Training in progress, step 5090, 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:c9797bcb0d61a00b583b387effee455ab179a9ddae7b233f100e51eab951a91e
|
| 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:bd5652763c7bd02a62ec8651fcb9db9b6e67a624adfac3fc58404cd2d2b62660
|
| 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 sha256:5ce5eace27dd7730917cfb4fc09b14ad15eabc09868b8d331db69916afb14c88
|
| 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": 39.
|
| 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,
|
|
@@ -9152,6 +9152,24 @@
|
|
| 9152 |
"mean_token_accuracy": 0.650596770644188,
|
| 9153 |
"num_tokens": 18526534.0,
|
| 9154 |
"step": 5080
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9155 |
}
|
| 9156 |
],
|
| 9157 |
"logging_steps": 5,
|
|
@@ -9171,7 +9189,7 @@
|
|
| 9171 |
"attributes": {}
|
| 9172 |
}
|
| 9173 |
},
|
| 9174 |
-
"total_flos": 9.
|
| 9175 |
"train_batch_size": 4,
|
| 9176 |
"trial_name": null,
|
| 9177 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 39.15384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5090,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9152 |
"mean_token_accuracy": 0.650596770644188,
|
| 9153 |
"num_tokens": 18526534.0,
|
| 9154 |
"step": 5080
|
| 9155 |
+
},
|
| 9156 |
+
{
|
| 9157 |
+
"epoch": 39.11538461538461,
|
| 9158 |
+
"grad_norm": 0.0,
|
| 9159 |
+
"learning_rate": 2.4580000000000002e-05,
|
| 9160 |
+
"loss": 1.7074,
|
| 9161 |
+
"mean_token_accuracy": 0.6542585700750351,
|
| 9162 |
+
"num_tokens": 18544958.0,
|
| 9163 |
+
"step": 5085
|
| 9164 |
+
},
|
| 9165 |
+
{
|
| 9166 |
+
"epoch": 39.15384615384615,
|
| 9167 |
+
"grad_norm": 0.0,
|
| 9168 |
+
"learning_rate": 2.4555e-05,
|
| 9169 |
+
"loss": 1.7504,
|
| 9170 |
+
"mean_token_accuracy": 0.6499609500169754,
|
| 9171 |
+
"num_tokens": 18562850.0,
|
| 9172 |
+
"step": 5090
|
| 9173 |
}
|
| 9174 |
],
|
| 9175 |
"logging_steps": 5,
|
|
|
|
| 9189 |
"attributes": {}
|
| 9190 |
}
|
| 9191 |
},
|
| 9192 |
+
"total_flos": 9.406621235729203e+17,
|
| 9193 |
"train_batch_size": 4,
|
| 9194 |
"trial_name": null,
|
| 9195 |
"trial_params": null
|