Femboyuwu2000
commited on
Commit
•
d5c9f3b
1
Parent(s):
e919f65
Training in progress, step 3640, 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 13982248
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d54e67b174db8aa6d78fd7e5ad7cc14e255ae9e2ac4b07617e63a3c6e1f44fd1
|
3 |
size 13982248
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 7062522
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a538e98a56080dc8b839b137de6d2baa98652765c46f5d7d5638ebbff1fc24e
|
3 |
size 7062522
|
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 sha256:77ef44b95127212e765792a1cf83babb6419dbbbc5242f9919c1607c1deb549f
|
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:c6436b03258a74e4e347dfaffcfa88289f9f39a08c2a52b4713027be6b232347
|
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,
|
@@ -1274,6 +1274,13 @@
|
|
1274 |
"learning_rate": 2.8241678862842374e-05,
|
1275 |
"loss": 3.4831,
|
1276 |
"step": 3620
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1277 |
}
|
1278 |
],
|
1279 |
"logging_steps": 20,
|
@@ -1281,7 +1288,7 @@
|
|
1281 |
"num_input_tokens_seen": 0,
|
1282 |
"num_train_epochs": 2,
|
1283 |
"save_steps": 20,
|
1284 |
-
"total_flos":
|
1285 |
"train_batch_size": 8,
|
1286 |
"trial_name": null,
|
1287 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.2912,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 3640,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1274 |
"learning_rate": 2.8241678862842374e-05,
|
1275 |
"loss": 3.4831,
|
1276 |
"step": 3620
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"epoch": 0.29,
|
1280 |
+
"grad_norm": 31.194787979125977,
|
1281 |
+
"learning_rate": 2.8218786465788984e-05,
|
1282 |
+
"loss": 3.6001,
|
1283 |
+
"step": 3640
|
1284 |
}
|
1285 |
],
|
1286 |
"logging_steps": 20,
|
|
|
1288 |
"num_input_tokens_seen": 0,
|
1289 |
"num_train_epochs": 2,
|
1290 |
"save_steps": 20,
|
1291 |
+
"total_flos": 8607877788991488.0,
|
1292 |
"train_batch_size": 8,
|
1293 |
"trial_name": null,
|
1294 |
"trial_params": null
|