Training in progress, step 550, 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:d1373aa907f406c2a9a059e9f7dd6d8ab313a44593760eb21bec5f66cfa79290
|
| 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:e87965615be6532f700b360379291c73709ed2b89bdb73d3a0e9e4d2436a88cd
|
| 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 sha256:47d46faea8b6ef817b5f8a4954749e3f9a7577ad87f750461ef35ca0eef05e24
|
| 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 sha256:3175a1c494fdb1ecab89a31951e6cddf6494463267320da3674109b13ee3461d
|
| 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,
|
|
@@ -558,6 +558,16 @@
|
|
| 558 |
"mean_token_accuracy": 0.7413557574152947,
|
| 559 |
"num_tokens": 2490595.0,
|
| 560 |
"step": 540
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 561 |
}
|
| 562 |
],
|
| 563 |
"logging_steps": 10,
|
|
@@ -577,7 +587,7 @@
|
|
| 577 |
"attributes": {}
|
| 578 |
}
|
| 579 |
},
|
| 580 |
-
"total_flos": 1.
|
| 581 |
"train_batch_size": 4,
|
| 582 |
"trial_name": null,
|
| 583 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.11733333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 550,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 558 |
"mean_token_accuracy": 0.7413557574152947,
|
| 559 |
"num_tokens": 2490595.0,
|
| 560 |
"step": 540
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"entropy": 0.863083366304636,
|
| 564 |
+
"epoch": 0.11733333333333333,
|
| 565 |
+
"grad_norm": 0.2839767634868622,
|
| 566 |
+
"learning_rate": 9.98143988744349e-05,
|
| 567 |
+
"loss": 0.9366037368774414,
|
| 568 |
+
"mean_token_accuracy": 0.786571592092514,
|
| 569 |
+
"num_tokens": 2537415.0,
|
| 570 |
+
"step": 550
|
| 571 |
}
|
| 572 |
],
|
| 573 |
"logging_steps": 10,
|
|
|
|
| 587 |
"attributes": {}
|
| 588 |
}
|
| 589 |
},
|
| 590 |
+
"total_flos": 1.2078760782849024e+16,
|
| 591 |
"train_batch_size": 4,
|
| 592 |
"trial_name": null,
|
| 593 |
"trial_params": null
|