687,
|
| 321 |
+
"eval_model_preparation_time": 0.0003,
|
| 322 |
+
"eval_runtime": 175.0177,
|
| 323 |
+
"eval_samples_per_second": 11.879,
|
| 324 |
+
"eval_steps_per_second": 1.486,
|
| 325 |
+
"step": 40
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.1331168831168831,
|
| 329 |
+
"grad_norm": 0.671875,
|
| 330 |
+
"learning_rate": 1.64e-05,
|
| 331 |
+
"loss": 0.438,
|
| 332 |
+
"step": 41
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.13636363636363635,
|
| 336 |
+
"grad_norm": 0.6484375,
|
| 337 |
+
"learning_rate": 1.6800000000000002e-05,
|
| 338 |
+
"loss": 0.4392,
|
| 339 |
+
"step": 42
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.1396103896103896,
|
| 343 |
+
"grad_norm": 0.65234375,
|
| 344 |
+
"learning_rate": 1.72e-05,
|
| 345 |
+
"loss": 0.435,
|
| 346 |
+
"step": 43
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.14285714285714285,
|
| 350 |
+
"grad_norm": 0.62109375,
|
| 351 |
+
"learning_rate": 1.76e-05,
|
| 352 |
+
"loss": 0.4356,
|
| 353 |
+
"step": 44
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.1461038961038961,
|
| 357 |
+
"grad_norm": 0.6171875,
|
| 358 |
+
"learning_rate": 1.8e-05,
|
| 359 |
+
"loss": 0.4172,
|
| 360 |
+
"step": 45
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.14935064935064934,
|
| 364 |
+
"grad_norm": 0.6015625,
|
| 365 |
+
"learning_rate": 1.8400000000000003e-05,
|
| 366 |
+
"loss": 0.4162,
|
| 367 |
+
"step": 46
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.1525974025974026,
|
| 371 |
+
"grad_norm": 0.609375,
|
| 372 |
+
"learning_rate": 1.88e-05,
|
| 373 |
+
"loss": 0.418,
|
| 374 |
+
"step": 47
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.15584415584415584,
|
| 378 |
+
"grad_norm": 0.6328125,
|
| 379 |
+
"learning_rate": 1.9200000000000003e-05,
|
| 380 |
+
"loss": 0.4177,
|
| 381 |
+
"step": 48
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.1590909090909091,
|
| 385 |
+
"grad_norm": 0.6171875,
|
| 386 |
+
"learning_rate": 1.9600000000000002e-05,
|
| 387 |
+
"loss": 0.4064,
|
| 388 |
+
"step": 49
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.16233766233766234,
|
| 392 |
+
"grad_norm": 0.62890625,
|
| 393 |
+
"learning_rate": 2e-05,
|
| 394 |
+
"loss": 0.4078,
|
| 395 |
+
"step": 50
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.16233766233766234,
|
| 399 |
+
"eval_loss": 0.4077843129634857,
|
| 400 |
+
"eval_model_preparation_time": 0.0003,
|
| 401 |
+
"eval_runtime": 174.8482,
|
| 402 |
+
"eval_samples_per_second": 11.89,
|
| 403 |
+
"eval_steps_per_second": 1.487,
|
| 404 |
+
"step": 50
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.16558441558441558,
|
| 408 |
+
"grad_norm": 0.61328125,
|
| 409 |
+
"learning_rate": 1.9999258647132645e-05,
|
| 410 |
+
"loss": 0.4057,
|
| 411 |
+
"step": 51
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.16883116883116883,
|
| 415 |
+
"grad_norm": 0.62890625,
|
| 416 |
+
"learning_rate": 1.9997034698451396e-05,
|
| 417 |
+
"loss": 0.4172,
|
| 418 |
+
"step": 52
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.17207792207792208,
|
| 422 |
+
"grad_norm": 0.61328125,
|
| 423 |
+
"learning_rate": 1.9993328483702393e-05,
|
| 424 |
+
"loss": 0.4082,
|
| 425 |
+
"step": 53
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.17532467532467533,
|
| 429 |
+
"grad_norm": 0.59375,
|
| 430 |
+
"learning_rate": 1.998814055240823e-05,
|
| 431 |
+
"loss": 0.3973,
|
| 432 |
+
"step": 54
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.17857142857142858,
|
| 436 |
+
"grad_norm": 0.59375,
|
| 437 |
+
"learning_rate": 1.998147167378645e-05,
|
| 438 |
+
"loss": 0.3969,
|
| 439 |
+
"step": 55
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.18181818181818182,
|
| 443 |
+
"grad_norm": 0.609375,
|
| 444 |
+
"learning_rate": 1.9973322836635517e-05,
|
| 445 |
+
"loss": 0.4032,
|
| 446 |
+
"step": 56
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.18506493506493507,
|
| 450 |
+
"grad_norm": 0.5859375,
|
| 451 |
+
"learning_rate": 1.9963695249188185e-05,
|
| 452 |
+
"loss": 0.3956,
|
| 453 |
+
"step": 57
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.18831168831168832,
|
| 457 |
+
"grad_norm": 0.57421875,
|
| 458 |
+
"learning_rate": 1.995259033893236e-05,
|
| 459 |
+
"loss": 0.3952,
|
| 460 |
+
"step": 58
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.19155844155844157,
|
| 464 |
+
"grad_norm": 0.59765625,
|
| 465 |
+
"learning_rate": 1.9940009752399462e-05,
|
| 466 |
+
"loss": 0.3905,
|
| 467 |
+
"step": 59
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.19480519480519481,
|
| 471 |
+
"grad_norm": 0.60546875,
|
| 472 |
+
"learning_rate": 1.9925955354920265e-05,
|
| 473 |
+
"loss": 0.3822,
|
| 474 |
+
"step": 60
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.19480519480519481,
|
| 478 |
+
"eval_loss": 0.38575297594070435,
|
| 479 |
+
"eval_model_preparation_time": 0.0003,
|
| 480 |
+
"eval_runtime": 174.9122,
|
| 481 |
+
"eval_samples_per_second": 11.886,
|
| 482 |
+
"eval_steps_per_second": 1.486,
|
| 483 |
+
"step": 60
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.19805194805194806,
|
| 487 |
+
"grad_norm": 0.5859375,
|
| 488 |
+
"learning_rate": 1.9910429230348348e-05,
|
| 489 |
+
"loss": 0.3976,
|
| 490 |
+
"step": 61
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.2012987012987013,
|
| 494 |
+
"grad_norm": 0.578125,
|
| 495 |
+
"learning_rate": 1.9893433680751105e-05,
|
| 496 |
+
"loss": 0.3714,
|
| 497 |
+
"step": 62
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 0.20454545454545456,
|
| 501 |
+
"grad_norm": 0.5859375,
|
| 502 |
+
"learning_rate": 1.9874971226068417e-05,
|
| 503 |
+
"loss": 0.3739,
|
| 504 |
+
"step": 63
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.2077922077922078,
|
| 508 |
+
"grad_norm": 0.5859375,
|
| 509 |
+
"learning_rate": 1.985504460373903e-05,
|
| 510 |
+
"loss": 0.3907,
|
| 511 |
+
"step": 64
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 0.21103896103896103,
|
| 515 |
+
"grad_norm": 0.609375,
|
| 516 |
+
"learning_rate": 1.983365676829466e-05,
|
| 517 |
+
"loss": 0.3803,
|
| 518 |
+
"step": 65
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.21428571428571427,
|
| 522 |
+
"grad_norm": 0.59765625,
|
| 523 |
+
"learning_rate": 1.9810810890921943e-05,
|
| 524 |
+
"loss": 0.3902,
|
| 525 |
+
"step": 66
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.21753246753246752,
|
| 529 |
+
"grad_norm": 0.578125,
|
| 530 |
+
"learning_rate": 1.9786510358992213e-05,
|
| 531 |
+
"loss": 0.3744,
|
| 532 |
+
"step": 67
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.22077922077922077,
|
| 536 |
+
"grad_norm": 0.56640625,
|
| 537 |
+
"learning_rate": 1.9760758775559275e-05,
|
| 538 |
+
"loss": 0.3668,
|
| 539 |
+
"step": 68
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.22402597402597402,
|
| 543 |
+
"grad_norm": 0.625,
|
| 544 |
+
"learning_rate": 1.9733559958825167e-05,
|
| 545 |
+
"loss": 0.3755,
|
| 546 |
+
"step": 69
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.22727272727272727,
|
| 550 |
+
"grad_norm": 0.60546875,
|
| 551 |
+
"learning_rate": 1.9704917941574053e-05,
|
| 552 |
+
"loss": 0.3733,
|
| 553 |
+
"step": 70
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.22727272727272727,
|
| 557 |
+
"eval_loss": 0.3694484233856201,
|
| 558 |
+
"eval_model_preparation_time": 0.0003,
|
| 559 |
+
"eval_runtime": 174.9363,
|
| 560 |
+
"eval_samples_per_second": 11.884,
|
| 561 |
+
"eval_steps_per_second": 1.486,
|
| 562 |
+
"step": 70
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.2305194805194805,
|
| 566 |
+
"grad_norm": 0.6015625,
|
| 567 |
+
"learning_rate": 1.9674836970574253e-05,
|
| 568 |
+
"loss": 0.3676,
|
| 569 |
+
"step": 71
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.23376623376623376,
|
| 573 |
+
"grad_norm": 0.60546875,
|
| 574 |
+
"learning_rate": 1.9643321505948588e-05,
|
| 575 |
+
"loss": 0.3721,
|
| 576 |
+
"step": 72
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.237012987012987,
|
| 580 |
+
"grad_norm": 0.60546875,
|
| 581 |
+
"learning_rate": 1.9610376220513067e-05,
|
| 582 |
+
"loss": 0.3558,
|
| 583 |
+
"step": 73
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.24025974025974026,
|
| 587 |
+
"grad_norm": 0.625,
|
| 588 |
+
"learning_rate": 1.957600599908406e-05,
|
| 589 |
+
"loss": 0.357,
