Training in progress, step 4620, 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:d4d6d836e70f61a20b29e333a6c58f30be262b705619f0ffce4059249472f686
|
| 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 sha256:3947797d383f95e8d4b4ac8d1fd7756f5563b85f2958dd2a8a936be2eccb548f
|
| 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:ea46c8002c656ec2af61f99ecd4fcbc51922598d077280955c4f6013ce3e750f
|
| 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": 35.
|
| 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,
|
|
@@ -8306,6 +8306,24 @@
|
|
| 8306 |
"mean_token_accuracy": 0.6382217675447464,
|
| 8307 |
"num_tokens": 16812133.0,
|
| 8308 |
"step": 4610
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8309 |
}
|
| 8310 |
],
|
| 8311 |
"logging_steps": 5,
|
|
@@ -8325,7 +8343,7 @@
|
|
| 8325 |
"attributes": {}
|
| 8326 |
}
|
| 8327 |
},
|
| 8328 |
-
"total_flos": 8.
|
| 8329 |
"train_batch_size": 4,
|
| 8330 |
"trial_name": null,
|
| 8331 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 35.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4620,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8306 |
"mean_token_accuracy": 0.6382217675447464,
|
| 8307 |
"num_tokens": 16812133.0,
|
| 8308 |
"step": 4610
|
| 8309 |
+
},
|
| 8310 |
+
{
|
| 8311 |
+
"epoch": 35.5,
|
| 8312 |
+
"grad_norm": 0.0,
|
| 8313 |
+
"learning_rate": 2.693e-05,
|
| 8314 |
+
"loss": 1.7595,
|
| 8315 |
+
"mean_token_accuracy": 0.6477942883968353,
|
| 8316 |
+
"num_tokens": 16829745.0,
|
| 8317 |
+
"step": 4615
|
| 8318 |
+
},
|
| 8319 |
+
{
|
| 8320 |
+
"epoch": 35.53846153846154,
|
| 8321 |
+
"grad_norm": 0.0,
|
| 8322 |
+
"learning_rate": 2.6905e-05,
|
| 8323 |
+
"loss": 1.7319,
|
| 8324 |
+
"mean_token_accuracy": 0.6578234076499939,
|
| 8325 |
+
"num_tokens": 16848720.0,
|
| 8326 |
+
"step": 4620
|
| 8327 |
}
|
| 8328 |
],
|
| 8329 |
"logging_steps": 5,
|
|
|
|
| 8343 |
"attributes": {}
|
| 8344 |
}
|
| 8345 |
},
|
| 8346 |
+
"total_flos": 8.539223462151782e+17,
|
| 8347 |
"train_batch_size": 4,
|
| 8348 |
"trial_name": null,
|
| 8349 |
"trial_params": null
|