Training in progress, step 2440, 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 sha256:877256650b7a8ab456adddb51d08278cfbe43d4db2b3dc77bca7fcf30ed2fe4f
|
| 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 sha256:2c127466db4d213449c52bd6d68d5c64c89d6aa0c5b042d1daae6e98efaeb8b2
|
| 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:f0102bd114592cc21c21be0343e5e62d496f463a23a272dadff75312ffae918b
|
| 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:fb41a100db46242c18f39a26a42d3d0396b78dd79e428ab8473d72afa767aec9
|
| 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,
|
|
@@ -2448,6 +2448,16 @@
|
|
| 2448 |
"mean_token_accuracy": 0.7529917880892754,
|
| 2449 |
"num_tokens": 11302807.0,
|
| 2450 |
"step": 2430
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2451 |
}
|
| 2452 |
],
|
| 2453 |
"logging_steps": 10,
|
|
@@ -2467,7 +2477,7 @@
|
|
| 2467 |
"attributes": {}
|
| 2468 |
}
|
| 2469 |
},
|
| 2470 |
-
"total_flos": 5.
|
| 2471 |
"train_batch_size": 4,
|
| 2472 |
"trial_name": null,
|
| 2473 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.5205333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2440,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2448 |
"mean_token_accuracy": 0.7529917880892754,
|
| 2449 |
"num_tokens": 11302807.0,
|
| 2450 |
"step": 2430
|
| 2451 |
+
},
|
| 2452 |
+
{
|
| 2453 |
+
"entropy": 1.0103901624679565,
|
| 2454 |
+
"epoch": 0.5205333333333333,
|
| 2455 |
+
"grad_norm": 0.3081832230091095,
|
| 2456 |
+
"learning_rate": 8.690995302697081e-05,
|
| 2457 |
+
"loss": 1.1663932800292969,
|
| 2458 |
+
"mean_token_accuracy": 0.7516932919621467,
|
| 2459 |
+
"num_tokens": 11350668.0,
|
| 2460 |
+
"step": 2440
|
| 2461 |
}
|
| 2462 |
],
|
| 2463 |
"logging_steps": 10,
|
|
|
|
| 2477 |
"attributes": {}
|
| 2478 |
}
|
| 2479 |
},
|
| 2480 |
+
"total_flos": 5.38359391765801e+16,
|
| 2481 |
"train_batch_size": 4,
|
| 2482 |
"trial_name": null,
|
| 2483 |
"trial_params": null
|