|
| 590 |
+
"step": 74
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.2435064935064935,
|
| 594 |
+
"grad_norm": 0.66015625,
|
| 595 |
+
"learning_rate": 1.954021593775401e-05,
|
| 596 |
+
"loss": 0.3608,
|
| 597 |
+
"step": 75
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.24675324675324675,
|
| 601 |
+
"grad_norm": 0.59375,
|
| 602 |
+
"learning_rate": 1.9503011343135828e-05,
|
| 603 |
+
"loss": 0.3513,
|
| 604 |
+
"step": 76
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.25,
|
| 608 |
+
"grad_norm": 0.609375,
|
| 609 |
+
"learning_rate": 1.9464397731576093e-05,
|
| 610 |
+
"loss": 0.3693,
|
| 611 |
+
"step": 77
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.2532467532467532,
|
| 615 |
+
"grad_norm": 0.59375,
|
| 616 |
+
"learning_rate": 1.9424380828337146e-05,
|
| 617 |
+
"loss": 0.3605,
|
| 618 |
+
"step": 78
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.2564935064935065,
|
| 622 |
+
"grad_norm": 0.6171875,
|
| 623 |
+
"learning_rate": 1.938296656674817e-05,
|
| 624 |
+
"loss": 0.3553,
|
| 625 |
+
"step": 79
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.2597402597402597,
|
| 629 |
+
"grad_norm": 0.671875,
|
| 630 |
+
"learning_rate": 1.9340161087325483e-05,
|
| 631 |
+
"loss": 0.3721,
|
| 632 |
+
"step": 80
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.2597402597402597,
|
| 636 |
+
"eval_loss": 0.3553767800331116,
|
| 637 |
+
"eval_model_preparation_time": 0.0003,
|
| 638 |
+
"eval_runtime": 175.0277,
|
| 639 |
+
"eval_samples_per_second": 11.878,
|
| 640 |
+
"eval_steps_per_second": 1.485,
|
| 641 |
+
"step": 80
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.262987012987013,
|
| 645 |
+
"grad_norm": 0.609375,
|
| 646 |
+
"learning_rate": 1.9295970736862063e-05,
|
| 647 |
+
"loss": 0.3597,
|
| 648 |
+
"step": 81
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.2662337662337662,
|
| 652 |
+
"grad_norm": 0.65625,
|
| 653 |
+
"learning_rate": 1.9250402067486523e-05,
|
| 654 |
+
"loss": 0.3527,
|
| 655 |
+
"step": 82
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.2694805194805195,
|
| 659 |
+
"grad_norm": 0.61328125,
|
| 660 |
+
"learning_rate": 1.9203461835691596e-05,
|
| 661 |
+
"loss": 0.3528,
|
| 662 |
+
"step": 83
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.2727272727272727,
|
| 666 |
+
"grad_norm": 0.6640625,
|
| 667 |
+
"learning_rate": 1.9155157001332374e-05,
|
| 668 |
+
"loss": 0.356,
|
| 669 |
+
"step": 84
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.275974025974026,
|
| 673 |
+
"grad_norm": 0.6171875,
|
| 674 |
+
"learning_rate": 1.9105494726594344e-05,
|
| 675 |
+
"loss": 0.3556,
|
| 676 |
+
"step": 85
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.2792207792207792,
|
| 680 |
+
"grad_norm": 0.6171875,
|
| 681 |
+
"learning_rate": 1.905448237493147e-05,
|
| 682 |
+
"loss": 0.3473,
|
| 683 |
+
"step": 86
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.2824675324675325,
|
| 687 |
+
"grad_norm": 0.5859375,
|
| 688 |
+
"learning_rate": 1.9002127509974376e-05,
|
| 689 |
+
"loss": 0.3441,
|
| 690 |
+
"step": 87
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.2857142857142857,
|
| 694 |
+
"grad_norm": 0.6171875,
|
| 695 |
+
"learning_rate": 1.894843789440892e-05,
|
| 696 |
+
"loss": 0.3492,
|
| 697 |
+
"step": 88
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.288961038961039,
|
| 701 |
+
"grad_norm": 0.6328125,
|
| 702 |
+
"learning_rate": 1.889342148882519e-05,
|
| 703 |
+
"loss": 0.3338,
|
| 704 |
+
"step": 89
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.2922077922077922,
|
| 708 |
+
"grad_norm": 0.67578125,
|
| 709 |
+
"learning_rate": 1.8837086450537195e-05,
|
| 710 |
+
"loss": 0.3347,
|
| 711 |
+
"step": 90
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.2922077922077922,
|
| 715 |
+
"eval_loss": 0.34332525730133057,
|
| 716 |
+
"eval_model_preparation_time": 0.0003,
|
| 717 |
+
"eval_runtime": 174.9257,
|
| 718 |
+
"eval_samples_per_second": 11.885,
|
| 719 |
+
"eval_steps_per_second": 1.486,
|
| 720 |
+
"step": 90
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.29545454545454547,
|
| 724 |
+
"grad_norm": 0.6328125,
|
| 725 |
+
"learning_rate": 1.877944113237336e-05,
|
| 726 |
+
"loss": 0.3438,
|
| 727 |
+
"step": 91
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.2987012987012987,
|
| 731 |
+
"grad_norm": 0.6328125,
|
| 732 |
+
"learning_rate": 1.872049408143808e-05,
|
| 733 |
+
"loss": 0.3505,
|
| 734 |
+
"step": 92
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.30194805194805197,
|
| 738 |
+
"grad_norm": 0.6328125,
|
| 739 |
+
"learning_rate": 1.866025403784439e-05,
|
| 740 |
+
"loss": 0.3362,
|
| 741 |
+
"step": 93
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.3051948051948052,
|
| 745 |
+
"grad_norm": 0.640625,
|
| 746 |
+
"learning_rate": 1.8598729933418102e-05,
|
| 747 |
+
"loss": 0.337,
|
| 748 |
+
"step": 94
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 0.30844155844155846,
|
| 752 |
+
"grad_norm": 0.64453125,
|
| 753 |
+
"learning_rate": 1.8535930890373467e-05,
|
| 754 |
+
"loss": 0.3324,
|
| 755 |
+
"step": 95
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 0.3116883116883117,
|
| 759 |
+
"grad_norm": 0.6875,
|
| 760 |
+
"learning_rate": 1.8471866219960604e-05,
|
| 761 |
+
"loss": 0.3461,
|
| 762 |
+
"step": 96
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.31493506493506496,
|
| 766 |
+
"grad_norm": 0.6328125,
|
| 767 |
+
"learning_rate": 1.840654542108494e-05,
|
| 768 |
+
"loss": 0.3318,
|
| 769 |
+
"step": 97
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 0.3181818181818182,
|
| 773 |
+
"grad_norm": 0.62109375,
|
| 774 |
+
"learning_rate": 1.833997817889878e-05,
|
| 775 |
+
"loss": 0.3335,
|
| 776 |
+
"step": 98
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 0.32142857142857145,
|
| 780 |
+
"grad_norm": 0.61328125,
|
| 781 |
+
"learning_rate": 1.82721743633653e-05,
|
| 782 |
+
"loss": 0.3291,
|
| 783 |
+
"step": 99
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.3246753246753247,
|
| 787 |
+
"grad_norm": 0.6171875,
|
| 788 |
+
"learning_rate": 1.820314402779511e-05,
|
| 789 |
+
"loss": 0.3324,
|
| 790 |
+
"step": 100
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.3246753246753247,
|
| 794 |
+
"eval_loss": 0.33332687616348267,
|
| 795 |
+
"eval_model_preparation_time": 0.0003,
|
| 796 |
+
"eval_runtime": 174.9506,
|
| 797 |
+
"eval_samples_per_second": 11.883,
|
| 798 |
+
"eval_steps_per_second": 1.486,
|
| 799 |
+
"step": 100
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 0.32792207792207795,
|
| 803 |
+
"grad_norm": 0.6328125,
|
| 804 |
+
"learning_rate": 1.8132897407355657e-05,
|
| 805 |
+
"loss": 0.3288,
|
| 806 |
+
"step": 101
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 0.33116883116883117,
|
| 810 |
+
"grad_norm": 0.6484375,
|
| 811 |
+
"learning_rate": 1.806144491755363e-05,
|
| 812 |
+
"loss": 0.3384,
|
| 813 |
+
"step": 102
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.3344155844155844,
|
| 817 |
+
"grad_norm": 0.6328125,
|
| 818 |
+
"learning_rate": 1.798879715269067e-05,
|
| 819 |
+
"loss": 0.3329,
|
| 820 |
+
"step": 103
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 0.33766233766233766,
|
| 824 |
+
"grad_norm": 0.6171875,
|
| 825 |
+
"learning_rate": 1.7914964884292543e-05,
|
| 826 |
+
"loss": 0.3329,
|
| 827 |
+
"step": 104
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 0.3409090909090909,
|
| 831 |
+
"grad_norm": 0.671875,
|
| 832 |
+
"learning_rate": 1.7839959059512016e-05,
|
| 833 |
+
"loss": 0.3335,
|
| 834 |
+
"step": 105
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 0.34415584415584416,
|
| 838 |
+
"grad_norm": 0.609375,
|
| 839 |
+
"learning_rate": 1.7763790799505746e-05,
|
| 840 |
+
"loss": 0.3201,
|
| 841 |
+
"step": 106
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.3474025974025974,
|
| 845 |
+
"grad_norm": 0.6171875,
|
| 846 |
+
"learning_rate": 1.7686471397785322e-05,
|
| 847 |
+
"loss": 0.3327,
|
| 848 |
+
"step": 107
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 0.35064935064935066,
|
| 852 |
+
"grad_norm": 0.640625,
|
| 853 |
+
"learning_rate": 1.760801231854278e-05,
|
| 854 |
+
"loss": 0.3205,
|
| 855 |
+
"step": 108
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.3538961038961039,
|
| 859 |
+
