Training in progress, step 5750, 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 sha256:7b4a42d8e6450d95b4ed588a584edd873b2d68b0dce55074bc2232ddc52b490a
|
| 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 sha256:16c33dc92926f7960c49e5739713d3d425a247a11075cd6479c7519e7b8d988a
|
| 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:d786dbbdcc83d1d262aedf181488e6fda4c5a55e7ccd638465c135ae64cdab27
|
| 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": 44.
|
| 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,
|
|
@@ -10340,6 +10340,24 @@
|
|
| 10340 |
"mean_token_accuracy": 0.6603229939937592,
|
| 10341 |
"num_tokens": 20932992.0,
|
| 10342 |
"step": 5740
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10343 |
}
|
| 10344 |
],
|
| 10345 |
"logging_steps": 5,
|
|
@@ -10359,7 +10377,7 @@
|
|
| 10359 |
"attributes": {}
|
| 10360 |
}
|
| 10361 |
},
|
| 10362 |
-
"total_flos": 1.
|
| 10363 |
"train_batch_size": 4,
|
| 10364 |
"trial_name": null,
|
| 10365 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 44.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5750,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10340 |
"mean_token_accuracy": 0.6603229939937592,
|
| 10341 |
"num_tokens": 20932992.0,
|
| 10342 |
"step": 5740
|
| 10343 |
+
},
|
| 10344 |
+
{
|
| 10345 |
+
"epoch": 44.19230769230769,
|
| 10346 |
+
"grad_norm": 0.0,
|
| 10347 |
+
"learning_rate": 2.128e-05,
|
| 10348 |
+
"loss": 1.7463,
|
| 10349 |
+
"mean_token_accuracy": 0.65241838991642,
|
| 10350 |
+
"num_tokens": 20950902.0,
|
| 10351 |
+
"step": 5745
|
| 10352 |
+
},
|
| 10353 |
+
{
|
| 10354 |
+
"epoch": 44.23076923076923,
|
| 10355 |
+
"grad_norm": 0.0,
|
| 10356 |
+
"learning_rate": 2.1255e-05,
|
| 10357 |
+
"loss": 1.7803,
|
| 10358 |
+
"mean_token_accuracy": 0.6396133095026016,
|
| 10359 |
+
"num_tokens": 20969175.0,
|
| 10360 |
+
"step": 5750
|
| 10361 |
}
|
| 10362 |
],
|
| 10363 |
"logging_steps": 5,
|
|
|
|
| 10377 |
"attributes": {}
|
| 10378 |
}
|
| 10379 |
},
|
| 10380 |
+
"total_flos": 1.062622132370473e+18,
|
| 10381 |
"train_batch_size": 4,
|
| 10382 |
"trial_name": null,
|
| 10383 |
"trial_params": null
|