Training in progress, step 7940, 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 sha256:30045ad841c3b4e442a12dfea13d5119704cc03756c7707586abaf8df68f7dd3
|
| 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:a8c4ae0846fad8066d6f6522357fd6fb9993d8decccb14539d6b27b481ceb146
|
| 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 sha256:334d644848c4b020f7fd8392c556cf9e286dabbb4839bbb1b87675e376af4e13
|
| 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": 61.
|
| 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,
|
|
@@ -14282,6 +14282,24 @@
|
|
| 14282 |
"mean_token_accuracy": 0.6521394342184067,
|
| 14283 |
"num_tokens": 28920405.0,
|
| 14284 |
"step": 7930
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14285 |
}
|
| 14286 |
],
|
| 14287 |
"logging_steps": 5,
|
|
@@ -14301,7 +14319,7 @@
|
|
| 14301 |
"attributes": {}
|
| 14302 |
}
|
| 14303 |
},
|
| 14304 |
-
"total_flos": 1.
|
| 14305 |
"train_batch_size": 4,
|
| 14306 |
"trial_name": null,
|
| 14307 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 61.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7940,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14282 |
"mean_token_accuracy": 0.6521394342184067,
|
| 14283 |
"num_tokens": 28920405.0,
|
| 14284 |
"step": 7930
|
| 14285 |
+
},
|
| 14286 |
+
{
|
| 14287 |
+
"epoch": 61.03846153846154,
|
| 14288 |
+
"grad_norm": 0.0,
|
| 14289 |
+
"learning_rate": 1.0330000000000001e-05,
|
| 14290 |
+
"loss": 1.7788,
|
| 14291 |
+
"mean_token_accuracy": 0.6419234901666642,
|
| 14292 |
+
"num_tokens": 28937930.0,
|
| 14293 |
+
"step": 7935
|
| 14294 |
+
},
|
| 14295 |
+
{
|
| 14296 |
+
"epoch": 61.07692307692308,
|
| 14297 |
+
"grad_norm": 0.0,
|
| 14298 |
+
"learning_rate": 1.0305e-05,
|
| 14299 |
+
"loss": 1.8234,
|
| 14300 |
+
"mean_token_accuracy": 0.6357664644718171,
|
| 14301 |
+
"num_tokens": 28955347.0,
|
| 14302 |
+
"step": 7940
|
| 14303 |
}
|
| 14304 |
],
|
| 14305 |
"logging_steps": 5,
|
|
|
|
| 14319 |
"attributes": {}
|
| 14320 |
}
|
| 14321 |
},
|
| 14322 |
+
"total_flos": 1.4681451833214566e+18,
|
| 14323 |
"train_batch_size": 4,
|
| 14324 |
"trial_name": null,
|
| 14325 |
"trial_params": null
|