Training in progress, step 8420, 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 sha256:347ffc3b1d2126f1df71ad5c852759b65975fc27713160ce0e88c75ee584c83a
|
| 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 sha256:3f8f27b1cd6c79c54ac50e69f610e0cf9df920a0c8607bbe220b6aa5c56402cc
|
| 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 sha256:8831267f98e585529172e723630b97fe684b45e574936b4191e5b530b7ebccea
|
| 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": 64.
|
| 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,
|
|
@@ -15146,6 +15146,24 @@
|
|
| 15146 |
"mean_token_accuracy": 0.649465736746788,
|
| 15147 |
"num_tokens": 30672362.0,
|
| 15148 |
"step": 8410
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15149 |
}
|
| 15150 |
],
|
| 15151 |
"logging_steps": 5,
|
|
@@ -15165,7 +15183,7 @@
|
|
| 15165 |
"attributes": {}
|
| 15166 |
}
|
| 15167 |
},
|
| 15168 |
-
"total_flos": 1.
|
| 15169 |
"train_batch_size": 4,
|
| 15170 |
"trial_name": null,
|
| 15171 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 64.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8420,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15146 |
"mean_token_accuracy": 0.649465736746788,
|
| 15147 |
"num_tokens": 30672362.0,
|
| 15148 |
"step": 8410
|
| 15149 |
+
},
|
| 15150 |
+
{
|
| 15151 |
+
"epoch": 64.73076923076923,
|
| 15152 |
+
"grad_norm": 0.0,
|
| 15153 |
+
"learning_rate": 7.93e-06,
|
| 15154 |
+
"loss": 1.7322,
|
| 15155 |
+
"mean_token_accuracy": 0.6514311760663987,
|
| 15156 |
+
"num_tokens": 30690881.0,
|
| 15157 |
+
"step": 8415
|
| 15158 |
+
},
|
| 15159 |
+
{
|
| 15160 |
+
"epoch": 64.76923076923077,
|
| 15161 |
+
"grad_norm": 0.0,
|
| 15162 |
+
"learning_rate": 7.905e-06,
|
| 15163 |
+
"loss": 1.7387,
|
| 15164 |
+
"mean_token_accuracy": 0.6512942612171173,
|
| 15165 |
+
"num_tokens": 30708498.0,
|
| 15166 |
+
"step": 8420
|
| 15167 |
}
|
| 15168 |
],
|
| 15169 |
"logging_steps": 5,
|
|
|
|
| 15183 |
"attributes": {}
|
| 15184 |
}
|
| 15185 |
},
|
| 15186 |
+
"total_flos": 1.5570024393734554e+18,
|
| 15187 |
"train_batch_size": 4,
|
| 15188 |
"trial_name": null,
|
| 15189 |
"trial_params": null
|