Training in progress, step 4250, 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 sha256:234ae46be3234a4d6eb3d3ced990d2867b36ff0e36446ecc97db768ab046f28a
|
| 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 sha256:41fe669f6586d48056e9db3721d1a6cb8140fe65932bc7dcb377b2cb0b9e7172
|
| 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:be45b31610dc9b7b30978cbbf0b5d1111e99e0e0a37748635d3a485fbdfec4c4
|
| 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": 32.
|
| 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,
|
|
@@ -7640,6 +7640,24 @@
|
|
| 7640 |
"mean_token_accuracy": 0.634194228053093,
|
| 7641 |
"num_tokens": 15464761.0,
|
| 7642 |
"step": 4240
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7643 |
}
|
| 7644 |
],
|
| 7645 |
"logging_steps": 5,
|
|
@@ -7659,7 +7677,7 @@
|
|
| 7659 |
"attributes": {}
|
| 7660 |
}
|
| 7661 |
},
|
| 7662 |
-
"total_flos": 7.
|
| 7663 |
"train_batch_size": 4,
|
| 7664 |
"trial_name": null,
|
| 7665 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 32.69230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4250,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7640 |
"mean_token_accuracy": 0.634194228053093,
|
| 7641 |
"num_tokens": 15464761.0,
|
| 7642 |
"step": 4240
|
| 7643 |
+
},
|
| 7644 |
+
{
|
| 7645 |
+
"epoch": 32.65384615384615,
|
| 7646 |
+
"grad_norm": 0.0,
|
| 7647 |
+
"learning_rate": 2.8780000000000002e-05,
|
| 7648 |
+
"loss": 1.7199,
|
| 7649 |
+
"mean_token_accuracy": 0.6551119357347488,
|
| 7650 |
+
"num_tokens": 15483259.0,
|
| 7651 |
+
"step": 4245
|
| 7652 |
+
},
|
| 7653 |
+
{
|
| 7654 |
+
"epoch": 32.69230769230769,
|
| 7655 |
+
"grad_norm": 0.0,
|
| 7656 |
+
"learning_rate": 2.8754999999999998e-05,
|
| 7657 |
+
"loss": 1.718,
|
| 7658 |
+
"mean_token_accuracy": 0.6517602205276489,
|
| 7659 |
+
"num_tokens": 15502102.0,
|
| 7660 |
+
"step": 4250
|
| 7661 |
}
|
| 7662 |
],
|
| 7663 |
"logging_steps": 5,
|
|
|
|
| 7677 |
"attributes": {}
|
| 7678 |
}
|
| 7679 |
},
|
| 7680 |
+
"total_flos": 7.857190815060787e+17,
|
| 7681 |
"train_batch_size": 4,
|
| 7682 |
"trial_name": null,
|
| 7683 |
"trial_params": null
|