Training in progress, step 4720, 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:a2c39282c5791e94072004ec33ee74653755c57adad9c31d6588af372fafc86c
|
| 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:ca1336e0ab14ffa427c850409448617c2739aaff3ffc22ac3ddcb147db937346
|
| 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:e5f5920f2f525f04a8b0fc149417f9fd6779cdf4226eb896672cd1b0e1bbbec3
|
| 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": 36.
|
| 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,
|
|
@@ -8486,6 +8486,24 @@
|
|
| 8486 |
"mean_token_accuracy": 0.6504531025886535,
|
| 8487 |
"num_tokens": 17176907.0,
|
| 8488 |
"step": 4710
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8489 |
}
|
| 8490 |
],
|
| 8491 |
"logging_steps": 5,
|
|
@@ -8505,7 +8523,7 @@
|
|
| 8505 |
"attributes": {}
|
| 8506 |
}
|
| 8507 |
},
|
| 8508 |
-
"total_flos": 8.
|
| 8509 |
"train_batch_size": 4,
|
| 8510 |
"trial_name": null,
|
| 8511 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 36.30769230769231,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4720,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8486 |
"mean_token_accuracy": 0.6504531025886535,
|
| 8487 |
"num_tokens": 17176907.0,
|
| 8488 |
"step": 4710
|
| 8489 |
+
},
|
| 8490 |
+
{
|
| 8491 |
+
"epoch": 36.26923076923077,
|
| 8492 |
+
"grad_norm": 0.0,
|
| 8493 |
+
"learning_rate": 2.643e-05,
|
| 8494 |
+
"loss": 1.751,
|
| 8495 |
+
"mean_token_accuracy": 0.6483948498964309,
|
| 8496 |
+
"num_tokens": 17195007.0,
|
| 8497 |
+
"step": 4715
|
| 8498 |
+
},
|
| 8499 |
+
{
|
| 8500 |
+
"epoch": 36.30769230769231,
|
| 8501 |
+
"grad_norm": 0.0,
|
| 8502 |
+
"learning_rate": 2.6405000000000002e-05,
|
| 8503 |
+
"loss": 1.6963,
|
| 8504 |
+
"mean_token_accuracy": 0.6590126276016235,
|
| 8505 |
+
"num_tokens": 17213782.0,
|
| 8506 |
+
"step": 4720
|
| 8507 |
}
|
| 8508 |
],
|
| 8509 |
"logging_steps": 5,
|
|
|
|
| 8523 |
"attributes": {}
|
| 8524 |
}
|
| 8525 |
},
|
| 8526 |
+
"total_flos": 8.724212282061619e+17,
|
| 8527 |
"train_batch_size": 4,
|
| 8528 |
"trial_name": null,
|
| 8529 |
"trial_params": null
|