Training in progress, step 2870, 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 sha256:1ce25dad29fdcbe26bdb7a65d772644f136fde461836fcd63fcc52ecd1c3f165
|
| 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 sha256:41c402c50b95728dbde1b88e6b91a63753613ef25ad8daf06849d9aae7da2598
|
| 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 sha256:874d88f226163cd0c864f08a040d52d2291b0799ca347c287eae611f9278d9df
|
| 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,
|
|
@@ -5156,6 +5156,24 @@
|
|
| 5156 |
"mean_token_accuracy": 0.6423673510551453,
|
| 5157 |
"num_tokens": 10430310.0,
|
| 5158 |
"step": 2860
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5159 |
}
|
| 5160 |
],
|
| 5161 |
"logging_steps": 5,
|
|
@@ -5175,7 +5193,7 @@
|
|
| 5175 |
"attributes": {}
|
| 5176 |
}
|
| 5177 |
},
|
| 5178 |
-
"total_flos": 5.
|
| 5179 |
"train_batch_size": 4,
|
| 5180 |
"trial_name": null,
|
| 5181 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 22.076923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2870,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5156 |
"mean_token_accuracy": 0.6423673510551453,
|
| 5157 |
"num_tokens": 10430310.0,
|
| 5158 |
"step": 2860
|
| 5159 |
+
},
|
| 5160 |
+
{
|
| 5161 |
+
"epoch": 22.03846153846154,
|
| 5162 |
+
"grad_norm": 0.0,
|
| 5163 |
+
"learning_rate": 3.5680000000000004e-05,
|
| 5164 |
+
"loss": 1.7693,
|
| 5165 |
+
"mean_token_accuracy": 0.6458660453557968,
|
| 5166 |
+
"num_tokens": 10448139.0,
|
| 5167 |
+
"step": 2865
|
| 5168 |
+
},
|
| 5169 |
+
{
|
| 5170 |
+
"epoch": 22.076923076923077,
|
| 5171 |
+
"grad_norm": 0.0,
|
| 5172 |
+
"learning_rate": 3.5654999999999997e-05,
|
| 5173 |
+
"loss": 1.7493,
|
| 5174 |
+
"mean_token_accuracy": 0.6492699027061463,
|
| 5175 |
+
"num_tokens": 10466020.0,
|
| 5176 |
+
"step": 2870
|
| 5177 |
}
|
| 5178 |
],
|
| 5179 |
"logging_steps": 5,
|
|
|
|
| 5193 |
"attributes": {}
|
| 5194 |
}
|
| 5195 |
},
|
| 5196 |
+
"total_flos": 5.303020247108813e+17,
|
| 5197 |
"train_batch_size": 4,
|
| 5198 |
"trial_name": null,
|
| 5199 |
"trial_params": null
|