Training in progress, step 7900, 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 sha256:515fbcc8cce1291f5a9a6c9022704f43b02621c218ae3bd9d96f942e8d107d82
|
| 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:ed55ecb945186849d74c8fa0299403a4a03e403ef4b15c084426a3ae5129f8a3
|
| 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:e2f02ae708266e84dc9e48391afa7060be3555e66e0d54da1f6b2ac7afd52109
|
| 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,
|
|
@@ -14210,6 +14210,24 @@
|
|
| 14210 |
"mean_token_accuracy": 0.651301595568657,
|
| 14211 |
"num_tokens": 28775068.0,
|
| 14212 |
"step": 7890
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14213 |
}
|
| 14214 |
],
|
| 14215 |
"logging_steps": 5,
|
|
@@ -14229,7 +14247,7 @@
|
|
| 14229 |
"attributes": {}
|
| 14230 |
}
|
| 14231 |
},
|
| 14232 |
-
"total_flos": 1.
|
| 14233 |
"train_batch_size": 4,
|
| 14234 |
"trial_name": null,
|
| 14235 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 60.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7900,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14210 |
"mean_token_accuracy": 0.651301595568657,
|
| 14211 |
"num_tokens": 28775068.0,
|
| 14212 |
"step": 7890
|
| 14213 |
+
},
|
| 14214 |
+
{
|
| 14215 |
+
"epoch": 60.73076923076923,
|
| 14216 |
+
"grad_norm": 0.0,
|
| 14217 |
+
"learning_rate": 1.053e-05,
|
| 14218 |
+
"loss": 1.7901,
|
| 14219 |
+
"mean_token_accuracy": 0.6404271066188812,
|
| 14220 |
+
"num_tokens": 28792926.0,
|
| 14221 |
+
"step": 7895
|
| 14222 |
+
},
|
| 14223 |
+
{
|
| 14224 |
+
"epoch": 60.76923076923077,
|
| 14225 |
+
"grad_norm": 0.0,
|
| 14226 |
+
"learning_rate": 1.0505e-05,
|
| 14227 |
+
"loss": 1.7377,
|
| 14228 |
+
"mean_token_accuracy": 0.6532931387424469,
|
| 14229 |
+
"num_tokens": 28810975.0,
|
| 14230 |
+
"step": 7900
|
| 14231 |
}
|
| 14232 |
],
|
| 14233 |
"logging_steps": 5,
|
|
|
|
| 14247 |
"attributes": {}
|
| 14248 |
}
|
| 14249 |
},
|
| 14250 |
+
"total_flos": 1.460917080247173e+18,
|
| 14251 |
"train_batch_size": 4,
|
| 14252 |
"trial_name": null,
|
| 14253 |
"trial_params": null
|