"grad_norm": 0.6328125,
|
| 860 |
+
"learning_rate": 1.7528425194950794e-05,
|
| 861 |
+
"loss": 0.334,
|
| 862 |
+
"step": 109
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 0.35714285714285715,
|
| 866 |
+
"grad_norm": 0.6015625,
|
| 867 |
+
"learning_rate": 1.744772182743782e-05,
|
| 868 |
+
"loss": 0.3165,
|
| 869 |
+
"step": 110
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 0.35714285714285715,
|
| 873 |
+
"eval_loss": 0.32505103945732117,
|
| 874 |
+
"eval_model_preparation_time": 0.0003,
|
| 875 |
+
"eval_runtime": 175.0106,
|
| 876 |
+
"eval_samples_per_second": 11.879,
|
| 877 |
+
"eval_steps_per_second": 1.486,
|
| 878 |
+
"step": 110
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.36038961038961037,
|
| 882 |
+
"grad_norm": 0.62890625,
|
| 883 |
+
"learning_rate": 1.736591418193844e-05,
|
| 884 |
+
"loss": 0.3236,
|
| 885 |
+
"step": 111
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.36363636363636365,
|
| 889 |
+
"grad_norm": 0.63671875,
|
| 890 |
+
"learning_rate": 1.728301438811916e-05,
|
| 891 |
+
"loss": 0.3192,
|
| 892 |
+
"step": 112
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.36688311688311687,
|
| 896 |
+
"grad_norm": 0.6484375,
|
| 897 |
+
"learning_rate": 1.7199034737579962e-05,
|
| 898 |
+
"loss": 0.327,
|
| 899 |
+
"step": 113
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.37012987012987014,
|
| 903 |
+
"grad_norm": 0.62109375,
|
| 904 |
+
"learning_rate": 1.711398768203178e-05,
|
| 905 |
+
"loss": 0.3169,
|
| 906 |
+
"step": 114
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.37337662337662336,
|
| 910 |
+
"grad_norm": 0.625,
|
| 911 |
+
"learning_rate": 1.7027885831450318e-05,
|
| 912 |
+
"loss": 0.3186,
|
| 913 |
+
"step": 115
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.37662337662337664,
|
| 917 |
+
"grad_norm": 0.60546875,
|
| 918 |
+
"learning_rate": 1.6940741952206342e-05,
|
| 919 |
+
"loss": 0.3136,
|
| 920 |
+
"step": 116
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.37987012987012986,
|
| 924 |
+
"grad_norm": 0.62109375,
|
| 925 |
+
"learning_rate": 1.6852568965172794e-05,
|
| 926 |
+
"loss": 0.3184,
|
| 927 |
+
"step": 117
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.38311688311688313,
|
| 931 |
+
"grad_norm": 0.60546875,
|
| 932 |
+
"learning_rate": 1.676337994380903e-05,
|
| 933 |
+
"loss": 0.3114,
|
| 934 |
+
"step": 118
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.38636363636363635,
|
| 938 |
+
"grad_norm": 0.6640625,
|
| 939 |
+
"learning_rate": 1.6673188112222394e-05,
|
| 940 |
+
"loss": 0.3329,
|
| 941 |
+
"step": 119
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.38961038961038963,
|
| 945 |
+
"grad_norm": 0.60546875,
|
| 946 |
+
"learning_rate": 1.658200684320748e-05,
|
| 947 |
+
"loss": 0.3105,
|
| 948 |
+
"step": 120
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.38961038961038963,
|
| 952 |
+
"eval_loss": 0.31796982884407043,
|
| 953 |
+
"eval_model_preparation_time": 0.0003,
|
| 954 |
+
"eval_runtime": 174.9896,
|
| 955 |
+
"eval_samples_per_second": 11.881,
|
| 956 |
+
"eval_steps_per_second": 1.486,
|
| 957 |
+
"step": 120
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.39285714285714285,
|
| 961 |
+
"grad_norm": 0.58203125,
|
| 962 |
+
"learning_rate": 1.6489849656263336e-05,
|
| 963 |
+
"loss": 0.3084,
|
| 964 |
+
"step": 121
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.3961038961038961,
|
| 968 |
+
"grad_norm": 0.57421875,
|
| 969 |
+
"learning_rate": 1.6396730215588913e-05,
|
| 970 |
+
"loss": 0.3124,
|
| 971 |
+
"step": 122
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.39935064935064934,
|
| 975 |
+
"grad_norm": 0.609375,
|
| 976 |
+
"learning_rate": 1.630266232805709e-05,
|
| 977 |
+
"loss": 0.3167,
|
| 978 |
+
"step": 123
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.4025974025974026,
|
| 982 |
+
"grad_norm": 0.6171875,
|
| 983 |
+
"learning_rate": 1.6207659941167485e-05,
|
| 984 |
+
"loss": 0.3084,
|
| 985 |
+
"step": 124
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.40584415584415584,
|
| 989 |
+
"grad_norm": 0.62890625,
|
| 990 |
+
"learning_rate": 1.6111737140978495e-05,
|
| 991 |
+
"loss": 0.3143,
|
| 992 |
+
"step": 125
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.4090909090909091,
|
| 996 |
+
"grad_norm": 0.6171875,
|
| 997 |
+
"learning_rate": 1.6014908150018703e-05,
|
| 998 |
+
"loss": 0.3173,
|
| 999 |
+
"step": 126
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.41233766233766234,
|
| 1003 |
+
"grad_norm": 0.609375,
|
| 1004 |
+
"learning_rate": 1.591718732517814e-05,
|
| 1005 |
+
"loss": 0.3199,
|
| 1006 |
+
"step": 127
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.4155844155844156,
|
| 1010 |
+
"grad_norm": 0.609375,
|
| 1011 |
+
"learning_rate": 1.581858915557953e-05,
|
| 1012 |
+
"loss": 0.312,
|
| 1013 |
+
"step": 128
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.41883116883116883,
|
| 1017 |
+
"grad_norm": 0.61328125,
|
| 1018 |
+
"learning_rate": 1.571912826043003e-05,
|
| 1019 |
+
"loss": 0.3217,
|
| 1020 |
+
"step": 129
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.42207792207792205,
|
| 1024 |
+
"grad_norm": 0.59765625,
|
| 1025 |
+
"learning_rate": 1.5618819386853607e-05,
|
| 1026 |
+
"loss": 0.3123,
|
| 1027 |
+
"step": 130
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.42207792207792205,
|
| 1031 |
+
"eval_loss": 0.3119741976261139,
|
| 1032 |
+
"eval_model_preparation_time": 0.0003,
|
| 1033 |
+
"eval_runtime": 174.9669,
|
| 1034 |
+
"eval_samples_per_second": 11.882,
|
| 1035 |
+
"eval_steps_per_second": 1.486,
|
| 1036 |
+
"step": 130
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 0.4253246753246753,
|
| 1040 |
+
"grad_norm": 0.61328125,
|
| 1041 |
+
"learning_rate": 1.551767740770446e-05,
|
| 1042 |
+
"loss": 0.3088,
|
| 1043 |
+
"step": 131
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 0.42857142857142855,
|
| 1047 |
+
"grad_norm": 0.578125,
|
| 1048 |
+
"learning_rate": 1.541571731936185e-05,
|
| 1049 |
+
"loss": 0.3084,
|
| 1050 |
+
"step": 132
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 0.4318181818181818,
|
| 1054 |
+
"grad_norm": 0.6328125,
|
| 1055 |
+
"learning_rate": 1.5312954239506536e-05,
|
| 1056 |
+
"loss": 0.3179,
|
| 1057 |
+
"step": 133
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 0.43506493506493504,
|
| 1061 |
+
"grad_norm": 0.60546875,
|
| 1062 |
+
"learning_rate": 1.5209403404879305e-05,
|
| 1063 |
+
"loss": 0.3145,
|
| 1064 |
+
"step": 134
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 0.4383116883116883,
|
| 1068 |
+
"grad_norm": 0.59765625,
|
| 1069 |
+
"learning_rate": 1.5105080169021792e-05,
|
| 1070 |
+
"loss": 0.3045,
|
| 1071 |
+
"step": 135
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 0.44155844155844154,
|
| 1075 |
+
"grad_norm": 0.5859375,
|
| 1076 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 1077 |
+
"loss": 0.314,
|
| 1078 |
+
"step": 136
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 0.4448051948051948,
|
| 1082 |
+
"grad_norm": 0.6484375,
|
| 1083 |
+
"learning_rate": 1.4894178478110856e-05,
|
| 1084 |
+
"loss": 0.2985,
|
| 1085 |
+
"step": 137
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 0.44805194805194803,
|
| 1089 |
+
"grad_norm": 0.58984375,
|
| 1090 |
+
"learning_rate": 1.4787631293572094e-05,
|
| 1091 |
+
"loss": 0.3114,
|
| 1092 |
+
"step": 138
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 0.4512987012987013,
|
| 1096 |
+
"grad_norm": 0.60546875,
|
| 1097 |
+
"learning_rate": 1.4680374244195861e-05,
|
| 1098 |
+
"loss": 0.3129,
|
| 1099 |
+
"step": 139
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 0.45454545454545453,
|
| 1103 |
+
"grad_norm": 0.58984375,
|
| 1104 |
+
"learning_rate": 1.4572423233046386e-05,
|
| 1105 |
+
"loss": 0.3007,
|
| 1106 |
+
"step": 140
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 0.45454545454545453,
|
| 1110 |
+
"eval_loss": 0.30710509419441223,
|
| 1111 |
+
"eval_model_preparation_time": 0.0003,
|
| 1112 |
+
"eval_runtime": 174.9622,
|
| 1113 |
+
"eval_samples_per_second": 11.883,
|
| 1114 |
+
"eval_steps_per_second": 1.486,
|
| 1115 |
+
"step": 140
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.4577922077922078,
|
| 1119 |
+
"grad_norm": 0.58203125,
|
| 1120 |
+
"learning_rate": 1.4463794266081994e-05,
