Training in progress, step 2920, 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:a96c1a57db5c4fbc2f443352fc5e79f16f20aeec9f446adb5f9a45c40d55f438
|
| 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 sha256:08b59600068962804b1d94d6dcaa11830286076c209a46ba2442638c675584a2
|
| 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:c7f9c40ebcfe0991f7eee489c5fdce883a36e244a9ece11850896e4854e9e735
|
| 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,
|
|
@@ -5246,6 +5246,24 @@
|
|
| 5246 |
"mean_token_accuracy": 0.6606644958257675,
|
| 5247 |
"num_tokens": 10611295.0,
|
| 5248 |
"step": 2910
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5249 |
}
|
| 5250 |
],
|
| 5251 |
"logging_steps": 5,
|
|
@@ -5265,7 +5283,7 @@
|
|
| 5265 |
"attributes": {}
|
| 5266 |
}
|
| 5267 |
},
|
| 5268 |
-
"total_flos": 5.
|
| 5269 |
"train_batch_size": 4,
|
| 5270 |
"trial_name": null,
|
| 5271 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 22.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2920,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5246 |
"mean_token_accuracy": 0.6606644958257675,
|
| 5247 |
"num_tokens": 10611295.0,
|
| 5248 |
"step": 2910
|
| 5249 |
+
},
|
| 5250 |
+
{
|
| 5251 |
+
"epoch": 22.423076923076923,
|
| 5252 |
+
"grad_norm": 0.0,
|
| 5253 |
+
"learning_rate": 3.5430000000000005e-05,
|
| 5254 |
+
"loss": 1.6849,
|
| 5255 |
+
"mean_token_accuracy": 0.6587489366531372,
|
| 5256 |
+
"num_tokens": 10629917.0,
|
| 5257 |
+
"step": 2915
|
| 5258 |
+
},
|
| 5259 |
+
{
|
| 5260 |
+
"epoch": 22.46153846153846,
|
| 5261 |
+
"grad_norm": 0.0,
|
| 5262 |
+
"learning_rate": 3.5405e-05,
|
| 5263 |
+
"loss": 1.7484,
|
| 5264 |
+
"mean_token_accuracy": 0.6465423703193665,
|
| 5265 |
+
"num_tokens": 10647956.0,
|
| 5266 |
+
"step": 2920
|
| 5267 |
}
|
| 5268 |
],
|
| 5269 |
"logging_steps": 5,
|
|
|
|
| 5283 |
"attributes": {}
|
| 5284 |
}
|
| 5285 |
},
|
| 5286 |
+
"total_flos": 5.3960997582176256e+17,
|
| 5287 |
"train_batch_size": 4,
|
| 5288 |
"trial_name": null,
|
| 5289 |
"trial_params": null
|