Training in progress, step 2500, 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 sha256:5fb2bd4f7a80eb40d2530475250df49d51b1d8a3700a89614c1a2536866086a7
|
| 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:b9ec9783d423282cb76fb52866c8a208f9223b796eeeb00ddb08827afbec228e
|
| 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 sha256:9111dc5965b3afd3c9bf84e72d677f38968c6f9466692468cba75e25452a3307
|
| 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:e8aedc8c45f41bf64919c375727c80db9e0aeff0f8950601fa0a0a492e6b25a1
|
| 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,
|
|
@@ -2508,6 +2508,16 @@
|
|
| 2508 |
"mean_token_accuracy": 0.7662723585963249,
|
| 2509 |
"num_tokens": 11568739.0,
|
| 2510 |
"step": 2490
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2511 |
}
|
| 2512 |
],
|
| 2513 |
"logging_steps": 10,
|
|
@@ -2527,7 +2537,7 @@
|
|
| 2527 |
"attributes": {}
|
| 2528 |
}
|
| 2529 |
},
|
| 2530 |
-
"total_flos": 5.
|
| 2531 |
"train_batch_size": 4,
|
| 2532 |
"trial_name": null,
|
| 2533 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.5333333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2500,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2508 |
"mean_token_accuracy": 0.7662723585963249,
|
| 2509 |
"num_tokens": 11568739.0,
|
| 2510 |
"step": 2490
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"entropy": 0.9251207195222377,
|
| 2514 |
+
"epoch": 0.5333333333333333,
|
| 2515 |
+
"grad_norm": 0.23416800796985626,
|
| 2516 |
+
"learning_rate": 8.620153719937535e-05,
|
| 2517 |
+
"loss": 0.9998083114624023,
|
| 2518 |
+
"mean_token_accuracy": 0.7651191413402557,
|
| 2519 |
+
"num_tokens": 11616235.0,
|
| 2520 |
+
"step": 2500
|
| 2521 |
}
|
| 2522 |
],
|
| 2523 |
"logging_steps": 10,
|
|
|
|
| 2537 |
"attributes": {}
|
| 2538 |
}
|
| 2539 |
},
|
| 2540 |
+
"total_flos": 5.513579309009203e+16,
|
| 2541 |
"train_batch_size": 4,
|
| 2542 |
"trial_name": null,
|
| 2543 |
"trial_params": null
|