|
| 1121 |
+
"loss": 0.2981,
|
| 1122 |
+
"step": 141
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.461038961038961,
|
| 1126 |
+
"grad_norm": 0.5703125,
|
| 1127 |
+
"learning_rate": 1.4354503449781914e-05,
|
| 1128 |
+
"loss": 0.2974,
|
| 1129 |
+
"step": 142
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.4642857142857143,
|
| 1133 |
+
"grad_norm": 0.5859375,
|
| 1134 |
+
"learning_rate": 1.4244566988758152e-05,
|
| 1135 |
+
"loss": 0.3064,
|
| 1136 |
+
"step": 143
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.4675324675324675,
|
| 1140 |
+
"grad_norm": 0.56640625,
|
| 1141 |
+
"learning_rate": 1.4134001183352833e-05,
|
| 1142 |
+
"loss": 0.298,
|
| 1143 |
+
"step": 144
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.4707792207792208,
|
| 1147 |
+
"grad_norm": 0.5703125,
|
| 1148 |
+
"learning_rate": 1.4022822427221325e-05,
|
| 1149 |
+
"loss": 0.3037,
|
| 1150 |
+
"step": 145
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.474025974025974,
|
| 1154 |
+
"grad_norm": 0.58203125,
|
| 1155 |
+
"learning_rate": 1.391104720490156e-05,
|
| 1156 |
+
"loss": 0.3062,
|
| 1157 |
+
"step": 146
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.4772727272727273,
|
| 1161 |
+
"grad_norm": 0.609375,
|
| 1162 |
+
"learning_rate": 1.3798692089369855e-05,
|
| 1163 |
+
"loss": 0.3019,
|
| 1164 |
+
"step": 147
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.4805194805194805,
|
| 1168 |
+
"grad_norm": 0.61328125,
|
| 1169 |
+
"learning_rate": 1.368577373958362e-05,
|
| 1170 |
+
"loss": 0.3008,
|
| 1171 |
+
"step": 148
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.4837662337662338,
|
| 1175 |
+
"grad_norm": 0.56640625,
|
| 1176 |
+
"learning_rate": 1.3572308898011328e-05,
|
| 1177 |
+
"loss": 0.3055,
|
| 1178 |
+
"step": 149
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.487012987012987,
|
| 1182 |
+
"grad_norm": 0.5859375,
|
| 1183 |
+
"learning_rate": 1.3458314388150115e-05,
|
| 1184 |
+
"loss": 0.2942,
|
| 1185 |
+
"step": 150
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.487012987012987,
|
| 1189 |
+
"eval_loss": 0.30315953493118286,
|
| 1190 |
+
"eval_model_preparation_time": 0.0003,
|
| 1191 |
+
"eval_runtime": 174.9566,
|
| 1192 |
+
"eval_samples_per_second": 11.883,
|
| 1193 |
+
"eval_steps_per_second": 1.486,
|
| 1194 |
+
"step": 150
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 0.4902597402597403,
|
| 1198 |
+
"grad_norm": 0.578125,
|
| 1199 |
+
"learning_rate": 1.3343807112031329e-05,
|
| 1200 |
+
"loss": 0.3097,
|
| 1201 |
+
"step": 151
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 0.4935064935064935,
|
| 1205 |
+
"grad_norm": 0.56640625,
|
| 1206 |
+
"learning_rate": 1.3228804047714462e-05,
|
| 1207 |
+
"loss": 0.3004,
|
| 1208 |
+
"step": 152
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 0.4967532467532468,
|
| 1212 |
+
"grad_norm": 0.58203125,
|
| 1213 |
+
"learning_rate": 1.3113322246769817e-05,
|
| 1214 |
+
"loss": 0.3046,
|
| 1215 |
+
"step": 153
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 0.5,
|
| 1219 |
+
"grad_norm": 0.57421875,
|
| 1220 |
+
"learning_rate": 1.2997378831750242e-05,
|
| 1221 |
+
"loss": 0.2966,
|
| 1222 |
+
"step": 154
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 0.5032467532467533,
|
| 1226 |
+
"grad_norm": 0.5703125,
|
| 1227 |
+
"learning_rate": 1.2880990993652379e-05,
|
| 1228 |
+
"loss": 0.2989,
|
| 1229 |
+
"step": 155
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 0.5064935064935064,
|
| 1233 |
+
"grad_norm": 0.609375,
|
| 1234 |
+
"learning_rate": 1.2764175989367717e-05,
|
| 1235 |
+
"loss": 0.3015,
|
| 1236 |
+
"step": 156
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 0.5097402597402597,
|
| 1240 |
+
"grad_norm": 0.5703125,
|
| 1241 |
+
"learning_rate": 1.2646951139123935e-05,
|
| 1242 |
+
"loss": 0.2976,
|
| 1243 |
+
"step": 157
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 0.512987012987013,
|
| 1247 |
+
"grad_norm": 0.59765625,
|
| 1248 |
+
"learning_rate": 1.2529333823916807e-05,
|
| 1249 |
+
"loss": 0.2919,
|
| 1250 |
+
"step": 158
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 0.5162337662337663,
|
| 1254 |
+
"grad_norm": 0.6328125,
|
| 1255 |
+
"learning_rate": 1.241134148293311e-05,
|
| 1256 |
+
"loss": 0.3041,
|
| 1257 |
+
"step": 159
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 0.5194805194805194,
|
| 1261 |
+
"grad_norm": 0.58984375,
|
| 1262 |
+
"learning_rate": 1.2292991610964902e-05,
|
| 1263 |
+
"loss": 0.3053,
|
| 1264 |
+
"step": 160
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 0.5194805194805194,
|
| 1268 |
+
"eval_loss": 0.3000594675540924,
|
| 1269 |
+
"eval_model_preparation_time": 0.0003,
|
| 1270 |
+
"eval_runtime": 174.9643,
|
| 1271 |
+
"eval_samples_per_second": 11.882,
|
| 1272 |
+
"eval_steps_per_second": 1.486,
|
| 1273 |
+
"step": 160
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.5227272727272727,
|
| 1277 |
+
"grad_norm": 0.5859375,
|
| 1278 |
+
"learning_rate": 1.2174301755815572e-05,
|
| 1279 |
+
"loss": 0.3043,
|
| 1280 |
+
"step": 161
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.525974025974026,
|
| 1284 |
+
"grad_norm": 0.55859375,
|
| 1285 |
+
"learning_rate": 1.2055289515698008e-05,
|
| 1286 |
+
"loss": 0.2988,
|
| 1287 |
+
"step": 162
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.5292207792207793,
|
| 1291 |
+
"grad_norm": 0.5703125,
|
| 1292 |
+
"learning_rate": 1.1935972536625302e-05,
|
| 1293 |
+
"loss": 0.2871,
|
| 1294 |
+
"step": 163
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.5324675324675324,
|
| 1298 |
+
"grad_norm": 0.578125,
|
| 1299 |
+
"learning_rate": 1.1816368509794365e-05,
|
| 1300 |
+
"loss": 0.2985,
|
| 1301 |
+
"step": 164
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.5357142857142857,
|
| 1305 |
+
"grad_norm": 0.609375,
|
| 1306 |
+
"learning_rate": 1.1696495168962848e-05,
|
| 1307 |
+
"loss": 0.3066,
|
| 1308 |
+
"step": 165
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.538961038961039,
|
| 1312 |
+
"grad_norm": 0.57421875,
|
| 1313 |
+
"learning_rate": 1.1576370287819737e-05,
|
| 1314 |
+
"loss": 0.296,
|
| 1315 |
+
"step": 166
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.5422077922077922,
|
| 1319 |
+
"grad_norm": 0.59375,
|
| 1320 |
+
"learning_rate": 1.1456011677350052e-05,
|
| 1321 |
+
"loss": 0.2997,
|
| 1322 |
+
"step": 167
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.5454545454545454,
|
| 1326 |
+
"grad_norm": 0.58984375,
|
| 1327 |
+
"learning_rate": 1.133543718319398e-05,
|
| 1328 |
+
"loss": 0.3011,
|
| 1329 |
+
"step": 168
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.5487012987012987,
|
| 1333 |
+
"grad_norm": 0.5703125,
|
| 1334 |
+
"learning_rate": 1.1214664683000927e-05,
|
| 1335 |
+
"loss": 0.2898,
|
| 1336 |
+
"step": 169
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.551948051948052,
|
| 1340 |
+
"grad_norm": 0.58203125,
|
| 1341 |
+
"learning_rate": 1.1093712083778748e-05,
|
| 1342 |
+
"loss": 0.292,
|
| 1343 |
+
"step": 170
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.551948051948052,
|
| 1347 |
+
"eval_loss": 0.29717138409614563,
|
| 1348 |
+
"eval_model_preparation_time": 0.0003,
|
| 1349 |
+
"eval_runtime": 174.9869,
|
| 1350 |
+
"eval_samples_per_second": 11.881,
|
| 1351 |
+
"eval_steps_per_second": 1.486,
|
| 1352 |
+
"step": 170
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 0.5551948051948052,
|
| 1356 |
+
"grad_norm": 0.578125,
|
| 1357 |
+
"learning_rate": 1.0972597319238692e-05,
|
| 1358 |
+
"loss": 0.2995,
|
| 1359 |
+
"step": 171
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 0.5584415584415584,
|
| 1363 |
+
"grad_norm": 0.58984375,
|
| 1364 |
+
"learning_rate": 1.0851338347136358e-05,
|
| 1365 |
+
"loss": 0.3015,
|
| 1366 |
+
"step": 172
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 0.5616883116883117,
|
| 1370 |
+
"grad_norm": 0.5625,
|
| 1371 |
+
"learning_rate": 1.0729953146609076e-05,
|
| 1372 |
+
"loss": 0.2953,
|
| 1373 |
+
"step": 173
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 0.564935064935065,
|
| 1377 |
+
"grad_norm": 0.55859375,
|
| 1378 |
+
"learning_rate": 1.060845971551014e-05,
|
| 1379 |
+
"loss": 0.3011,
|
| 1380 |
+
"step": 174
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 0.5681818181818182,
