Training in progress, step 1830, 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 sha256:73887a09e73b83071b634ee2e9536cdf57759965aa47ece2a0504481b9d1ac8c
|
| 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 sha256:347bf9e8a4df3e026b7920cb06cf5d72aac0570b95bd4433f1b6986094341db6
|
| 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:e8acf1f692688dc5d62ba01f97da01f81860f9277391fac5fcbe61a93438cf0c
|
| 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": 14.
|
| 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,
|
|
@@ -3284,6 +3284,24 @@
|
|
| 3284 |
"mean_token_accuracy": 0.6513684660196304,
|
| 3285 |
"num_tokens": 6637470.0,
|
| 3286 |
"step": 1820
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3287 |
}
|
| 3288 |
],
|
| 3289 |
"logging_steps": 5,
|
|
@@ -3303,7 +3321,7 @@
|
|
| 3303 |
"attributes": {}
|
| 3304 |
}
|
| 3305 |
},
|
| 3306 |
-
"total_flos": 3.
|
| 3307 |
"train_batch_size": 4,
|
| 3308 |
"trial_name": null,
|
| 3309 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 14.076923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1830,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3284 |
"mean_token_accuracy": 0.6513684660196304,
|
| 3285 |
"num_tokens": 6637470.0,
|
| 3286 |
"step": 1820
|
| 3287 |
+
},
|
| 3288 |
+
{
|
| 3289 |
+
"epoch": 14.038461538461538,
|
| 3290 |
+
"grad_norm": 0.0,
|
| 3291 |
+
"learning_rate": 4.088e-05,
|
| 3292 |
+
"loss": 1.6674,
|
| 3293 |
+
"mean_token_accuracy": 0.656906321644783,
|
| 3294 |
+
"num_tokens": 6657126.0,
|
| 3295 |
+
"step": 1825
|
| 3296 |
+
},
|
| 3297 |
+
{
|
| 3298 |
+
"epoch": 14.076923076923077,
|
| 3299 |
+
"grad_norm": 0.0,
|
| 3300 |
+
"learning_rate": 4.0855e-05,
|
| 3301 |
+
"loss": 1.7146,
|
| 3302 |
+
"mean_token_accuracy": 0.6526720136404037,
|
| 3303 |
+
"num_tokens": 6675746.0,
|
| 3304 |
+
"step": 1830
|
| 3305 |
}
|
| 3306 |
],
|
| 3307 |
"logging_steps": 5,
|
|
|
|
| 3321 |
"attributes": {}
|
| 3322 |
}
|
| 3323 |
},
|
| 3324 |
+
"total_flos": 3.3824181674409984e+17,
|
| 3325 |
"train_batch_size": 4,
|
| 3326 |
"trial_name": null,
|
| 3327 |
"trial_params": null
|