Training in progress, step 8440, 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 sha256:3f3e8532588602c16c3b284689ac52b59a236012bfef8991460f3d4b31b40dc2
|
| 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:fbf0d4260b660a45cfbd7b32169f923965a7923ffa80f0c70490bbe2878d8af8
|
| 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:ef92a637e0d97c79feaca7b9920041c1091d68057daea04b624c1a1aaed33d46
|
| 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": 64.
|
| 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,
|
|
@@ -15182,6 +15182,24 @@
|
|
| 15182 |
"mean_token_accuracy": 0.6423812568187713,
|
| 15183 |
"num_tokens": 30745189.0,
|
| 15184 |
"step": 8430
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15185 |
}
|
| 15186 |
],
|
| 15187 |
"logging_steps": 5,
|
|
@@ -15201,7 +15219,7 @@
|
|
| 15201 |
"attributes": {}
|
| 15202 |
}
|
| 15203 |
},
|
| 15204 |
-
"total_flos": 1.
|
| 15205 |
"train_batch_size": 4,
|
| 15206 |
"trial_name": null,
|
| 15207 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 64.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8440,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15182 |
"mean_token_accuracy": 0.6423812568187713,
|
| 15183 |
"num_tokens": 30745189.0,
|
| 15184 |
"step": 8430
|
| 15185 |
+
},
|
| 15186 |
+
{
|
| 15187 |
+
"epoch": 64.88461538461539,
|
| 15188 |
+
"grad_norm": 0.0,
|
| 15189 |
+
"learning_rate": 7.83e-06,
|
| 15190 |
+
"loss": 1.7892,
|
| 15191 |
+
"mean_token_accuracy": 0.6339890867471695,
|
| 15192 |
+
"num_tokens": 30762976.0,
|
| 15193 |
+
"step": 8435
|
| 15194 |
+
},
|
| 15195 |
+
{
|
| 15196 |
+
"epoch": 64.92307692307692,
|
| 15197 |
+
"grad_norm": 0.0,
|
| 15198 |
+
"learning_rate": 7.805e-06,
|
| 15199 |
+
"loss": 1.7893,
|
| 15200 |
+
"mean_token_accuracy": 0.6393702328205109,
|
| 15201 |
+
"num_tokens": 30779931.0,
|
| 15202 |
+
"step": 8440
|
| 15203 |
}
|
| 15204 |
],
|
| 15205 |
"logging_steps": 5,
|
|
|
|
| 15219 |
"attributes": {}
|
| 15220 |
}
|
| 15221 |
},
|
| 15222 |
+
"total_flos": 1.5606835750998835e+18,
|
| 15223 |
"train_batch_size": 4,
|
| 15224 |
"trial_name": null,
|
| 15225 |
"trial_params": null
|