|
| 1384 |
+
"grad_norm": 0.58984375,
|
| 1385 |
+
"learning_rate": 1.0486876067740253e-05,
|
| 1386 |
+
"loss": 0.3016,
|
| 1387 |
+
"step": 175
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 0.5714285714285714,
|
| 1391 |
+
"grad_norm": 0.5859375,
|
| 1392 |
+
"learning_rate": 1.0365220230576592e-05,
|
| 1393 |
+
"loss": 0.2953,
|
| 1394 |
+
"step": 176
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 0.5746753246753247,
|
| 1398 |
+
"grad_norm": 0.5625,
|
| 1399 |
+
"learning_rate": 1.0243510241999898e-05,
|
| 1400 |
+
"loss": 0.2948,
|
| 1401 |
+
"step": 177
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 0.577922077922078,
|
| 1405 |
+
"grad_norm": 0.5703125,
|
| 1406 |
+
"learning_rate": 1.0121764148019977e-05,
|
| 1407 |
+
"loss": 0.2958,
|
| 1408 |
+
"step": 178
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 0.5811688311688312,
|
| 1412 |
+
"grad_norm": 0.5546875,
|
| 1413 |
+
"learning_rate": 1e-05,
|
| 1414 |
+
"loss": 0.2829,
|
| 1415 |
+
"step": 179
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"epoch": 0.5844155844155844,
|
| 1419 |
+
"grad_norm": 0.58203125,
|
| 1420 |
+
"learning_rate": 9.878235851980027e-06,
|
| 1421 |
+
"loss": 0.2917,
|
| 1422 |
+
"step": 180
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"epoch": 0.5844155844155844,
|
| 1426 |
+
"eval_loss": 0.29469791054725647,
|
| 1427 |
+
"eval_model_preparation_time": 0.0003,
|
| 1428 |
+
"eval_runtime": 174.9839,
|
| 1429 |
+
"eval_samples_per_second": 11.881,
|
| 1430 |
+
"eval_steps_per_second": 1.486,
|
| 1431 |
+
"step": 180
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.5876623376623377,
|
| 1435 |
+
"grad_norm": 0.59375,
|
| 1436 |
+
"learning_rate": 9.756489758000105e-06,
|
| 1437 |
+
"loss": 0.2994,
|
| 1438 |
+
"step": 181
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.5909090909090909,
|
| 1442 |
+
"grad_norm": 0.57421875,
|
| 1443 |
+
"learning_rate": 9.634779769423412e-06,
|
| 1444 |
+
"loss": 0.3054,
|
| 1445 |
+
"step": 182
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.5941558441558441,
|
| 1449 |
+
"grad_norm": 0.59375,
|
| 1450 |
+
"learning_rate": 9.51312393225975e-06,
|
| 1451 |
+
"loss": 0.2925,
|
| 1452 |
+
"step": 183
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.5974025974025974,
|
| 1456 |
+
"grad_norm": 0.5703125,
|
| 1457 |
+
"learning_rate": 9.391540284489862e-06,
|
| 1458 |
+
"loss": 0.2816,
|
| 1459 |
+
"step": 184
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.6006493506493507,
|
| 1463 |
+
"grad_norm": 0.5390625,
|
| 1464 |
+
"learning_rate": 9.270046853390924e-06,
|
| 1465 |
+
"loss": 0.2856,
|
| 1466 |
+
"step": 185
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.6038961038961039,
|
| 1470 |
+
"grad_norm": 0.5703125,
|
| 1471 |
+
"learning_rate": 9.148661652863644e-06,
|
| 1472 |
+
"loss": 0.2936,
|
| 1473 |
+
"step": 186
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.6071428571428571,
|
| 1477 |
+
"grad_norm": 0.55078125,
|
| 1478 |
+
"learning_rate": 9.02740268076131e-06,
|
| 1479 |
+
"loss": 0.2938,
|
| 1480 |
+
"step": 187
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.6103896103896104,
|
| 1484 |
+
"grad_norm": 0.5859375,
|
| 1485 |
+
"learning_rate": 8.906287916221259e-06,
|
| 1486 |
+
"loss": 0.3017,
|
| 1487 |
+
"step": 188
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.6136363636363636,
|
| 1491 |
+
"grad_norm": 0.578125,
|
| 1492 |
+
"learning_rate": 8.785335316999078e-06,
|
| 1493 |
+
"loss": 0.2957,
|
| 1494 |
+
"step": 189
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.6168831168831169,
|
| 1498 |
+
"grad_norm": 0.58203125,
|
| 1499 |
+
"learning_rate": 8.664562816806022e-06,
|
| 1500 |
+
"loss": 0.2961,
|
| 1501 |
+
"step": 190
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.6168831168831169,
|
| 1505 |
+
"eval_loss": 0.2927069365978241,
|
| 1506 |
+
"eval_model_preparation_time": 0.0003,
|
| 1507 |
+
"eval_runtime": 174.9405,
|
| 1508 |
+
"eval_samples_per_second": 11.884,
|
| 1509 |
+
"eval_steps_per_second": 1.486,
|
| 1510 |
+
"step": 190
|
| 1511 |
+
},
|
| 1512 |
+
{
|
| 1513 |
+
"epoch": 0.6201298701298701,
|
| 1514 |
+
"grad_norm": 0.58203125,
|
| 1515 |
+
"learning_rate": 8.543988322649954e-06,
|
| 1516 |
+
"loss": 0.2915,
|
| 1517 |
+
"step": 191
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 0.6233766233766234,
|
| 1521 |
+
"grad_norm": 0.57421875,
|
| 1522 |
+
"learning_rate": 8.423629712180265e-06,
|
| 1523 |
+
"loss": 0.2875,
|
| 1524 |
+
"step": 192
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 0.6266233766233766,
|
| 1528 |
+
"grad_norm": 0.5703125,
|
| 1529 |
+
"learning_rate": 8.303504831037154e-06,
|
| 1530 |
+
"loss": 0.2979,
|
| 1531 |
+
"step": 193
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 0.6298701298701299,
|
| 1535 |
+
"grad_norm": 0.5703125,
|
| 1536 |
+
"learning_rate": 8.183631490205636e-06,
|
| 1537 |
+
"loss": 0.2891,
|
| 1538 |
+
"step": 194
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 0.6331168831168831,
|
| 1542 |
+
"grad_norm": 0.5703125,
|
| 1543 |
+
"learning_rate": 8.064027463374702e-06,
|
| 1544 |
+
"loss": 0.2796,
|
| 1545 |
+
"step": 195
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 0.6363636363636364,
|
| 1549 |
+
"grad_norm": 0.57421875,
|
| 1550 |
+
"learning_rate": 7.944710484301995e-06,
|
| 1551 |
+
"loss": 0.285,
|
| 1552 |
+
"step": 196
|
| 1553 |
+
},
|
| 1554 |
+
{
|
| 1555 |
+
"epoch": 0.6396103896103896,
|
| 1556 |
+
"grad_norm": 0.58203125,
|
| 1557 |
+
"learning_rate": 7.825698244184432e-06,
|
| 1558 |
+
"loss": 0.295,
|
| 1559 |
+
"step": 197
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 0.6428571428571429,
|
| 1563 |
+
"grad_norm": 0.57421875,
|
| 1564 |
+
"learning_rate": 7.707008389035102e-06,
|
| 1565 |
+
"loss": 0.2962,
|
| 1566 |
+
"step": 198
|
| 1567 |
+
},
|
| 1568 |
+
{
|
| 1569 |
+
"epoch": 0.6461038961038961,
|
| 1570 |
+
"grad_norm": 0.57421875,
|
| 1571 |
+
"learning_rate": 7.588658517066893e-06,
|
| 1572 |
+
"loss": 0.2912,
|
| 1573 |
+
"step": 199
|
| 1574 |
+
},
|
| 1575 |
+
{
|
| 1576 |
+
"epoch": 0.6493506493506493,
|
| 1577 |
+
"grad_norm": 0.57421875,
|
| 1578 |
+
"learning_rate": 7.470666176083193e-06,
|
| 1579 |
+
"loss": 0.2917,
|
| 1580 |
+
"step": 200
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 0.6493506493506493,
|
| 1584 |
+
"eval_loss": 0.2912693917751312,
|
| 1585 |
+
"eval_model_preparation_time": 0.0003,
|
| 1586 |
+
"eval_runtime": 174.9875,
|
| 1587 |
+
"eval_samples_per_second": 11.881,
|
| 1588 |
+
"eval_steps_per_second": 1.486,
|
| 1589 |
+
"step": 200
|
| 1590 |
+
},
|
| 1591 |
+
{
|
| 1592 |
+
"epoch": 0.6525974025974026,
|
| 1593 |
+
"grad_norm": 0.6015625,
|
| 1594 |
+
"learning_rate": 7.3530488608760645e-06,
|
| 1595 |
+
"loss": 0.291,
|
| 1596 |
+
"step": 201
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"epoch": 0.6558441558441559,
|
| 1600 |
+
"grad_norm": 0.5625,
|
| 1601 |
+
"learning_rate": 7.235824010632284e-06,
|
| 1602 |
+
"loss": 0.2862,
|
| 1603 |
+
"step": 202
|
| 1604 |
+
},
|
| 1605 |
+
{
|
| 1606 |
+
"epoch": 0.6590909090909091,
|
| 1607 |
+
"grad_norm": 0.5546875,
|
| 1608 |
+
"learning_rate": 7.119009006347625e-06,
|
| 1609 |
+
"loss": 0.2936,
|
| 1610 |
+
"step": 203
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 0.6623376623376623,
|
| 1614 |
+
"grad_norm": 0.5546875,
|
| 1615 |
+
"learning_rate": 7.002621168249759e-06,
|
| 1616 |
+
"loss": 0.2934,
|
| 1617 |
+
"step": 204
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 0.6655844155844156,
|
| 1621 |
+
"grad_norm": 0.578125,
|
| 1622 |
+
"learning_rate": 6.886677753230184e-06,
|
| 1623 |
+
"loss": 0.2783,
|
| 1624 |
+
"step": 205
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 0.6688311688311688,
|
| 1628 |
+
"grad_norm": 0.546875,
|
| 1629 |
+
"learning_rate": 6.771195952285541e-06,
|
| 1630 |
+
"loss": 0.2844,
|
| 1631 |
+
"step": 206
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 0.672077922077922,
|
| 1635 |
+
"grad_norm": 0.5546875,
|
| 1636 |
+
"learning_rate": 6.656192887968675e-06,
|
| 1637 |
+
"loss": 0.2835,
|
| 1638 |
+
"step": 207
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 0.6753246753246753,
|
| 1642 |
+
"grad_norm": 0.56640625,
|
| 1643 |
+
"learning_rate": 6.5416856118498874e-06,
|
| 1644 |
+
"loss": 0.2887,
