Training in progress, step 2420, 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 sha256:732c0620b6620ef6660996fb3e9ac9b3137a5be7d76d703d0da370eb307d81be
|
| 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:f1f5635ff69b136f998e3689dd52ca5c58e366dfb22327b9c502b824aa3c2873
|
| 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 sha256:087df49092c52e165c9723e1486ab1a345be983cc3e4358e5f1f7a951597f5da
|
| 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 sha256:40611b5bb16b881c328c8279653d601536ae911d7590faf37b8b15b51cf90f5e
|
| 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,
|
|
@@ -2428,6 +2428,16 @@
|
|
| 2428 |
"mean_token_accuracy": 0.7603042379021645,
|
| 2429 |
"num_tokens": 11211815.0,
|
| 2430 |
"step": 2410
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2431 |
}
|
| 2432 |
],
|
| 2433 |
"logging_steps": 10,
|
|
@@ -2447,7 +2457,7 @@
|
|
| 2447 |
"attributes": {}
|
| 2448 |
}
|
| 2449 |
},
|
| 2450 |
-
"total_flos": 5.
|
| 2451 |
"train_batch_size": 4,
|
| 2452 |
"trial_name": null,
|
| 2453 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.5162666666666667,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2420,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2428 |
"mean_token_accuracy": 0.7603042379021645,
|
| 2429 |
"num_tokens": 11211815.0,
|
| 2430 |
"step": 2410
|
| 2431 |
+
},
|
| 2432 |
+
{
|
| 2433 |
+
"entropy": 0.8673077188432217,
|
| 2434 |
+
"epoch": 0.5162666666666667,
|
| 2435 |
+
"grad_norm": 0.2602537274360657,
|
| 2436 |
+
"learning_rate": 8.714256876641087e-05,
|
| 2437 |
+
"loss": 0.9992271423339844,
|
| 2438 |
+
"mean_token_accuracy": 0.7819159016013145,
|
| 2439 |
+
"num_tokens": 11257215.0,
|
| 2440 |
+
"step": 2420
|
| 2441 |
}
|
| 2442 |
],
|
| 2443 |
"logging_steps": 10,
|
|
|
|
| 2457 |
"attributes": {}
|
| 2458 |
}
|
| 2459 |
},
|
| 2460 |
+
"total_flos": 5.338501230383923e+16,
|
| 2461 |
"train_batch_size": 4,
|
| 2462 |
"trial_name": null,
|
| 2463 |
"trial_params": null
|