Training in progress, step 2860, 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 sha256:31006c9e88d8acbd2548e8856618daa489097c8c498dc064ed29583e6e190dd1
|
| 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 sha256:48c7acf8b4e7c22463b93c966f22d64fadece59b37694bd9246d1f8a97e4f79b
|
| 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 sha256:88d06da5c54a4af92a4814289c772512988d67591931561296ec680eb14ab04a
|
| 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":
|
| 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,
|
|
@@ -5138,6 +5138,24 @@
|
|
| 5138 |
"mean_token_accuracy": 0.6452168464660645,
|
| 5139 |
"num_tokens": 10394319.0,
|
| 5140 |
"step": 2850
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5141 |
}
|
| 5142 |
],
|
| 5143 |
"logging_steps": 5,
|
|
@@ -5157,7 +5175,7 @@
|
|
| 5157 |
"attributes": {}
|
| 5158 |
}
|
| 5159 |
},
|
| 5160 |
-
"total_flos": 5.
|
| 5161 |
"train_batch_size": 4,
|
| 5162 |
"trial_name": null,
|
| 5163 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 22.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2860,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5138 |
"mean_token_accuracy": 0.6452168464660645,
|
| 5139 |
"num_tokens": 10394319.0,
|
| 5140 |
"step": 2850
|
| 5141 |
+
},
|
| 5142 |
+
{
|
| 5143 |
+
"epoch": 21.96153846153846,
|
| 5144 |
+
"grad_norm": 0.0,
|
| 5145 |
+
"learning_rate": 3.5730000000000005e-05,
|
| 5146 |
+
"loss": 1.6929,
|
| 5147 |
+
"mean_token_accuracy": 0.6594237118959427,
|
| 5148 |
+
"num_tokens": 10412963.0,
|
| 5149 |
+
"step": 2855
|
| 5150 |
+
},
|
| 5151 |
+
{
|
| 5152 |
+
"epoch": 22.0,
|
| 5153 |
+
"grad_norm": 0.0,
|
| 5154 |
+
"learning_rate": 3.5705e-05,
|
| 5155 |
+
"loss": 1.786,
|
| 5156 |
+
"mean_token_accuracy": 0.6423673510551453,
|
| 5157 |
+
"num_tokens": 10430310.0,
|
| 5158 |
+
"step": 2860
|
| 5159 |
}
|
| 5160 |
],
|
| 5161 |
"logging_steps": 5,
|
|
|
|
| 5175 |
"attributes": {}
|
| 5176 |
}
|
| 5177 |
},
|
| 5178 |
+
"total_flos": 5.284903546522829e+17,
|
| 5179 |
"train_batch_size": 4,
|
| 5180 |
"trial_name": null,
|
| 5181 |
"trial_params": null
|