|
| 1645 |
+
"step": 208
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"epoch": 0.6785714285714286,
|
| 1649 |
+
"grad_norm": 0.5625,
|
| 1650 |
+
"learning_rate": 6.427691101988673e-06,
|
| 1651 |
+
"loss": 0.2925,
|
| 1652 |
+
"step": 209
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 0.6818181818181818,
|
| 1656 |
+
"grad_norm": 0.58203125,
|
| 1657 |
+
"learning_rate": 6.314226260416383e-06,
|
| 1658 |
+
"loss": 0.29,
|
| 1659 |
+
"step": 210
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 0.6818181818181818,
|
| 1663 |
+
"eval_loss": 0.29015374183654785,
|
| 1664 |
+
"eval_model_preparation_time": 0.0003,
|
| 1665 |
+
"eval_runtime": 174.8645,
|
| 1666 |
+
"eval_samples_per_second": 11.889,
|
| 1667 |
+
"eval_steps_per_second": 1.487,
|
| 1668 |
+
"step": 210
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.685064935064935,
|
| 1672 |
+
"grad_norm": 0.5625,
|
| 1673 |
+
"learning_rate": 6.2013079106301454e-06,
|
| 1674 |
+
"loss": 0.2858,
|
| 1675 |
+
"step": 211
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.6883116883116883,
|
| 1679 |
+
"grad_norm": 0.5703125,
|
| 1680 |
+
"learning_rate": 6.088952795098442e-06,
|
| 1681 |
+
"loss": 0.2828,
|
| 1682 |
+
"step": 212
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.6915584415584416,
|
| 1686 |
+
"grad_norm": 0.578125,
|
| 1687 |
+
"learning_rate": 5.977177572778679e-06,
|
| 1688 |
+
"loss": 0.2947,
|
| 1689 |
+
"step": 213
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.6948051948051948,
|
| 1693 |
+
"grad_norm": 0.578125,
|
| 1694 |
+
"learning_rate": 5.8659988166471715e-06,
|
| 1695 |
+
"loss": 0.2795,
|
| 1696 |
+
"step": 214
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.698051948051948,
|
| 1700 |
+
"grad_norm": 0.56640625,
|
| 1701 |
+
"learning_rate": 5.755433011241851e-06,
|
| 1702 |
+
"loss": 0.2899,
|
| 1703 |
+
"step": 215
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.7012987012987013,
|
| 1707 |
+
"grad_norm": 0.578125,
|
| 1708 |
+
"learning_rate": 5.645496550218089e-06,
|
| 1709 |
+
"loss": 0.2881,
|
| 1710 |
+
"step": 216
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 0.7045454545454546,
|
| 1714 |
+
"grad_norm": 0.56640625,
|
| 1715 |
+
"learning_rate": 5.5362057339180075e-06,
|
| 1716 |
+
"loss": 0.2937,
|
| 1717 |
+
"step": 217
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.7077922077922078,
|
| 1721 |
+
"grad_norm": 0.5625,
|
| 1722 |
+
"learning_rate": 5.427576766953615e-06,
|
| 1723 |
+
"loss": 0.2828,
|
| 1724 |
+
"step": 218
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 0.711038961038961,
|
| 1728 |
+
"grad_norm": 0.57421875,
|
| 1729 |
+
"learning_rate": 5.3196257558041386e-06,
|
| 1730 |
+
"loss": 0.2863,
|
| 1731 |
+
"step": 219
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.7142857142857143,
|
| 1735 |
+
"grad_norm": 0.5859375,
|
| 1736 |
+
"learning_rate": 5.212368706427913e-06,
|
| 1737 |
+
"loss": 0.2876,
|
| 1738 |
+
"step": 220
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 0.7142857142857143,
|
| 1742 |
+
"eval_loss": 0.2891963720321655,
|
| 1743 |
+
"eval_model_preparation_time": 0.0003,
|
| 1744 |
+
"eval_runtime": 174.9738,
|
| 1745 |
+
"eval_samples_per_second": 11.882,
|
| 1746 |
+
"eval_steps_per_second": 1.486,
|
| 1747 |
+
"step": 220
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"epoch": 0.7175324675324676,
|
| 1751 |
+
"grad_norm": 0.5859375,
|
| 1752 |
+
"learning_rate": 5.105821521889147e-06,
|
| 1753 |
+
"loss": 0.2955,
|
| 1754 |
+
"step": 221
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 0.7207792207792207,
|
| 1758 |
+
"grad_norm": 0.56640625,
|
| 1759 |
+
"learning_rate": 5.000000000000003e-06,
|
| 1760 |
+
"loss": 0.2873,
|
| 1761 |
+
"step": 222
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 0.724025974025974,
|
| 1765 |
+
"grad_norm": 0.5625,
|
| 1766 |
+
"learning_rate": 4.894919830978212e-06,
|
| 1767 |
+
"loss": 0.2813,
|
| 1768 |
+
"step": 223
|
| 1769 |
+
},
|
| 1770 |
+
{
|
| 1771 |
+
"epoch": 0.7272727272727273,
|
| 1772 |
+
"grad_norm": 0.59375,
|
| 1773 |
+
"learning_rate": 4.790596595120699e-06,
|
| 1774 |
+
"loss": 0.2912,
|
| 1775 |
+
"step": 224
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 0.7305194805194806,
|
| 1779 |
+
"grad_norm": 0.5859375,
|
| 1780 |
+
"learning_rate": 4.687045760493468e-06,
|
| 1781 |
+
"loss": 0.2921,
|
| 1782 |
+
"step": 225
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"epoch": 0.7337662337662337,
|
| 1786 |
+
"grad_norm": 0.55078125,
|
| 1787 |
+
"learning_rate": 4.584282680638155e-06,
|
| 1788 |
+
"loss": 0.288,
|
| 1789 |
+
"step": 226
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 0.737012987012987,
|
| 1793 |
+
"grad_norm": 0.5546875,
|
| 1794 |
+
"learning_rate": 4.482322592295541e-06,
|
| 1795 |
+
"loss": 0.2914,
|
| 1796 |
+
"step": 227
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 0.7402597402597403,
|
| 1800 |
+
"grad_norm": 0.56640625,
|
| 1801 |
+
"learning_rate": 4.381180613146396e-06,
|
| 1802 |
+
"loss": 0.2901,
|
| 1803 |
+
"step": 228
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 0.7435064935064936,
|
| 1807 |
+
"grad_norm": 0.56640625,
|
| 1808 |
+
"learning_rate": 4.280871739569972e-06,
|
| 1809 |
+
"loss": 0.2941,
|
| 1810 |
+
"step": 229
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 0.7467532467532467,
|
| 1814 |
+
"grad_norm": 0.54296875,
|
| 1815 |
+
"learning_rate": 4.181410844420473e-06,
|
| 1816 |
+
"loss": 0.2836,
|
| 1817 |
+
"step": 230
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 0.7467532467532467,
|
| 1821 |
+
"eval_loss": 0.2885654866695404,
|
| 1822 |
+
"eval_model_preparation_time": 0.0003,
|
| 1823 |
+
"eval_runtime": 174.9437,
|
| 1824 |
+
"eval_samples_per_second": 11.884,
|
| 1825 |
+
"eval_steps_per_second": 1.486,
|
| 1826 |
+
"step": 230
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 0.75,
|
| 1830 |
+
"grad_norm": 0.58203125,
|
| 1831 |
+
"learning_rate": 4.082812674821865e-06,
|
| 1832 |
+
"loss": 0.2882,
|
| 1833 |
+
"step": 231
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 0.7532467532467533,
|
| 1837 |
+
"grad_norm": 0.56640625,
|
| 1838 |
+
"learning_rate": 3.9850918499812976e-06,
|
| 1839 |
+
"loss": 0.293,
|
| 1840 |
+
"step": 232
|
| 1841 |
+
},
|
| 1842 |
+
{
|
| 1843 |
+
"epoch": 0.7564935064935064,
|
| 1844 |
+
"grad_norm": 0.56640625,
|
| 1845 |
+
"learning_rate": 3.888262859021508e-06,
|
| 1846 |
+
"loss": 0.2818,
|
| 1847 |
+
"step": 233
|
| 1848 |
+
},
|
| 1849 |
+
{
|
| 1850 |
+
"epoch": 0.7597402597402597,
|
| 1851 |
+
"grad_norm": 0.5703125,
|
| 1852 |
+
"learning_rate": 3.7923400588325156e-06,
|
| 1853 |
+
"loss": 0.2836,
|
| 1854 |
+
"step": 234
|
| 1855 |
+
},
|
| 1856 |
+
{
|
| 1857 |
+
"epoch": 0.762987012987013,
|
| 1858 |
+
"grad_norm": 0.6015625,
|
| 1859 |
+
"learning_rate": 3.6973376719429134e-06,
|
| 1860 |
+
"loss": 0.2833,
|
| 1861 |
+
"step": 235
|
| 1862 |
+
},
|
| 1863 |
+
{
|
| 1864 |
+
"epoch": 0.7662337662337663,
|
| 1865 |
+
"grad_norm": 0.5625,
|
| 1866 |
+
"learning_rate": 3.6032697844110896e-06,
|
| 1867 |
+
"loss": 0.2956,
|
| 1868 |
+
"step": 236
|
| 1869 |
+
},
|
| 1870 |
+
{
|
| 1871 |
+
"epoch": 0.7694805194805194,
|
| 1872 |
+
"grad_norm": 0.578125,
|
| 1873 |
+
"learning_rate": 3.5101503437366678e-06,
|
| 1874 |
+
"loss": 0.288,
|
| 1875 |
+
"step": 237
|
| 1876 |
+
},
|
| 1877 |
+
{
|
| 1878 |
+
"epoch": 0.7727272727272727,
|
| 1879 |
+
"grad_norm": 0.578125,
|
| 1880 |
+
"learning_rate": 3.4179931567925216e-06,
|
| 1881 |
+
"loss": 0.2898,
|
| 1882 |
+
"step": 238
|
| 1883 |
+
},
|
| 1884 |
+
{
|
| 1885 |
+
"epoch": 0.775974025974026,
|
| 1886 |
+
"grad_norm": 0.55859375,
|
| 1887 |
+
"learning_rate": 3.326811887777607e-06,
|
| 1888 |
+
"loss": 0.2809,
|
| 1889 |
+
"step": 239
|
| 1890 |
+
},
|
| 1891 |
+
{
|
| 1892 |
+
"epoch": 0.7792207792207793,
|
| 1893 |
+
"grad_norm": 0.546875,
|
| 1894 |
+
"learning_rate": 3.236620056190972e-06,
|
| 1895 |
+
"loss": 0.285,
|
| 1896 |
+
"step": 240
|
| 1897 |
+
},
|
| 1898 |
+
{
|
| 1899 |
+
"epoch": 0.7792207792207793,
|
| 1900 |
+
"eval_loss": 0.2881048321723938,
|
| 1901 |
+
"eval_model_preparation_time": 0.0003,
|
| 1902 |
+
"eval_runtime": 174.9387,
|
| 1903 |
+
"eval_samples_per_second": 11.884,
|
| 1904 |
+
"eval_steps_per_second": 1.486,
|
| 1905 |
+
