Training in progress, step 8500, 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 sha256:2eb5a7adc438be776275392221a962a2f95d71384e0169eee91ae65c4dd9f7d6
|
| 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 sha256:65cc2192368390a76d70fce6c8a66c2682a32f002415f8ca61472791121c6a95
|
| 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 sha256:0546b3887c8906e6c1bffd1db184e352265dcb1064d4b6c03dcb3d90d0f7a01b
|
| 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": 65.
|
| 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,
|
|
@@ -15290,6 +15290,24 @@
|
|
| 15290 |
"mean_token_accuracy": 0.6492012023925782,
|
| 15291 |
"num_tokens": 30964389.0,
|
| 15292 |
"step": 8490
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15293 |
}
|
| 15294 |
],
|
| 15295 |
"logging_steps": 5,
|
|
@@ -15309,7 +15327,7 @@
|
|
| 15309 |
"attributes": {}
|
| 15310 |
}
|
| 15311 |
},
|
| 15312 |
-
"total_flos": 1.
|
| 15313 |
"train_batch_size": 4,
|
| 15314 |
"trial_name": null,
|
| 15315 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 65.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8500,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15290 |
"mean_token_accuracy": 0.6492012023925782,
|
| 15291 |
"num_tokens": 30964389.0,
|
| 15292 |
"step": 8490
|
| 15293 |
+
},
|
| 15294 |
+
{
|
| 15295 |
+
"epoch": 65.34615384615384,
|
| 15296 |
+
"grad_norm": 0.0,
|
| 15297 |
+
"learning_rate": 7.530000000000001e-06,
|
| 15298 |
+
"loss": 1.6994,
|
| 15299 |
+
"mean_token_accuracy": 0.6621949762105942,
|
| 15300 |
+
"num_tokens": 30982829.0,
|
| 15301 |
+
"step": 8495
|
| 15302 |
+
},
|
| 15303 |
+
{
|
| 15304 |
+
"epoch": 65.38461538461539,
|
| 15305 |
+
"grad_norm": 0.0,
|
| 15306 |
+
"learning_rate": 7.505000000000001e-06,
|
| 15307 |
+
"loss": 1.6986,
|
| 15308 |
+
"mean_token_accuracy": 0.6562123388051987,
|
| 15309 |
+
"num_tokens": 31001822.0,
|
| 15310 |
+
"step": 8500
|
| 15311 |
}
|
| 15312 |
],
|
| 15313 |
"logging_steps": 5,
|
|
|
|
| 15327 |
"attributes": {}
|
| 15328 |
}
|
| 15329 |
},
|
| 15330 |
+
"total_flos": 1.5718425734976307e+18,
|
| 15331 |
"train_batch_size": 4,
|
| 15332 |
"trial_name": null,
|
| 15333 |
"trial_params": null
|