Training in progress, step 3560, 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 sha256:8d5f1028afe39be13e5e2d3169b86befec6ca511254a3e8d6662cbb988017a44
|
| 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 sha256:3898fb6533f1e6272bd6f942bff5dfb22ea89b00668e96657660d683512eaac2
|
| 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 sha256:27a549a6210b23c1a164b630278ffa41fb81041efb2d5bd2257daf14d713fb1e
|
| 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": 27.
|
| 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,
|
|
@@ -6398,6 +6398,24 @@
|
|
| 6398 |
"mean_token_accuracy": 0.6481869876384735,
|
| 6399 |
"num_tokens": 12945933.0,
|
| 6400 |
"step": 3550
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6401 |
}
|
| 6402 |
],
|
| 6403 |
"logging_steps": 5,
|
|
@@ -6417,7 +6435,7 @@
|
|
| 6417 |
"attributes": {}
|
| 6418 |
}
|
| 6419 |
},
|
| 6420 |
-
"total_flos": 6.
|
| 6421 |
"train_batch_size": 4,
|
| 6422 |
"trial_name": null,
|
| 6423 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 27.384615384615383,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3560,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6398 |
"mean_token_accuracy": 0.6481869876384735,
|
| 6399 |
"num_tokens": 12945933.0,
|
| 6400 |
"step": 3550
|
| 6401 |
+
},
|
| 6402 |
+
{
|
| 6403 |
+
"epoch": 27.346153846153847,
|
| 6404 |
+
"grad_norm": 0.0,
|
| 6405 |
+
"learning_rate": 3.223e-05,
|
| 6406 |
+
"loss": 1.7767,
|
| 6407 |
+
"mean_token_accuracy": 0.6434827774763108,
|
| 6408 |
+
"num_tokens": 12963760.0,
|
| 6409 |
+
"step": 3555
|
| 6410 |
+
},
|
| 6411 |
+
{
|
| 6412 |
+
"epoch": 27.384615384615383,
|
| 6413 |
+
"grad_norm": 0.0,
|
| 6414 |
+
"learning_rate": 3.2205e-05,
|
| 6415 |
+
"loss": 1.7383,
|
| 6416 |
+
"mean_token_accuracy": 0.6473019540309906,
|
| 6417 |
+
"num_tokens": 12982243.0,
|
| 6418 |
+
"step": 3560
|
| 6419 |
}
|
| 6420 |
],
|
| 6421 |
"logging_steps": 5,
|
|
|
|
| 6435 |
"attributes": {}
|
| 6436 |
}
|
| 6437 |
},
|
| 6438 |
+
"total_flos": 6.578045371662336e+17,
|
| 6439 |
"train_batch_size": 4,
|
| 6440 |
"trial_name": null,
|
| 6441 |
"trial_params": null
|