"step": 240
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 0.7824675324675324,
|
| 1909 |
+
"grad_norm": 0.56640625,
|
| 1910 |
+
"learning_rate": 3.1474310348272084e-06,
|
| 1911 |
+
"loss": 0.2888,
|
| 1912 |
+
"step": 241
|
| 1913 |
+
},
|
| 1914 |
+
{
|
| 1915 |
+
"epoch": 0.7857142857142857,
|
| 1916 |
+
"grad_norm": 0.56640625,
|
| 1917 |
+
"learning_rate": 3.0592580477936606e-06,
|
| 1918 |
+
"loss": 0.2875,
|
| 1919 |
+
"step": 242
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 0.788961038961039,
|
| 1923 |
+
"grad_norm": 0.5625,
|
| 1924 |
+
"learning_rate": 2.9721141685496825e-06,
|
| 1925 |
+
"loss": 0.2828,
|
| 1926 |
+
"step": 243
|
| 1927 |
+
},
|
| 1928 |
+
{
|
| 1929 |
+
"epoch": 0.7922077922077922,
|
| 1930 |
+
"grad_norm": 0.55859375,
|
| 1931 |
+
"learning_rate": 2.8860123179682244e-06,
|
| 1932 |
+
"loss": 0.2866,
|
| 1933 |
+
"step": 244
|
| 1934 |
+
},
|
| 1935 |
+
{
|
| 1936 |
+
"epoch": 0.7954545454545454,
|
| 1937 |
+
"grad_norm": 0.5703125,
|
| 1938 |
+
"learning_rate": 2.8009652624200436e-06,
|
| 1939 |
+
"loss": 0.289,
|
| 1940 |
+
"step": 245
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 0.7987012987012987,
|
| 1944 |
+
"grad_norm": 0.5625,
|
| 1945 |
+
"learning_rate": 2.7169856118808414e-06,
|
| 1946 |
+
"loss": 0.2832,
|
| 1947 |
+
"step": 246
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 0.801948051948052,
|
| 1951 |
+
"grad_norm": 0.56640625,
|
| 1952 |
+
"learning_rate": 2.634085818061565e-06,
|
| 1953 |
+
"loss": 0.2913,
|
| 1954 |
+
"step": 247
|
| 1955 |
+
},
|
| 1956 |
+
{
|
| 1957 |
+
"epoch": 0.8051948051948052,
|
| 1958 |
+
"grad_norm": 0.58203125,
|
| 1959 |
+
"learning_rate": 2.5522781725621814e-06,
|
| 1960 |
+
"loss": 0.2917,
|
| 1961 |
+
"step": 248
|
| 1962 |
+
},
|
| 1963 |
+
{
|
| 1964 |
+
"epoch": 0.8084415584415584,
|
| 1965 |
+
"grad_norm": 0.56640625,
|
| 1966 |
+
"learning_rate": 2.471574805049206e-06,
|
| 1967 |
+
"loss": 0.2937,
|
| 1968 |
+
"step": 249
|
| 1969 |
+
},
|
| 1970 |
+
{
|
| 1971 |
+
"epoch": 0.8116883116883117,
|
| 1972 |
+
"grad_norm": 0.5625,
|
| 1973 |
+
"learning_rate": 2.3919876814572197e-06,
|
| 1974 |
+
"loss": 0.2932,
|
| 1975 |
+
"step": 250
|
| 1976 |
+
},
|
| 1977 |
+
{
|
| 1978 |
+
"epoch": 0.8116883116883117,
|
| 1979 |
+
"eval_loss": 0.28785035014152527,
|
| 1980 |
+
"eval_model_preparation_time": 0.0003,
|
| 1981 |
+
"eval_runtime": 174.993,
|
| 1982 |
+
"eval_samples_per_second": 11.88,
|
| 1983 |
+
"eval_steps_per_second": 1.486,
|
| 1984 |
+
"step": 250
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 0.814935064935065,
|
| 1988 |
+
"grad_norm": 0.56640625,
|
| 1989 |
+
"learning_rate": 2.3135286022146785e-06,
|
| 1990 |
+
"loss": 0.2973,
|
| 1991 |
+
"step": 251
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 0.8181818181818182,
|
| 1995 |
+
"grad_norm": 0.5703125,
|
| 1996 |
+
"learning_rate": 2.2362092004942583e-06,
|
| 1997 |
+
"loss": 0.2862,
|
| 1998 |
+
"step": 252
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 0.8214285714285714,
|
| 2002 |
+
"grad_norm": 0.57421875,
|
| 2003 |
+
"learning_rate": 2.1600409404879875e-06,
|
| 2004 |
+
"loss": 0.279,
|
| 2005 |
+
"step": 253
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 0.8246753246753247,
|
| 2009 |
+
"grad_norm": 0.55859375,
|
| 2010 |
+
"learning_rate": 2.08503511570746e-06,
|
| 2011 |
+
"loss": 0.2844,
|
| 2012 |
+
"step": 254
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 0.827922077922078,
|
| 2016 |
+
"grad_norm": 0.5546875,
|
| 2017 |
+
"learning_rate": 2.0112028473093294e-06,
|
| 2018 |
+
"loss": 0.2792,
|
| 2019 |
+
"step": 255
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 0.8311688311688312,
|
| 2023 |
+
"grad_norm": 0.5703125,
|
| 2024 |
+
"learning_rate": 1.9385550824463727e-06,
|
| 2025 |
+
"loss": 0.2921,
|
| 2026 |
+
"step": 256
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 0.8344155844155844,
|
| 2030 |
+
"grad_norm": 0.5625,
|
| 2031 |
+
"learning_rate": 1.8671025926443464e-06,
|
| 2032 |
+
"loss": 0.2891,
|
| 2033 |
+
"step": 257
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 0.8376623376623377,
|
| 2037 |
+
"grad_norm": 0.5625,
|
| 2038 |
+
"learning_rate": 1.7968559722048906e-06,
|
| 2039 |
+
"loss": 0.2848,
|
| 2040 |
+
"step": 258
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 0.8409090909090909,
|
| 2044 |
+
"grad_norm": 0.55078125,
|
| 2045 |
+
"learning_rate": 1.7278256366347034e-06,
|
| 2046 |
+
"loss": 0.2921,
|
| 2047 |
+
"step": 259
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 0.8441558441558441,
|
| 2051 |
+
"grad_norm": 0.56640625,
|
| 2052 |
+
"learning_rate": 1.660021821101222e-06,
|
| 2053 |
+
"loss": 0.2907,
|
| 2054 |
+
"step": 260
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 0.8441558441558441,
|
| 2058 |
+
"eval_loss": 0.2877131402492523,
|
| 2059 |
+
"eval_model_preparation_time": 0.0003,
|
| 2060 |
+
"eval_runtime": 175.008,
|
| 2061 |
+
"eval_samples_per_second": 11.879,
|
| 2062 |
+
"eval_steps_per_second": 1.486,
|
| 2063 |
+
"step": 260
|
| 2064 |
+
},
|
| 2065 |
+
{
|
| 2066 |
+
"epoch": 0.8474025974025974,
|
| 2067 |
+
"grad_norm": 0.5625,
|
| 2068 |
+
"learning_rate": 1.5934545789150625e-06,
|
| 2069 |
+
"loss": 0.2979,
|
| 2070 |
+
"step": 261
|
| 2071 |
+
},
|
| 2072 |
+
{
|
| 2073 |
+
"epoch": 0.8506493506493507,
|
| 2074 |
+
"grad_norm": 0.5625,
|
| 2075 |
+
"learning_rate": 1.528133780039397e-06,
|
| 2076 |
+
"loss": 0.2847,
|
| 2077 |
+
"step": 262
|
| 2078 |
+
},
|
| 2079 |
+
{
|
| 2080 |
+
"epoch": 0.8538961038961039,
|
| 2081 |
+
"grad_norm": 0.55078125,
|
| 2082 |
+
"learning_rate": 1.4640691096265358e-06,
|
| 2083 |
+
"loss": 0.2902,
|
| 2084 |
+
"step": 263
|
| 2085 |
+
},
|
| 2086 |
+
{
|
| 2087 |
+
"epoch": 0.8571428571428571,
|
| 2088 |
+
"grad_norm": 0.5703125,
|
| 2089 |
+
"learning_rate": 1.401270066581899e-06,
|
| 2090 |
+
"loss": 0.2861,
|
| 2091 |
+
"step": 264
|
| 2092 |
+
},
|
| 2093 |
+
{
|
| 2094 |
+
"epoch": 0.8603896103896104,
|
| 2095 |
+
"grad_norm": 0.5625,
|
| 2096 |
+
"learning_rate": 1.339745962155613e-06,
|
| 2097 |
+
"loss": 0.2823,
|
| 2098 |
+
"step": 265
|
| 2099 |
+
},
|
| 2100 |
+
{
|
| 2101 |
+
"epoch": 0.8636363636363636,
|
| 2102 |
+
"grad_norm": 0.5703125,
|
| 2103 |
+
"learning_rate": 1.279505918561923e-06,
|
| 2104 |
+
"loss": 0.2855,
|
| 2105 |
+
"step": 266
|
| 2106 |
+
},
|
| 2107 |
+
{
|
| 2108 |
+
"epoch": 0.8668831168831169,
|
| 2109 |
+
"grad_norm": 0.58203125,
|
| 2110 |
+
"learning_rate": 1.220558867626639e-06,
|
| 2111 |
+
"loss": 0.2853,
|
| 2112 |
+
"step": 267
|
| 2113 |
+
},
|
| 2114 |
+
{
|
| 2115 |
+
"epoch": 0.8701298701298701,
|
| 2116 |
+
"grad_norm": 0.5703125,
|
| 2117 |
+
"learning_rate": 1.1629135494628097e-06,
|
| 2118 |
+
"loss": 0.2891,
|
| 2119 |
+
"step": 268
|
| 2120 |
+
},
|
| 2121 |
+
{
|
| 2122 |
+
"epoch": 0.8733766233766234,
|
| 2123 |
+
"grad_norm": 0.56640625,
|
| 2124 |
+
"learning_rate": 1.1065785111748117e-06,
|
| 2125 |
+
"loss": 0.2853,
|
| 2126 |
+
"step": 269
|
| 2127 |
+
},
|
| 2128 |
+
{
|
| 2129 |
+
"epoch": 0.8766233766233766,
|
| 2130 |
+
"grad_norm": 0.5625,
|
| 2131 |
+
"learning_rate": 1.051562105591082e-06,
|
| 2132 |
+
"loss": 0.292,
|
| 2133 |
+
"step": 270
|
| 2134 |
+
},
|
| 2135 |
+
{
|
| 2136 |
+
"epoch": 0.8766233766233766,
|
| 2137 |
+
"eval_loss": 0.28765836358070374,
|
| 2138 |
+
"eval_model_preparation_time": 0.0003,
|
| 2139 |
+
"eval_runtime": 174.932,
|
| 2140 |
+
"eval_samples_per_second": 11.885,
|
| 2141 |
+
"eval_steps_per_second": 1.486,
|
| 2142 |
+
"step": 270
|
| 2143 |
+
},
|
| 2144 |
+
{
|
| 2145 |
+
"epoch": 0.8798701298701299,
|
| 2146 |
+
"grad_norm": 0.55859375,
|
| 2147 |
+
"learning_rate": 9.978724900256265e-07,
|
| 2148 |
+
"loss": 0.2825,
|
| 2149 |
+
"step": 271
|
| 2150 |
+
},
|
| 2151 |
+
{
|
| 2152 |
+
"epoch": 0.8831168831168831,
|
| 2153 |
+
"grad_norm": 0.5546875,
|
| 2154 |
+
"learning_rate": 9.455176250685338e-07,
|
| 2155 |
+
"loss": 0.2836,
|
| 2156 |
+
"step": 272
|
| 2157 |
+
},
|
| 2158 |
+
{
|
| 2159 |
+
"epoch": 0.8863636363636364,
|
| 2160 |
+
"grad_norm": 0.58203125,
|
| 2161 |
+
"learning_rate": 8.945052734056581e-07,
|
| 2162 |
+
"loss": 0.2959,
|
| 2163 |
+
"step": 273
|
| 2164 |
+
},
|
| 2165 |
+
{
|
| 2166 |
+
"epoch": 0.8896103896103896,
|
| 2167 |
+
"grad_norm": 0.57421875,
|
