Training in progress, step 7990, 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 sha256:0ab2599d8da5e7645b56ebd6e6444491c3dbf04b13c7442f777ceafe2e9531a5
|
| 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 sha256:244fd01ad37bada1d466cbb3aabfbb2361bd85af4d8d233774f7abbd17c45296
|
| 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 sha256:4646dde16c113bda37550a17e895ff50934b2e405f8c2a31d7ad7624e7afd53c
|
| 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": 61.
|
| 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,
|
|
@@ -14372,6 +14372,24 @@
|
|
| 14372 |
"mean_token_accuracy": 0.6553202778100967,
|
| 14373 |
"num_tokens": 29100554.0,
|
| 14374 |
"step": 7980
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14375 |
}
|
| 14376 |
],
|
| 14377 |
"logging_steps": 5,
|
|
@@ -14391,7 +14409,7 @@
|
|
| 14391 |
"attributes": {}
|
| 14392 |
}
|
| 14393 |
},
|
| 14394 |
-
"total_flos": 1.
|
| 14395 |
"train_batch_size": 4,
|
| 14396 |
"trial_name": null,
|
| 14397 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 61.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7990,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14372 |
"mean_token_accuracy": 0.6553202778100967,
|
| 14373 |
"num_tokens": 29100554.0,
|
| 14374 |
"step": 7980
|
| 14375 |
+
},
|
| 14376 |
+
{
|
| 14377 |
+
"epoch": 61.42307692307692,
|
| 14378 |
+
"grad_norm": 0.0,
|
| 14379 |
+
"learning_rate": 1.008e-05,
|
| 14380 |
+
"loss": 1.7646,
|
| 14381 |
+
"mean_token_accuracy": 0.6500458031892776,
|
| 14382 |
+
"num_tokens": 29118533.0,
|
| 14383 |
+
"step": 7985
|
| 14384 |
+
},
|
| 14385 |
+
{
|
| 14386 |
+
"epoch": 61.46153846153846,
|
| 14387 |
+
"grad_norm": 0.0,
|
| 14388 |
+
"learning_rate": 1.0055000000000001e-05,
|
| 14389 |
+
"loss": 1.7526,
|
| 14390 |
+
"mean_token_accuracy": 0.6455101191997528,
|
| 14391 |
+
"num_tokens": 29137065.0,
|
| 14392 |
+
"step": 7990
|
| 14393 |
}
|
| 14394 |
],
|
| 14395 |
"logging_steps": 5,
|
|
|
|
| 14409 |
"attributes": {}
|
| 14410 |
}
|
| 14411 |
},
|
| 14412 |
+
"total_flos": 1.4772438635175936e+18,
|
| 14413 |
"train_batch_size": 4,
|
| 14414 |
"trial_name": null,
|
| 14415 |
"trial_params": null
|