Training in progress, step 4650, 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:d46c708bf9e93bebb8c5ed9786eae9647033d32a9eff5912fa79c1c6c7690872
|
| 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 sha256:0b8cec1f8ef2f66c1e899a42b2226891acec11da91645757952254b2f722848a
|
| 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:e3ffcb1fdffcb2f945f45941075aadaebbfab0c00996084273ffa88ad6333d0f
|
| 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": 35.
|
| 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,
|
|
@@ -8360,6 +8360,24 @@
|
|
| 8360 |
"mean_token_accuracy": 0.6473292171955108,
|
| 8361 |
"num_tokens": 16921974.0,
|
| 8362 |
"step": 4640
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8363 |
}
|
| 8364 |
],
|
| 8365 |
"logging_steps": 5,
|
|
@@ -8379,7 +8397,7 @@
|
|
| 8379 |
"attributes": {}
|
| 8380 |
}
|
| 8381 |
},
|
| 8382 |
-
"total_flos": 8.
|
| 8383 |
"train_batch_size": 4,
|
| 8384 |
"trial_name": null,
|
| 8385 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 35.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4650,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8360 |
"mean_token_accuracy": 0.6473292171955108,
|
| 8361 |
"num_tokens": 16921974.0,
|
| 8362 |
"step": 4640
|
| 8363 |
+
},
|
| 8364 |
+
{
|
| 8365 |
+
"epoch": 35.73076923076923,
|
| 8366 |
+
"grad_norm": 0.0,
|
| 8367 |
+
"learning_rate": 2.678e-05,
|
| 8368 |
+
"loss": 1.758,
|
| 8369 |
+
"mean_token_accuracy": 0.6488713294267654,
|
| 8370 |
+
"num_tokens": 16939451.0,
|
| 8371 |
+
"step": 4645
|
| 8372 |
+
},
|
| 8373 |
+
{
|
| 8374 |
+
"epoch": 35.76923076923077,
|
| 8375 |
+
"grad_norm": 0.0,
|
| 8376 |
+
"learning_rate": 2.6755000000000004e-05,
|
| 8377 |
+
"loss": 1.7267,
|
| 8378 |
+
"mean_token_accuracy": 0.653421950340271,
|
| 8379 |
+
"num_tokens": 16958067.0,
|
| 8380 |
+
"step": 4650
|
| 8381 |
}
|
| 8382 |
],
|
| 8383 |
"logging_steps": 5,
|
|
|
|
| 8397 |
"attributes": {}
|
| 8398 |
}
|
| 8399 |
},
|
| 8400 |
+
"total_flos": 8.594218207243469e+17,
|
| 8401 |
"train_batch_size": 4,
|
| 8402 |
"trial_name": null,
|
| 8403 |
"trial_params": null
|