Training in progress, step 2910, 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:e08a0894293088b579c25fb0ecd4b507fe926454f3b5e54b9cfcd07d92f8d8f5
|
| 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 sha256:0abc82a7f2c8a17a25e1d019c94e544d119924c25684ebec316c1cde760d590c
|
| 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:a67e5a788c749c81a4c2b7846263651156bf784843dc095293f42f9f27e24db0
|
| 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,
|
|
@@ -5228,6 +5228,24 @@
|
|
| 5228 |
"mean_token_accuracy": 0.6496516615152359,
|
| 5229 |
"num_tokens": 10572379.0,
|
| 5230 |
"step": 2900
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5231 |
}
|
| 5232 |
],
|
| 5233 |
"logging_steps": 5,
|
|
@@ -5247,7 +5265,7 @@
|
|
| 5247 |
"attributes": {}
|
| 5248 |
}
|
| 5249 |
},
|
| 5250 |
-
"total_flos": 5.
|
| 5251 |
"train_batch_size": 4,
|
| 5252 |
"trial_name": null,
|
| 5253 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 22.384615384615383,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2910,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5228 |
"mean_token_accuracy": 0.6496516615152359,
|
| 5229 |
"num_tokens": 10572379.0,
|
| 5230 |
"step": 2900
|
| 5231 |
+
},
|
| 5232 |
+
{
|
| 5233 |
+
"epoch": 22.346153846153847,
|
| 5234 |
+
"grad_norm": 0.0,
|
| 5235 |
+
"learning_rate": 3.548e-05,
|
| 5236 |
+
"loss": 1.7381,
|
| 5237 |
+
"mean_token_accuracy": 0.6457451343536377,
|
| 5238 |
+
"num_tokens": 10591449.0,
|
| 5239 |
+
"step": 2905
|
| 5240 |
+
},
|
| 5241 |
+
{
|
| 5242 |
+
"epoch": 22.384615384615383,
|
| 5243 |
+
"grad_norm": 0.0,
|
| 5244 |
+
"learning_rate": 3.5455e-05,
|
| 5245 |
+
"loss": 1.6608,
|
| 5246 |
+
"mean_token_accuracy": 0.6606644958257675,
|
| 5247 |
+
"num_tokens": 10611295.0,
|
| 5248 |
+
"step": 2910
|
| 5249 |
}
|
| 5250 |
],
|
| 5251 |
"logging_steps": 5,
|
|
|
|
| 5265 |
"attributes": {}
|
| 5266 |
}
|
| 5267 |
},
|
| 5268 |
+
"total_flos": 5.377058963000525e+17,
|
| 5269 |
"train_batch_size": 4,
|
| 5270 |
"trial_name": null,
|
| 5271 |
"trial_params": null
|