Training in progress, step 1330, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3aeb90892bbb98947ed7432dec094c97a649ec364778ec0fbb5422ec6f0cf1ce
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce5803c6a1c56aad9939c0347d2441d9ba79446d37407747f2a4ffd27470a609
|
| 3 |
size 14709
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e784ac3e2ae7837759867b98f93f23df1b4dabc095047965180f9108729a35e2
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 10.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -2384,6 +2384,24 @@
|
|
| 2384 |
"mean_token_accuracy": 0.641847088932991,
|
| 2385 |
"num_tokens": 4812856.0,
|
| 2386 |
"step": 1320
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2387 |
}
|
| 2388 |
],
|
| 2389 |
"logging_steps": 5,
|
|
@@ -2403,7 +2421,7 @@
|
|
| 2403 |
"attributes": {}
|
| 2404 |
}
|
| 2405 |
},
|
| 2406 |
-
"total_flos": 2.
|
| 2407 |
"train_batch_size": 4,
|
| 2408 |
"trial_name": null,
|
| 2409 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 10.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1330,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2384 |
"mean_token_accuracy": 0.641847088932991,
|
| 2385 |
"num_tokens": 4812856.0,
|
| 2386 |
"step": 1320
|
| 2387 |
+
},
|
| 2388 |
+
{
|
| 2389 |
+
"epoch": 10.192307692307692,
|
| 2390 |
+
"grad_norm": 0.0,
|
| 2391 |
+
"learning_rate": 4.338e-05,
|
| 2392 |
+
"loss": 1.713,
|
| 2393 |
+
"mean_token_accuracy": 0.6589140474796296,
|
| 2394 |
+
"num_tokens": 4831209.0,
|
| 2395 |
+
"step": 1325
|
| 2396 |
+
},
|
| 2397 |
+
{
|
| 2398 |
+
"epoch": 10.23076923076923,
|
| 2399 |
+
"grad_norm": 0.0,
|
| 2400 |
+
"learning_rate": 4.3355e-05,
|
| 2401 |
+
"loss": 1.7601,
|
| 2402 |
+
"mean_token_accuracy": 0.6469725668430328,
|
| 2403 |
+
"num_tokens": 4849251.0,
|
| 2404 |
+
"step": 1330
|
| 2405 |
}
|
| 2406 |
],
|
| 2407 |
"logging_steps": 5,
|
|
|
|
| 2421 |
"attributes": {}
|
| 2422 |
}
|
| 2423 |
},
|
| 2424 |
+
"total_flos": 2.4566817599520768e+17,
|
| 2425 |
"train_batch_size": 4,
|
| 2426 |
"trial_name": null,
|
| 2427 |
"trial_params": null
|