Training in progress, step 7850, 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 sha256:6550b0075e7d6cfa897244fb25252704046b13c904a9b9070f086c47adf2dbce
|
| 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 sha256:63b3a0ad1389ac8814c8eed9fa30987baaa2e0db49a9a1b077be61eed6023a43
|
| 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 sha256:3cdd128a27fa3be9b9c7cc8b86226200ace9950a557616404973817f1d31a00f
|
| 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": 60.
|
| 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,
|
|
@@ -14120,6 +14120,24 @@
|
|
| 14120 |
"mean_token_accuracy": 0.6499844253063202,
|
| 14121 |
"num_tokens": 28590779.0,
|
| 14122 |
"step": 7840
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14123 |
}
|
| 14124 |
],
|
| 14125 |
"logging_steps": 5,
|
|
@@ -14139,7 +14157,7 @@
|
|
| 14139 |
"attributes": {}
|
| 14140 |
}
|
| 14141 |
},
|
| 14142 |
-
"total_flos": 1.
|
| 14143 |
"train_batch_size": 4,
|
| 14144 |
"trial_name": null,
|
| 14145 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 60.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7850,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14120 |
"mean_token_accuracy": 0.6499844253063202,
|
| 14121 |
"num_tokens": 28590779.0,
|
| 14122 |
"step": 7840
|
| 14123 |
+
},
|
| 14124 |
+
{
|
| 14125 |
+
"epoch": 60.34615384615385,
|
| 14126 |
+
"grad_norm": 0.0,
|
| 14127 |
+
"learning_rate": 1.0780000000000002e-05,
|
| 14128 |
+
"loss": 1.737,
|
| 14129 |
+
"mean_token_accuracy": 0.6540430366992951,
|
| 14130 |
+
"num_tokens": 28609298.0,
|
| 14131 |
+
"step": 7845
|
| 14132 |
+
},
|
| 14133 |
+
{
|
| 14134 |
+
"epoch": 60.38461538461539,
|
| 14135 |
+
"grad_norm": 0.0,
|
| 14136 |
+
"learning_rate": 1.0755000000000001e-05,
|
| 14137 |
+
"loss": 1.7464,
|
| 14138 |
+
"mean_token_accuracy": 0.6548949480056763,
|
| 14139 |
+
"num_tokens": 28626786.0,
|
| 14140 |
+
"step": 7850
|
| 14141 |
}
|
| 14142 |
],
|
| 14143 |
"logging_steps": 5,
|
|
|
|
| 14157 |
"attributes": {}
|
| 14158 |
}
|
| 14159 |
},
|
| 14160 |
+
"total_flos": 1.4515270403176858e+18,
|
| 14161 |
"train_batch_size": 4,
|
| 14162 |
"trial_name": null,
|
| 14163 |
"trial_params": null
|