Training in progress, step 1750, 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 sha256:7013009e24ebb7463537930970e04746e7804d535fa3b5ff3adf4c2757965deb
|
| 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 sha256:1d790e3e777e78c857c1f9dcd19c53ebf4e430fbba5ef75d0fe7390a9a57b870
|
| 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 sha256:75912b1f80056414d09766ac1971e8a7245b20f5c06ddc23c153b06b98cda606
|
| 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": 13.
|
| 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,
|
|
@@ -3140,6 +3140,24 @@
|
|
| 3140 |
"mean_token_accuracy": 0.6505321115255356,
|
| 3141 |
"num_tokens": 6344059.0,
|
| 3142 |
"step": 1740
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3143 |
}
|
| 3144 |
],
|
| 3145 |
"logging_steps": 5,
|
|
@@ -3159,7 +3177,7 @@
|
|
| 3159 |
"attributes": {}
|
| 3160 |
}
|
| 3161 |
},
|
| 3162 |
-
"total_flos": 3.
|
| 3163 |
"train_batch_size": 4,
|
| 3164 |
"trial_name": null,
|
| 3165 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 13.461538461538462,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1750,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3140 |
"mean_token_accuracy": 0.6505321115255356,
|
| 3141 |
"num_tokens": 6344059.0,
|
| 3142 |
"step": 1740
|
| 3143 |
+
},
|
| 3144 |
+
{
|
| 3145 |
+
"epoch": 13.423076923076923,
|
| 3146 |
+
"grad_norm": 0.0,
|
| 3147 |
+
"learning_rate": 4.1280000000000005e-05,
|
| 3148 |
+
"loss": 1.7164,
|
| 3149 |
+
"mean_token_accuracy": 0.652134558558464,
|
| 3150 |
+
"num_tokens": 6362364.0,
|
| 3151 |
+
"step": 1745
|
| 3152 |
+
},
|
| 3153 |
+
{
|
| 3154 |
+
"epoch": 13.461538461538462,
|
| 3155 |
+
"grad_norm": 0.0,
|
| 3156 |
+
"learning_rate": 4.1255e-05,
|
| 3157 |
+
"loss": 1.7474,
|
| 3158 |
+
"mean_token_accuracy": 0.6487911343574524,
|
| 3159 |
+
"num_tokens": 6380492.0,
|
| 3160 |
+
"step": 1750
|
| 3161 |
}
|
| 3162 |
],
|
| 3163 |
"logging_steps": 5,
|
|
|
|
| 3177 |
"attributes": {}
|
| 3178 |
}
|
| 3179 |
},
|
| 3180 |
+
"total_flos": 3.2324719051063296e+17,
|
| 3181 |
"train_batch_size": 4,
|
| 3182 |
"trial_name": null,
|
| 3183 |
"trial_params": null
|