Training in progress, step 3340, 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:b472b654199caf73d5cb5d2f954ca9d412ae63f453e15bb10b06780efffb5d0e
|
| 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:fcc9dac8600093e92e6824f514d93121b6860f3219ee38e132eaf05ee35f49fa
|
| 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 sha256:8f3a15a609dd69222c755802144ef733eb4308a90ecaad98dd4b46a6d5910978
|
| 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:f24b81d8db80ec4d4525377f81deff9eea1b6a666a034271c3130c7fd42bfce3
|
| 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,
|
|
@@ -3348,6 +3348,16 @@
|
|
| 3348 |
"mean_token_accuracy": 0.7463315047323704,
|
| 3349 |
"num_tokens": 15507585.0,
|
| 3350 |
"step": 3330
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3351 |
}
|
| 3352 |
],
|
| 3353 |
"logging_steps": 10,
|
|
@@ -3367,7 +3377,7 @@
|
|
| 3367 |
"attributes": {}
|
| 3368 |
}
|
| 3369 |
},
|
| 3370 |
-
"total_flos": 7.
|
| 3371 |
"train_batch_size": 4,
|
| 3372 |
"trial_name": null,
|
| 3373 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7125333333333334,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3340,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3348 |
"mean_token_accuracy": 0.7463315047323704,
|
| 3349 |
"num_tokens": 15507585.0,
|
| 3350 |
"step": 3330
|
| 3351 |
+
},
|
| 3352 |
+
{
|
| 3353 |
+
"entropy": 0.9354016333818436,
|
| 3354 |
+
"epoch": 0.7125333333333334,
|
| 3355 |
+
"grad_norm": 0.2948022782802582,
|
| 3356 |
+
"learning_rate": 7.47948792111662e-05,
|
| 3357 |
+
"loss": 1.0402913093566895,
|
| 3358 |
+
"mean_token_accuracy": 0.7643374137580394,
|
| 3359 |
+
"num_tokens": 15554937.0,
|
| 3360 |
+
"step": 3340
|
| 3361 |
}
|
| 3362 |
],
|
| 3363 |
"logging_steps": 10,
|
|
|
|
| 3377 |
"attributes": {}
|
| 3378 |
}
|
| 3379 |
},
|
| 3380 |
+
"total_flos": 7.369165424356762e+16,
|
| 3381 |
"train_batch_size": 4,
|
| 3382 |
"trial_name": null,
|
| 3383 |
"trial_params": null
|