Training in progress, step 3290, 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 sha256:8d2dd6a837e8d598d85e7170a0b6c74e7a1ec7e154f27d42d2c050674c450023
|
| 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:ac75c911f8d1fde27d3d3372563f6ab2ee3a76fddd6c4b40dad92728ded41535
|
| 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:d6f8260a7dbb753a98fe474b03106f02aea828e170c7ce3b6a50b66d6a9730db
|
| 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:c200a1e7bad32fe2ffbe478363617531be963da6c90eeb8485e761715bbef23c
|
| 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,
|
|
@@ -3298,6 +3298,16 @@
|
|
| 3298 |
"mean_token_accuracy": 0.7411856979131699,
|
| 3299 |
"num_tokens": 15261433.0,
|
| 3300 |
"step": 3280
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3301 |
}
|
| 3302 |
],
|
| 3303 |
"logging_steps": 10,
|
|
@@ -3317,7 +3327,7 @@
|
|
| 3317 |
"attributes": {}
|
| 3318 |
}
|
| 3319 |
},
|
| 3320 |
-
"total_flos": 7.
|
| 3321 |
"train_batch_size": 4,
|
| 3322 |
"trial_name": null,
|
| 3323 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7018666666666666,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3290,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3298 |
"mean_token_accuracy": 0.7411856979131699,
|
| 3299 |
"num_tokens": 15261433.0,
|
| 3300 |
"step": 3280
|
| 3301 |
+
},
|
| 3302 |
+
{
|
| 3303 |
+
"entropy": 0.8516895264387131,
|
| 3304 |
+
"epoch": 0.7018666666666666,
|
| 3305 |
+
"grad_norm": 0.30177560448646545,
|
| 3306 |
+
"learning_rate": 7.554258802801226e-05,
|
| 3307 |
+
"loss": 0.9454229354858399,
|
| 3308 |
+
"mean_token_accuracy": 0.7824687540531159,
|
| 3309 |
+
"num_tokens": 15302428.0,
|
| 3310 |
+
"step": 3290
|
| 3311 |
}
|
| 3312 |
],
|
| 3313 |
"logging_steps": 10,
|
|
|
|
| 3327 |
"attributes": {}
|
| 3328 |
}
|
| 3329 |
},
|
| 3330 |
+
"total_flos": 7.248685752080794e+16,
|
| 3331 |
"train_batch_size": 4,
|
| 3332 |
"trial_name": null,
|
| 3333 |
"trial_params": null
|