Training in progress, step 8550, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aff52beab5cf51589980b8237d70152c6cd71b73940823a59ffe97f61f5753d9
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc8da40d963f22eebf055312de8107052e7f07650ec9dc1f512770ff03ba83df
|
| 3 |
size 14709
|
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 sha256:9b98ac163cb6934836fd0d31b9e9df4a19ebf733e5d2f06b2827a952bb19b7ee
|
| 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": 65.
|
| 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,
|
|
@@ -15380,6 +15380,24 @@
|
|
| 15380 |
"mean_token_accuracy": 0.6444296389818192,
|
| 15381 |
"num_tokens": 31146338.0,
|
| 15382 |
"step": 8540
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15383 |
}
|
| 15384 |
],
|
| 15385 |
"logging_steps": 5,
|
|
@@ -15399,7 +15417,7 @@
|
|
| 15399 |
"attributes": {}
|
| 15400 |
}
|
| 15401 |
},
|
| 15402 |
-
"total_flos": 1.
|
| 15403 |
"train_batch_size": 4,
|
| 15404 |
"trial_name": null,
|
| 15405 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 65.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8550,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15380 |
"mean_token_accuracy": 0.6444296389818192,
|
| 15381 |
"num_tokens": 31146338.0,
|
| 15382 |
"step": 8540
|
| 15383 |
+
},
|
| 15384 |
+
{
|
| 15385 |
+
"epoch": 65.73076923076923,
|
| 15386 |
+
"grad_norm": 0.0,
|
| 15387 |
+
"learning_rate": 7.280000000000001e-06,
|
| 15388 |
+
"loss": 1.7123,
|
| 15389 |
+
"mean_token_accuracy": 0.6542566984891891,
|
| 15390 |
+
"num_tokens": 31165043.0,
|
| 15391 |
+
"step": 8545
|
| 15392 |
+
},
|
| 15393 |
+
{
|
| 15394 |
+
"epoch": 65.76923076923077,
|
| 15395 |
+
"grad_norm": 0.0,
|
| 15396 |
+
"learning_rate": 7.255000000000001e-06,
|
| 15397 |
+
"loss": 1.7491,
|
| 15398 |
+
"mean_token_accuracy": 0.6535750329494476,
|
| 15399 |
+
"num_tokens": 31183433.0,
|
| 15400 |
+
"step": 8550
|
| 15401 |
}
|
| 15402 |
],
|
| 15403 |
"logging_steps": 5,
|
|
|
|
| 15417 |
"attributes": {}
|
| 15418 |
}
|
| 15419 |
},
|
| 15420 |
+
"total_flos": 1.581188155266171e+18,
|
| 15421 |
"train_batch_size": 4,
|
| 15422 |
"trial_name": null,
|
| 15423 |
"trial_params": null
|