Training in progress, step 2940, 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:e636004d46cc560fa53640d4270ba338c639807fb70633b16972b00a9ca69c73
|
| 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:e33cec487132905ede368d6b5ff67ab17ef2e9e566257dd86f58cc9cfeaa42ce
|
| 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:cbe33ccdbc432df9ae10651a27e73d6049f64cfda292839ed159fe51f080eb9e
|
| 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": 22.
|
| 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,
|
|
@@ -5282,6 +5282,24 @@
|
|
| 5282 |
"mean_token_accuracy": 0.654433760046959,
|
| 5283 |
"num_tokens": 10684772.0,
|
| 5284 |
"step": 2930
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5285 |
}
|
| 5286 |
],
|
| 5287 |
"logging_steps": 5,
|
|
@@ -5301,7 +5319,7 @@
|
|
| 5301 |
"attributes": {}
|
| 5302 |
}
|
| 5303 |
},
|
| 5304 |
-
"total_flos": 5.
|
| 5305 |
"train_batch_size": 4,
|
| 5306 |
"trial_name": null,
|
| 5307 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 22.615384615384617,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2940,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5282 |
"mean_token_accuracy": 0.654433760046959,
|
| 5283 |
"num_tokens": 10684772.0,
|
| 5284 |
"step": 2930
|
| 5285 |
+
},
|
| 5286 |
+
{
|
| 5287 |
+
"epoch": 22.576923076923077,
|
| 5288 |
+
"grad_norm": 0.0,
|
| 5289 |
+
"learning_rate": 3.533e-05,
|
| 5290 |
+
"loss": 1.8088,
|
| 5291 |
+
"mean_token_accuracy": 0.63780497610569,
|
| 5292 |
+
"num_tokens": 10702520.0,
|
| 5293 |
+
"step": 2935
|
| 5294 |
+
},
|
| 5295 |
+
{
|
| 5296 |
+
"epoch": 22.615384615384617,
|
| 5297 |
+
"grad_norm": 0.0,
|
| 5298 |
+
"learning_rate": 3.5305e-05,
|
| 5299 |
+
"loss": 1.7072,
|
| 5300 |
+
"mean_token_accuracy": 0.659371867775917,
|
| 5301 |
+
"num_tokens": 10721196.0,
|
| 5302 |
+
"step": 2940
|
| 5303 |
}
|
| 5304 |
],
|
| 5305 |
"logging_steps": 5,
|
|
|
|
| 5319 |
"attributes": {}
|
| 5320 |
}
|
| 5321 |
},
|
| 5322 |
+
"total_flos": 5.4327967944966144e+17,
|
| 5323 |
"train_batch_size": 4,
|
| 5324 |
"trial_name": null,
|
| 5325 |
"trial_params": null
|