Training in progress, step 8170, 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 sha256:1b1c5491580541310fd8ac09551070b5d3fe9b6400f8e736a49de71b08a8a97c
|
| 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 sha256:5ef03099c01546d51d0ba7a8338fd564bf698233a418f221a1e2d01781725844
|
| 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:d53d7093b0d21ad867020e5ecc58d4f14bfeb7dce3e3eb660008e6f38ee743ca
|
| 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": 62.
|
| 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,
|
|
@@ -14696,6 +14696,24 @@
|
|
| 14696 |
"mean_token_accuracy": 0.6471410870552063,
|
| 14697 |
"num_tokens": 29760581.0,
|
| 14698 |
"step": 8160
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14699 |
}
|
| 14700 |
],
|
| 14701 |
"logging_steps": 5,
|
|
@@ -14715,7 +14733,7 @@
|
|
| 14715 |
"attributes": {}
|
| 14716 |
}
|
| 14717 |
},
|
| 14718 |
-
"total_flos": 1.
|
| 14719 |
"train_batch_size": 4,
|
| 14720 |
"trial_name": null,
|
| 14721 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 62.84615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8170,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14696 |
"mean_token_accuracy": 0.6471410870552063,
|
| 14697 |
"num_tokens": 29760581.0,
|
| 14698 |
"step": 8160
|
| 14699 |
+
},
|
| 14700 |
+
{
|
| 14701 |
+
"epoch": 62.80769230769231,
|
| 14702 |
+
"grad_norm": 0.0,
|
| 14703 |
+
"learning_rate": 9.180000000000002e-06,
|
| 14704 |
+
"loss": 1.7447,
|
| 14705 |
+
"mean_token_accuracy": 0.6508060991764069,
|
| 14706 |
+
"num_tokens": 29778883.0,
|
| 14707 |
+
"step": 8165
|
| 14708 |
+
},
|
| 14709 |
+
{
|
| 14710 |
+
"epoch": 62.84615384615385,
|
| 14711 |
+
"grad_norm": 0.0,
|
| 14712 |
+
"learning_rate": 9.155000000000001e-06,
|
| 14713 |
+
"loss": 1.7297,
|
| 14714 |
+
"mean_token_accuracy": 0.6586943835020065,
|
| 14715 |
+
"num_tokens": 29796604.0,
|
| 14716 |
+
"step": 8170
|
| 14717 |
}
|
| 14718 |
],
|
| 14719 |
"logging_steps": 5,
|
|
|
|
| 14733 |
"attributes": {}
|
| 14734 |
}
|
| 14735 |
},
|
| 14736 |
+
"total_flos": 1.5107070449251123e+18,
|
| 14737 |
"train_batch_size": 4,
|
| 14738 |
"trial_name": null,
|
| 14739 |
"trial_params": null
|