Training in progress, step 3090, 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:a9c063d6da9181d4e78427eede8bdf9723167d52c72131d644362eecd74ad48e
|
| 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 sha256:3dbcec87d986856441c11ae6d011d63d71dcb867cf969db05ee378582e014479
|
| 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 sha256:313f9033e78a4a688c1f2abf4ffc2d74334820a907a1d2d47718e904b04ed81b
|
| 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": 23.
|
| 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,
|
|
@@ -5552,6 +5552,24 @@
|
|
| 5552 |
"mean_token_accuracy": 0.6658029884099961,
|
| 5553 |
"num_tokens": 11233473.0,
|
| 5554 |
"step": 3080
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5555 |
}
|
| 5556 |
],
|
| 5557 |
"logging_steps": 5,
|
|
@@ -5571,7 +5589,7 @@
|
|
| 5571 |
"attributes": {}
|
| 5572 |
}
|
| 5573 |
},
|
| 5574 |
-
"total_flos": 5.
|
| 5575 |
"train_batch_size": 4,
|
| 5576 |
"trial_name": null,
|
| 5577 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 23.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3090,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5552 |
"mean_token_accuracy": 0.6658029884099961,
|
| 5553 |
"num_tokens": 11233473.0,
|
| 5554 |
"step": 3080
|
| 5555 |
+
},
|
| 5556 |
+
{
|
| 5557 |
+
"epoch": 23.73076923076923,
|
| 5558 |
+
"grad_norm": 0.0,
|
| 5559 |
+
"learning_rate": 3.4580000000000004e-05,
|
| 5560 |
+
"loss": 1.8208,
|
| 5561 |
+
"mean_token_accuracy": 0.6367295324802399,
|
| 5562 |
+
"num_tokens": 11250907.0,
|
| 5563 |
+
"step": 3085
|
| 5564 |
+
},
|
| 5565 |
+
{
|
| 5566 |
+
"epoch": 23.76923076923077,
|
| 5567 |
+
"grad_norm": 0.0,
|
| 5568 |
+
"learning_rate": 3.4555000000000004e-05,
|
| 5569 |
+
"loss": 1.7758,
|
| 5570 |
+
"mean_token_accuracy": 0.6431278616189957,
|
| 5571 |
+
"num_tokens": 11268887.0,
|
| 5572 |
+
"step": 3090
|
| 5573 |
}
|
| 5574 |
],
|
| 5575 |
"logging_steps": 5,
|
|
|
|
| 5589 |
"attributes": {}
|
| 5590 |
}
|
| 5591 |
},
|
| 5592 |
+
"total_flos": 5.709864816893952e+17,
|
| 5593 |
"train_batch_size": 4,
|
| 5594 |
"trial_name": null,
|
| 5595 |
"trial_params": null
|