Training in progress, step 2380, 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 sha256:718a1c6bb60e771d9b96310ba54b79e45ed169697daf1f618bfe3f8d3168e73d
|
| 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 sha256:86e91f7d5cf1bd75180f574dcd1eb0d0aac17c549c92633b40ff0c9318be2f7e
|
| 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 sha256:0a881cb2cd7ac582c47a6fbfb025af6326fe0f8e20798982276f9122c45c41bf
|
| 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": 18.
|
| 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,
|
|
@@ -4274,6 +4274,24 @@
|
|
| 4274 |
"mean_token_accuracy": 0.6589814841747283,
|
| 4275 |
"num_tokens": 8643122.0,
|
| 4276 |
"step": 2370
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4277 |
}
|
| 4278 |
],
|
| 4279 |
"logging_steps": 5,
|
|
@@ -4293,7 +4311,7 @@
|
|
| 4293 |
"attributes": {}
|
| 4294 |
}
|
| 4295 |
},
|
| 4296 |
-
"total_flos": 4.
|
| 4297 |
"train_batch_size": 4,
|
| 4298 |
"trial_name": null,
|
| 4299 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 18.307692307692307,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2380,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4274 |
"mean_token_accuracy": 0.6589814841747283,
|
| 4275 |
"num_tokens": 8643122.0,
|
| 4276 |
"step": 2370
|
| 4277 |
+
},
|
| 4278 |
+
{
|
| 4279 |
+
"epoch": 18.26923076923077,
|
| 4280 |
+
"grad_norm": 0.0,
|
| 4281 |
+
"learning_rate": 3.8129999999999996e-05,
|
| 4282 |
+
"loss": 1.7568,
|
| 4283 |
+
"mean_token_accuracy": 0.6480594784021377,
|
| 4284 |
+
"num_tokens": 8660823.0,
|
| 4285 |
+
"step": 2375
|
| 4286 |
+
},
|
| 4287 |
+
{
|
| 4288 |
+
"epoch": 18.307692307692307,
|
| 4289 |
+
"grad_norm": 0.0,
|
| 4290 |
+
"learning_rate": 3.8105e-05,
|
| 4291 |
+
"loss": 1.7531,
|
| 4292 |
+
"mean_token_accuracy": 0.6460558891296386,
|
| 4293 |
+
"num_tokens": 8678813.0,
|
| 4294 |
+
"step": 2380
|
| 4295 |
}
|
| 4296 |
],
|
| 4297 |
"logging_steps": 5,
|
|
|
|
| 4311 |
"attributes": {}
|
| 4312 |
}
|
| 4313 |
},
|
| 4314 |
+
"total_flos": 4.39766631862272e+17,
|
| 4315 |
"train_batch_size": 4,
|
| 4316 |
"trial_name": null,
|
| 4317 |
"trial_params": null
|