Training in progress, step 1340, 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:bb1b17a43693720b6e524dad8c586f7c30a7b0007666dfaf0e03f300740aac5f
|
| 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:c97f4a48a3a9cf1e8bb5a5ec4a20e44aba9475ac688185daaa1358b93539c456
|
| 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:d04b0f40a756726cc9df35c748cb79e9066ef8cb5eff2fa4e7b2c0d511d38c72
|
| 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,
|
|
@@ -2402,6 +2402,24 @@
|
|
| 2402 |
"mean_token_accuracy": 0.6469725668430328,
|
| 2403 |
"num_tokens": 4849251.0,
|
| 2404 |
"step": 1330
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2405 |
}
|
| 2406 |
],
|
| 2407 |
"logging_steps": 5,
|
|
@@ -2421,7 +2439,7 @@
|
|
| 2421 |
"attributes": {}
|
| 2422 |
}
|
| 2423 |
},
|
| 2424 |
-
"total_flos": 2.
|
| 2425 |
"train_batch_size": 4,
|
| 2426 |
"trial_name": null,
|
| 2427 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 10.307692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1340,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2402 |
"mean_token_accuracy": 0.6469725668430328,
|
| 2403 |
"num_tokens": 4849251.0,
|
| 2404 |
"step": 1330
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 10.26923076923077,
|
| 2408 |
+
"grad_norm": 0.0,
|
| 2409 |
+
"learning_rate": 4.333000000000001e-05,
|
| 2410 |
+
"loss": 1.7413,
|
| 2411 |
+
"mean_token_accuracy": 0.6520713210105896,
|
| 2412 |
+
"num_tokens": 4867548.0,
|
| 2413 |
+
"step": 1335
|
| 2414 |
+
},
|
| 2415 |
+
{
|
| 2416 |
+
"epoch": 10.307692307692308,
|
| 2417 |
+
"grad_norm": 0.0,
|
| 2418 |
+
"learning_rate": 4.3305e-05,
|
| 2419 |
+
"loss": 1.7205,
|
| 2420 |
+
"mean_token_accuracy": 0.650857400894165,
|
| 2421 |
+
"num_tokens": 4885905.0,
|
| 2422 |
+
"step": 1340
|
| 2423 |
}
|
| 2424 |
],
|
| 2425 |
"logging_steps": 5,
|
|
|
|
| 2439 |
"attributes": {}
|
| 2440 |
}
|
| 2441 |
},
|
| 2442 |
+
"total_flos": 2.475160476991488e+17,
|
| 2443 |
"train_batch_size": 4,
|
| 2444 |
"trial_name": null,
|
| 2445 |
"trial_params": null
|