Training in progress, step 1320, 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:fc8bb22c569d44aaa62161ad02b5743ba01d202c46f92eb1b50aefbc99db63db
|
| 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:ce394b5482f28d19409f460b5e2a88da0663590b81f271168168d02beb8db72a
|
| 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 sha256:1400862405223fe14525499da93d3c92d6792f72b9479122a8f425f8d79b554c
|
| 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,
|
|
@@ -2366,6 +2366,24 @@
|
|
| 2366 |
"mean_token_accuracy": 0.6466272503137589,
|
| 2367 |
"num_tokens": 4777543.0,
|
| 2368 |
"step": 1310
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2369 |
}
|
| 2370 |
],
|
| 2371 |
"logging_steps": 5,
|
|
@@ -2385,7 +2403,7 @@
|
|
| 2385 |
"attributes": {}
|
| 2386 |
}
|
| 2387 |
},
|
| 2388 |
-
"total_flos": 2.
|
| 2389 |
"train_batch_size": 4,
|
| 2390 |
"trial_name": null,
|
| 2391 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 10.153846153846153,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1320,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2366 |
"mean_token_accuracy": 0.6466272503137589,
|
| 2367 |
"num_tokens": 4777543.0,
|
| 2368 |
"step": 1310
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 10.115384615384615,
|
| 2372 |
+
"grad_norm": 0.0,
|
| 2373 |
+
"learning_rate": 4.343e-05,
|
| 2374 |
+
"loss": 1.7418,
|
| 2375 |
+
"mean_token_accuracy": 0.6525053322315216,
|
| 2376 |
+
"num_tokens": 4795767.0,
|
| 2377 |
+
"step": 1315
|
| 2378 |
+
},
|
| 2379 |
+
{
|
| 2380 |
+
"epoch": 10.153846153846153,
|
| 2381 |
+
"grad_norm": 0.0,
|
| 2382 |
+
"learning_rate": 4.3405e-05,
|
| 2383 |
+
"loss": 1.8019,
|
| 2384 |
+
"mean_token_accuracy": 0.641847088932991,
|
| 2385 |
+
"num_tokens": 4812856.0,
|
| 2386 |
+
"step": 1320
|
| 2387 |
}
|
| 2388 |
],
|
| 2389 |
"logging_steps": 5,
|
|
|
|
| 2403 |
"attributes": {}
|
| 2404 |
}
|
| 2405 |
},
|
| 2406 |
+
"total_flos": 2.4380680806383616e+17,
|
| 2407 |
"train_batch_size": 4,
|
| 2408 |
"trial_name": null,
|
| 2409 |
"trial_params": null
|