Training in progress, step 2530, 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:bb88d925858e94344d7f87fe677e32165eb8e3252e76d7f0da0e73d8b1d32ce3
|
| 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:b45818ae8407cc67d7bfd50a7787c613a72f2379e40affdd12142c829450fc81
|
| 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:a34422028f7ff9fe4ff4ee216ad704753af7fb1e625c31db00d387461d736940
|
| 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 sha256:3f957b3cff70835bb9ada1b9a20d676302da81eb94bd5937f10ed4e15a62423e
|
| 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,
|
|
@@ -2538,6 +2538,16 @@
|
|
| 2538 |
"mean_token_accuracy": 0.7509198278188706,
|
| 2539 |
"num_tokens": 11710341.0,
|
| 2540 |
"step": 2520
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2541 |
}
|
| 2542 |
],
|
| 2543 |
"logging_steps": 10,
|
|
@@ -2557,7 +2567,7 @@
|
|
| 2557 |
"attributes": {}
|
| 2558 |
}
|
| 2559 |
},
|
| 2560 |
-
"total_flos": 5.
|
| 2561 |
"train_batch_size": 4,
|
| 2562 |
"trial_name": null,
|
| 2563 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.5397333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2530,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2538 |
"mean_token_accuracy": 0.7509198278188706,
|
| 2539 |
"num_tokens": 11710341.0,
|
| 2540 |
"step": 2520
|
| 2541 |
+
},
|
| 2542 |
+
{
|
| 2543 |
+
"entropy": 0.8292181946337223,
|
| 2544 |
+
"epoch": 0.5397333333333333,
|
| 2545 |
+
"grad_norm": 0.2717600166797638,
|
| 2546 |
+
"learning_rate": 8.58414545323611e-05,
|
| 2547 |
+
"loss": 0.9124368667602539,
|
| 2548 |
+
"mean_token_accuracy": 0.789941257238388,
|
| 2549 |
+
"num_tokens": 11753282.0,
|
| 2550 |
+
"step": 2530
|
| 2551 |
}
|
| 2552 |
],
|
| 2553 |
"logging_steps": 10,
|
|
|
|
| 2567 |
"attributes": {}
|
| 2568 |
}
|
| 2569 |
},
|
| 2570 |
+
"total_flos": 5.576751607213056e+16,
|
| 2571 |
"train_batch_size": 4,
|
| 2572 |
"trial_name": null,
|
| 2573 |
"trial_params": null
|