Training in progress, step 2620, 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 sha256:8133e2015cc56948b9761fbdfd917992da7e0fc2e1320d9ed355fc54c23b859c
|
| 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:aee4b082c3832e1b4f69a01f86d8036c55da343a18260555dd90a97e60801603
|
| 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 sha256:6f5f95305552e4558b500000efeca45539ede1dbbe744eba1e310db9dfd3a111
|
| 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 sha256:223a0822a7379318784d6ef512bffecaedfbab19aee90fd0d3897ee3ffa956f6
|
| 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,
|
|
@@ -2628,6 +2628,16 @@
|
|
| 2628 |
"mean_token_accuracy": 0.7750694006681442,
|
| 2629 |
"num_tokens": 12125503.0,
|
| 2630 |
"step": 2610
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2631 |
}
|
| 2632 |
],
|
| 2633 |
"logging_steps": 10,
|
|
@@ -2647,7 +2657,7 @@
|
|
| 2647 |
"attributes": {}
|
| 2648 |
}
|
| 2649 |
},
|
| 2650 |
-
"total_flos": 5.
|
| 2651 |
"train_batch_size": 4,
|
| 2652 |
"trial_name": null,
|
| 2653 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.5589333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2620,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2628 |
"mean_token_accuracy": 0.7750694006681442,
|
| 2629 |
"num_tokens": 12125503.0,
|
| 2630 |
"step": 2610
|
| 2631 |
+
},
|
| 2632 |
+
{
|
| 2633 |
+
"entropy": 0.9893216907978057,
|
| 2634 |
+
"epoch": 0.5589333333333333,
|
| 2635 |
+
"grad_norm": 0.2604218125343323,
|
| 2636 |
+
"learning_rate": 8.47381746991739e-05,
|
| 2637 |
+
"loss": 1.040914249420166,
|
| 2638 |
+
"mean_token_accuracy": 0.7624668940901757,
|
| 2639 |
+
"num_tokens": 12177100.0,
|
| 2640 |
+
"step": 2620
|
| 2641 |
}
|
| 2642 |
],
|
| 2643 |
"logging_steps": 10,
|
|
|
|
| 2657 |
"attributes": {}
|
| 2658 |
}
|
| 2659 |
},
|
| 2660 |
+
"total_flos": 5.77057617504983e+16,
|
| 2661 |
"train_batch_size": 4,
|
| 2662 |
"trial_name": null,
|
| 2663 |
"trial_params": null
|