| 2168 |
+
"learning_rate": 8.448429986676298e-07,
|
| 2169 |
+
"loss": 0.3003,
|
| 2170 |
+
"step": 274
|
| 2171 |
+
},
|
| 2172 |
+
{
|
| 2173 |
+
"epoch": 0.8928571428571429,
|
| 2174 |
+
"grad_norm": 0.56640625,
|
| 2175 |
+
"learning_rate": 7.965381643084069e-07,
|
| 2176 |
+
"loss": 0.295,
|
| 2177 |
+
"step": 275
|
| 2178 |
+
},
|
| 2179 |
+
{
|
| 2180 |
+
"epoch": 0.8961038961038961,
|
| 2181 |
+
"grad_norm": 0.5625,
|
| 2182 |
+
"learning_rate": 7.495979325134806e-07,
|
| 2183 |
+
"loss": 0.2873,
|
| 2184 |
+
"step": 276
|
| 2185 |
+
},
|
| 2186 |
+
{
|
| 2187 |
+
"epoch": 0.8993506493506493,
|
| 2188 |
+
"grad_norm": 0.55078125,
|
| 2189 |
+
"learning_rate": 7.040292631379386e-07,
|
| 2190 |
+
"loss": 0.2827,
|
| 2191 |
+
"step": 277
|
| 2192 |
+
},
|
| 2193 |
+
{
|
| 2194 |
+
"epoch": 0.9025974025974026,
|
| 2195 |
+
"grad_norm": 0.54296875,
|
| 2196 |
+
"learning_rate": 6.598389126745209e-07,
|
| 2197 |
+
"loss": 0.2797,
|
| 2198 |
+
"step": 278
|
| 2199 |
+
},
|
| 2200 |
+
{
|
| 2201 |
+
"epoch": 0.9058441558441559,
|
| 2202 |
+
"grad_norm": 0.53125,
|
| 2203 |
+
"learning_rate": 6.170334332518325e-07,
|
| 2204 |
+
"loss": 0.272,
|
| 2205 |
+
"step": 279
|
| 2206 |
+
},
|
| 2207 |
+
{
|
| 2208 |
+
"epoch": 0.9090909090909091,
|
| 2209 |
+
"grad_norm": 0.58203125,
|
| 2210 |
+
"learning_rate": 5.756191716628556e-07,
|
| 2211 |
+
"loss": 0.292,
|
| 2212 |
+
"step": 280
|
| 2213 |
+
},
|
| 2214 |
+
{
|
| 2215 |
+
"epoch": 0.9090909090909091,
|
| 2216 |
+
"eval_loss": 0.28761279582977295,
|
| 2217 |
+
"eval_model_preparation_time": 0.0003,
|
| 2218 |
+
"eval_runtime": 174.9741,
|
| 2219 |
+
"eval_samples_per_second": 11.882,
|
| 2220 |
+
"eval_steps_per_second": 1.486,
|
| 2221 |
+
"step": 280
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.9123376623376623,
|
| 2225 |
+
"grad_norm": 0.5703125,
|
| 2226 |
+
"learning_rate": 5.35602268423906e-07,
|
| 2227 |
+
"loss": 0.2961,
|
| 2228 |
+
"step": 281
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 0.9155844155844156,
|
| 2232 |
+
"grad_norm": 0.578125,
|
| 2233 |
+
"learning_rate": 4.969886568641757e-07,
|
| 2234 |
+
"loss": 0.2904,
|
| 2235 |
+
"step": 282
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.9188311688311688,
|
| 2239 |
+
"grad_norm": 0.5625,
|
| 2240 |
+
"learning_rate": 4.597840622459937e-07,
|
| 2241 |
+
"loss": 0.2874,
|
| 2242 |
+
"step": 283
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 0.922077922077922,
|
| 2246 |
+
"grad_norm": 0.546875,
|
| 2247 |
+
"learning_rate": 4.2399400091594154e-07,
|
| 2248 |
+
"loss": 0.2794,
|
| 2249 |
+
"step": 284
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.9253246753246753,
|
| 2253 |
+
"grad_norm": 0.578125,
|
| 2254 |
+
"learning_rate": 3.8962377948693395e-07,
|
| 2255 |
+
"loss": 0.2962,
|
| 2256 |
+
"step": 285
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 0.9285714285714286,
|
| 2260 |
+
"grad_norm": 0.56640625,
|
| 2261 |
+
"learning_rate": 3.566784940514145e-07,
|
| 2262 |
+
"loss": 0.2914,
|
| 2263 |
+
"step": 286
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 0.9318181818181818,
|
| 2267 |
+
"grad_norm": 0.5703125,
|
| 2268 |
+
"learning_rate": 3.2516302942574794e-07,
|
| 2269 |
+
"loss": 0.2838,
|
| 2270 |
+
"step": 287
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 0.935064935064935,
|
| 2274 |
+
"grad_norm": 0.55859375,
|
| 2275 |
+
"learning_rate": 2.9508205842594727e-07,
|
| 2276 |
+
"loss": 0.2812,
|
| 2277 |
+
"step": 288
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.9383116883116883,
|
| 2281 |
+
"grad_norm": 0.5625,
|
| 2282 |
+
"learning_rate": 2.6644004117483357e-07,
|
| 2283 |
+
"loss": 0.2827,
|
| 2284 |
+
"step": 289
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 0.9415584415584416,
|
| 2288 |
+
"grad_norm": 0.5546875,
|
| 2289 |
+
"learning_rate": 2.392412244407294e-07,
|
| 2290 |
+
"loss": 0.2791,
|
| 2291 |
+
"step": 290
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.9415584415584416,
|
| 2295 |
+
"eval_loss": 0.28759849071502686,
|
| 2296 |
+
"eval_model_preparation_time": 0.0003,
|
| 2297 |
+
"eval_runtime": 175.0075,
|
| 2298 |
+
"eval_samples_per_second": 11.879,
|
| 2299 |
+
"eval_steps_per_second": 1.486,
|
| 2300 |
+
"step": 290
|
| 2301 |
+
},
|
| 2302 |
+
{
|
| 2303 |
+
"epoch": 0.9448051948051948,
|
| 2304 |
+
"grad_norm": 0.55859375,
|
| 2305 |
+
"learning_rate": 2.1348964100778914e-07,
|
| 2306 |
+
"loss": 0.285,
|
| 2307 |
+
"step": 291
|
| 2308 |
+
},
|
| 2309 |
+
{
|
| 2310 |
+
"epoch": 0.948051948051948,
|
| 2311 |
+
"grad_norm": 0.55859375,
|
| 2312 |
+
"learning_rate": 1.8918910907805733e-07,
|
| 2313 |
+
"loss": 0.288,
|
| 2314 |
+
"step": 292
|
| 2315 |
+
},
|
| 2316 |
+
{
|
| 2317 |
+
"epoch": 0.9512987012987013,
|
| 2318 |
+
"grad_norm": 0.57421875,
|
| 2319 |
+
"learning_rate": 1.6634323170533928e-07,
|
| 2320 |
+
"loss": 0.2854,
|
| 2321 |
+
"step": 293
|
| 2322 |
+
},
|
| 2323 |
+
{
|
| 2324 |
+
"epoch": 0.9545454545454546,
|
| 2325 |
+
"grad_norm": 0.57421875,
|
| 2326 |
+
"learning_rate": 1.4495539626097289e-07,
|
| 2327 |
+
"loss": 0.2873,
|
| 2328 |
+
"step": 294
|
| 2329 |
+
},
|
| 2330 |
+
{
|
| 2331 |
+
"epoch": 0.9577922077922078,
|
| 2332 |
+
"grad_norm": 0.56640625,
|
| 2333 |
+
"learning_rate": 1.2502877393158587e-07,
|
| 2334 |
+
"loss": 0.2841,
|
| 2335 |
+
"step": 295
|
| 2336 |
+
},
|
| 2337 |
+
{
|
| 2338 |
+
"epoch": 0.961038961038961,
|
| 2339 |
+
"grad_norm": 0.62109375,
|
| 2340 |
+
"learning_rate": 1.0656631924889749e-07,
|
| 2341 |
+
"loss": 0.2994,
|
| 2342 |
+
"step": 296
|
| 2343 |
+
},
|
| 2344 |
+
{
|
| 2345 |
+
"epoch": 0.9642857142857143,
|
| 2346 |
+
"grad_norm": 0.5546875,
|
| 2347 |
+
"learning_rate": 8.957076965165234e-08,
|
| 2348 |
+
"loss": 0.2797,
|
| 2349 |
+
"step": 297
|
| 2350 |
+
},
|
| 2351 |
+
{
|
| 2352 |
+
"epoch": 0.9675324675324676,
|
| 2353 |
+
"grad_norm": 0.56640625,
|
| 2354 |
+
"learning_rate": 7.404464507973608e-08,
|
| 2355 |
+
"loss": 0.2868,
|
| 2356 |
+
"step": 298
|
| 2357 |
+
},
|
| 2358 |
+
{
|
| 2359 |
+
"epoch": 0.9707792207792207,
|
| 2360 |
+
"grad_norm": 0.56640625,
|
| 2361 |
+
"learning_rate": 5.999024760054095e-08,
|
| 2362 |
+
"loss": 0.2867,
|
| 2363 |
+
"step": 299
|
| 2364 |
+
},
|
| 2365 |
+
{
|
| 2366 |
+
"epoch": 0.974025974025974,
|
| 2367 |
+
"grad_norm": 0.56640625,
|
| 2368 |
+
"learning_rate": 4.740966106764222e-08,
|
| 2369 |
+
"loss": 0.2832,
|
| 2370 |
+
"step": 300
|
| 2371 |
+
},
|
| 2372 |
+
{
|
| 2373 |
+
"epoch": 0.974025974025974,
|
| 2374 |
+
"eval_loss": 0.287624329328537,
|
| 2375 |
+
"eval_model_preparation_time": 0.0003,
|
| 2376 |
+
"eval_runtime": 174.9045,
|
| 2377 |
+
"eval_samples_per_second": 11.886,
|
| 2378 |
+
"eval_steps_per_second": 1.487,
|
| 2379 |
+
"step": 300
|
| 2380 |
+
}
|
| 2381 |
+
],
|
| 2382 |
+
"logging_steps": 1,
|
| 2383 |
+
"max_steps": 308,
|
| 2384 |
+
"num_input_tokens_seen": 0,
|
| 2385 |
+
"num_train_epochs": 1,
|
| 2386 |
+
"save_steps": 100,
|
| 2387 |
+
"stateful_callbacks": {
|
| 2388 |
+
"TrainerControl": {
|
| 2389 |
+
"args": {
|
| 2390 |
+
"should_epoch_stop": false,
|
| 2391 |
+
"should_evaluate": false,
|
| 2392 |
+
"should_log": false,
|
| 2393 |
+
"should_save": true,
|
| 2394 |
+
"should_training_stop": false
|
| 2395 |
+
},
|
| 2396 |
+
"attributes": {}
|
| 2397 |
+
}
|
| 2398 |
+
},
|
| 2399 |
+
"total_flos": 1.7706338758950912e+18,
|
| 2400 |
+
"train_batch_size": 8,
|
| 2401 |
+
"trial_name": null,
|
| 2402 |
+
"trial_params": null
|
| 2403 |
+
}
|
checkpoint-300/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d09f69be12f7ef607f0a1508435a517f5277e3160e5d6a59346e619fcbaa3592
|
| 3 |
+
size 5176
|
checkpoint-308/config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8b621112eddc9da772fae3f70d672f4d949cc5cb1d580f135d66b3836598c1a
|
| 3 |
+
size 915
|
checkpoint-308/generation_config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7327788370b7783e29852cf19b4a1f40cd31af5962c94bba76c336d491b4169
|
| 3 |
+
size 184
|
checkpoint-308/model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3abfe37c12d3907a891b3b7282c09590bedc9a560e05339e0aebfba26341dc1b
|
| 3 |
+
size 4976698672
|
checkpoint-308/model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:584021d05e0ffd6879fcb1af88d896f418db0a6656a6c799d17e6a28e6540c8b
|
| 3 |
+
size 4999802720
|