Training in progress, step 3330, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:40f7a41eb017920b1ba0f51c956225c54310527d5cb7b4edd5c0ac0d12e63d38
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91c52fb7b32e274420b678f63b3cddcf84924519fd4d65ceb98b701b5646eef5
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0bb26c2716c77e1930ff98eb344ea3e14cd002587776573c5a3f9d6745842460
|
| 3 |
size 14645
|
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 sha256:7161368fc381c5961b950cec89a17741bd71b752123efc592a708fb2d6b0aadc
|
| 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": 0.
|
| 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,
|
|
@@ -3338,6 +3338,16 @@
|
|
| 3338 |
"mean_token_accuracy": 0.752461838722229,
|
| 3339 |
"num_tokens": 15454949.0,
|
| 3340 |
"step": 3320
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3341 |
}
|
| 3342 |
],
|
| 3343 |
"logging_steps": 10,
|
|
@@ -3357,7 +3367,7 @@
|
|
| 3357 |
"attributes": {}
|
| 3358 |
}
|
| 3359 |
},
|
| 3360 |
-
"total_flos": 7.
|
| 3361 |
"train_batch_size": 4,
|
| 3362 |
"trial_name": null,
|
| 3363 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7104,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3330,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3338 |
"mean_token_accuracy": 0.752461838722229,
|
| 3339 |
"num_tokens": 15454949.0,
|
| 3340 |
"step": 3320
|
| 3341 |
+
},
|
| 3342 |
+
{
|
| 3343 |
+
"entropy": 1.0468340575695039,
|
| 3344 |
+
"epoch": 0.7104,
|
| 3345 |
+
"grad_norm": 0.29637107253074646,
|
| 3346 |
+
"learning_rate": 7.494502231803211e-05,
|
| 3347 |
+
"loss": 1.148671531677246,
|
| 3348 |
+
"mean_token_accuracy": 0.7463315047323704,
|
| 3349 |
+
"num_tokens": 15507585.0,
|
| 3350 |
+
"step": 3330
|
| 3351 |
}
|
| 3352 |
],
|
| 3353 |
"logging_steps": 10,
|
|
|
|
| 3367 |
"attributes": {}
|
| 3368 |
}
|
| 3369 |
},
|
| 3370 |
+
"total_flos": 7.346705144065536e+16,
|
| 3371 |
"train_batch_size": 4,
|
| 3372 |
"trial_name": null,
|
| 3373 |
"trial_params": null
|