Training in progress, step 3370, 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 sha256:63c3e5029ec4a167d3350051ef28b939629b3402a6ce7f9a9e1c4eea0879d95b
|
| 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 sha256:373613a25695c88fe3cb4b250a4f9e7fb494929dd7d80e3f73264d4e7fae0faf
|
| 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:c74bcc50eb158440098b1e17f6fa55f4b0330eb4234f1b9bf64394cf1eedeb9a
|
| 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 sha256:86e26c54275a3300408539c0bbac992fd488296f481832e199e21de56872c083
|
| 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,
|
|
@@ -3378,6 +3378,16 @@
|
|
| 3378 |
"mean_token_accuracy": 0.7655998513102531,
|
| 3379 |
"num_tokens": 15652544.0,
|
| 3380 |
"step": 3360
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3381 |
}
|
| 3382 |
],
|
| 3383 |
"logging_steps": 10,
|
|
@@ -3397,7 +3407,7 @@
|
|
| 3397 |
"attributes": {}
|
| 3398 |
}
|
| 3399 |
},
|
| 3400 |
-
"total_flos": 7.
|
| 3401 |
"train_batch_size": 4,
|
| 3402 |
"trial_name": null,
|
| 3403 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7189333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3370,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3378 |
"mean_token_accuracy": 0.7655998513102531,
|
| 3379 |
"num_tokens": 15652544.0,
|
| 3380 |
"step": 3360
|
| 3381 |
+
},
|
| 3382 |
+
{
|
| 3383 |
+
"entropy": 0.8534669198095799,
|
| 3384 |
+
"epoch": 0.7189333333333333,
|
| 3385 |
+
"grad_norm": 0.20464476943016052,
|
| 3386 |
+
"learning_rate": 7.434267462852496e-05,
|
| 3387 |
+
"loss": 0.9573710441589356,
|
| 3388 |
+
"mean_token_accuracy": 0.7839296951889991,
|
| 3389 |
+
"num_tokens": 15691801.0,
|
| 3390 |
+
"step": 3370
|
| 3391 |
}
|
| 3392 |
],
|
| 3393 |
"logging_steps": 10,
|
|
|
|
| 3407 |
"attributes": {}
|
| 3408 |
}
|
| 3409 |
},
|
| 3410 |
+
"total_flos": 7.432897359605146e+16,
|
| 3411 |
"train_batch_size": 4,
|
| 3412 |
"trial_name": null,
|
| 3413 |
"trial_params": null
|