Training in progress, step 40, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4725640
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82a235dcf79ae46d5d74eb2c277b2a88d917b4d0fe58e9c0483a1c6ef77bd3d0
|
3 |
size 4725640
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2423738
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8cafd0997844310ce6894d5bb35d3a49ea4d5dabe1e810d400c91685f3a3abb0
|
3 |
size 2423738
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac4bf1426427b0e2a018f4b1750c36bb7e3e5ebba9e8a477845308163b2a7fb5
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba9088914de78dc99d767c21058d110a360c0bb50564c9ed4886490601d97b6d
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -14,6 +14,13 @@
|
|
14 |
"learning_rate": 1.5833333333333336e-06,
|
15 |
"loss": 4.4875,
|
16 |
"step": 20
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
}
|
18 |
],
|
19 |
"logging_steps": 20,
|
@@ -21,7 +28,7 @@
|
|
21 |
"num_input_tokens_seen": 0,
|
22 |
"num_train_epochs": 3,
|
23 |
"save_steps": 20,
|
24 |
-
"total_flos":
|
25 |
"train_batch_size": 1,
|
26 |
"trial_name": null,
|
27 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.005451076587626056,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 40,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
14 |
"learning_rate": 1.5833333333333336e-06,
|
15 |
"loss": 4.4875,
|
16 |
"step": 20
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.01,
|
20 |
+
"grad_norm": 2.2963316440582275,
|
21 |
+
"learning_rate": 3.2500000000000002e-06,
|
22 |
+
"loss": 4.1113,
|
23 |
+
"step": 40
|
24 |
}
|
25 |
],
|
26 |
"logging_steps": 20,
|
|
|
28 |
"num_input_tokens_seen": 0,
|
29 |
"num_train_epochs": 3,
|
30 |
"save_steps": 20,
|
31 |
+
"total_flos": 334860439191552.0,
|
32 |
"train_batch_size": 1,
|
33 |
"trial_name": null,
|
34 |
"trial_params": null
|