Training in progress, step 7860, 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:cb4fda9ae6a26d9139f3ef90f4cb35befbba99db937e664e9ce620c49f5bc918
|
| 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 sha256:04e0d6c4e683c6553d408d48fb49f1670325b070696b84a5f98f629b10a9d1be
|
| 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 sha256:9905c99e70bbd35dbbc60dcff96aa69df5c7eb509be2ecdb117e2900695b5307
|
| 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": 60.
|
| 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,
|
|
@@ -14138,6 +14138,24 @@
|
|
| 14138 |
"mean_token_accuracy": 0.6548949480056763,
|
| 14139 |
"num_tokens": 28626786.0,
|
| 14140 |
"step": 7850
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14141 |
}
|
| 14142 |
],
|
| 14143 |
"logging_steps": 5,
|
|
@@ -14157,7 +14175,7 @@
|
|
| 14157 |
"attributes": {}
|
| 14158 |
}
|
| 14159 |
},
|
| 14160 |
-
"total_flos": 1.
|
| 14161 |
"train_batch_size": 4,
|
| 14162 |
"trial_name": null,
|
| 14163 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 60.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7860,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14138 |
"mean_token_accuracy": 0.6548949480056763,
|
| 14139 |
"num_tokens": 28626786.0,
|
| 14140 |
"step": 7850
|
| 14141 |
+
},
|
| 14142 |
+
{
|
| 14143 |
+
"epoch": 60.42307692307692,
|
| 14144 |
+
"grad_norm": 0.0,
|
| 14145 |
+
"learning_rate": 1.073e-05,
|
| 14146 |
+
"loss": 1.7265,
|
| 14147 |
+
"mean_token_accuracy": 0.6512384116649628,
|
| 14148 |
+
"num_tokens": 28645473.0,
|
| 14149 |
+
"step": 7855
|
| 14150 |
+
},
|
| 14151 |
+
{
|
| 14152 |
+
"epoch": 60.46153846153846,
|
| 14153 |
+
"grad_norm": 0.0,
|
| 14154 |
+
"learning_rate": 1.0705000000000002e-05,
|
| 14155 |
+
"loss": 1.6828,
|
| 14156 |
+
"mean_token_accuracy": 0.662873387336731,
|
| 14157 |
+
"num_tokens": 28664176.0,
|
| 14158 |
+
"step": 7860
|
| 14159 |
}
|
| 14160 |
],
|
| 14161 |
"logging_steps": 5,
|
|
|
|
| 14175 |
"attributes": {}
|
| 14176 |
}
|
| 14177 |
},
|
| 14178 |
+
"total_flos": 1.4534031747096576e+18,
|
| 14179 |
"train_batch_size": 4,
|
| 14180 |
"trial_name": null,
|
| 14181 |
"trial_params": null
|