Training in progress, step 7180, 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 sha256:2af3782459772ea2c14cc77082ba4b19afaa3f544cbd70a4aedf7fee7ad46236
|
| 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 sha256:3204b9bea999eed1681b9587184a3232be543b26a057502f357e0057e07d7776
|
| 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:f8c2b7ea13908f48866a2700829bf0fb28ff080983a522aa51b11a14422f251b
|
| 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": 55.
|
| 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,
|
|
@@ -12914,6 +12914,24 @@
|
|
| 12914 |
"mean_token_accuracy": 0.644039872288704,
|
| 12915 |
"num_tokens": 26148751.0,
|
| 12916 |
"step": 7170
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12917 |
}
|
| 12918 |
],
|
| 12919 |
"logging_steps": 5,
|
|
@@ -12933,7 +12951,7 @@
|
|
| 12933 |
"attributes": {}
|
| 12934 |
}
|
| 12935 |
},
|
| 12936 |
-
"total_flos": 1.
|
| 12937 |
"train_batch_size": 4,
|
| 12938 |
"trial_name": null,
|
| 12939 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 55.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7180,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12914 |
"mean_token_accuracy": 0.644039872288704,
|
| 12915 |
"num_tokens": 26148751.0,
|
| 12916 |
"step": 7170
|
| 12917 |
+
},
|
| 12918 |
+
{
|
| 12919 |
+
"epoch": 55.19230769230769,
|
| 12920 |
+
"grad_norm": 0.0,
|
| 12921 |
+
"learning_rate": 1.4130000000000002e-05,
|
| 12922 |
+
"loss": 1.743,
|
| 12923 |
+
"mean_token_accuracy": 0.6448181957006455,
|
| 12924 |
+
"num_tokens": 26167250.0,
|
| 12925 |
+
"step": 7175
|
| 12926 |
+
},
|
| 12927 |
+
{
|
| 12928 |
+
"epoch": 55.23076923076923,
|
| 12929 |
+
"grad_norm": 0.0,
|
| 12930 |
+
"learning_rate": 1.4105000000000001e-05,
|
| 12931 |
+
"loss": 1.7366,
|
| 12932 |
+
"mean_token_accuracy": 0.6529501020908356,
|
| 12933 |
+
"num_tokens": 26185026.0,
|
| 12934 |
+
"step": 7180
|
| 12935 |
}
|
| 12936 |
],
|
| 12937 |
"logging_steps": 5,
|
|
|
|
| 12951 |
"attributes": {}
|
| 12952 |
}
|
| 12953 |
},
|
| 12954 |
+
"total_flos": 1.3277447232587366e+18,
|
| 12955 |
"train_batch_size": 4,
|
| 12956 |
"trial_name": null,
|
| 12957 |
"trial_params": null
|