Training in progress, step 3280, 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:e45c3f6f05742bc6131e122410d700063c7b94c16446f38bbd4fda01c18a46a2
|
| 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 sha256:3bae4be30c6b5fbfd23c698ba28a300030f7b9a47e07fababe2d7b3090280a82
|
| 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:c41800993ded309f101c3b340160ad21de96415254d554502fa4c77e881cb579
|
| 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 sha256:5fa2b57bce6bf304e0446d71630bab51aed0163e838d537e1d9154359e0d2e40
|
| 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,
|
|
@@ -3288,6 +3288,16 @@
|
|
| 3288 |
"mean_token_accuracy": 0.7382091999053955,
|
| 3289 |
"num_tokens": 15212178.0,
|
| 3290 |
"step": 3270
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3291 |
}
|
| 3292 |
],
|
| 3293 |
"logging_steps": 10,
|
|
@@ -3307,7 +3317,7 @@
|
|
| 3307 |
"attributes": {}
|
| 3308 |
}
|
| 3309 |
},
|
| 3310 |
-
"total_flos": 7.
|
| 3311 |
"train_batch_size": 4,
|
| 3312 |
"trial_name": null,
|
| 3313 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.6997333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3280,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3288 |
"mean_token_accuracy": 0.7382091999053955,
|
| 3289 |
"num_tokens": 15212178.0,
|
| 3290 |
"step": 3270
|
| 3291 |
+
},
|
| 3292 |
+
{
|
| 3293 |
+
"entropy": 1.099733480066061,
|
| 3294 |
+
"epoch": 0.6997333333333333,
|
| 3295 |
+
"grad_norm": 0.26093462109565735,
|
| 3296 |
+
"learning_rate": 7.569121882647634e-05,
|
| 3297 |
+
"loss": 1.2072590827941894,
|
| 3298 |
+
"mean_token_accuracy": 0.7411856979131699,
|
| 3299 |
+
"num_tokens": 15261433.0,
|
| 3300 |
+
"step": 3280
|
| 3301 |
}
|
| 3302 |
],
|
| 3303 |
"logging_steps": 10,
|
|
|
|
| 3317 |
"attributes": {}
|
| 3318 |
}
|
| 3319 |
},
|
| 3320 |
+
"total_flos": 7.228015228907827e+16,
|
| 3321 |
"train_batch_size": 4,
|
| 3322 |
"trial_name": null,
|
| 3323 |
"trial_params": null
|