Training in progress, step 9600, 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 sha256:541f75b74a748691867242b8e155bc4be5c8df948e0c8ad57f20b953e293f7e0
|
| 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 sha256:6097951337f4fe069ccba7a86ed10877d52874a7d27aeeec87f74c2b828458d4
|
| 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:db8bb1e4185e67a5f220dd92e294f8e358d68e5311aa37b473368dfc3dc960fd
|
| 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": 73.
|
| 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,
|
|
@@ -17270,6 +17270,24 @@
|
|
| 17270 |
"mean_token_accuracy": 0.6624141722917557,
|
| 17271 |
"num_tokens": 34973992.0,
|
| 17272 |
"step": 9590
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17273 |
}
|
| 17274 |
],
|
| 17275 |
"logging_steps": 5,
|
|
@@ -17289,7 +17307,7 @@
|
|
| 17289 |
"attributes": {}
|
| 17290 |
}
|
| 17291 |
},
|
| 17292 |
-
"total_flos": 1.
|
| 17293 |
"train_batch_size": 4,
|
| 17294 |
"trial_name": null,
|
| 17295 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 73.84615384615384,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9600,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17270 |
"mean_token_accuracy": 0.6624141722917557,
|
| 17271 |
"num_tokens": 34973992.0,
|
| 17272 |
"step": 9590
|
| 17273 |
+
},
|
| 17274 |
+
{
|
| 17275 |
+
"epoch": 73.8076923076923,
|
| 17276 |
+
"grad_norm": 0.0,
|
| 17277 |
+
"learning_rate": 2.03e-06,
|
| 17278 |
+
"loss": 1.7145,
|
| 17279 |
+
"mean_token_accuracy": 0.6552868157625198,
|
| 17280 |
+
"num_tokens": 34992491.0,
|
| 17281 |
+
"step": 9595
|
| 17282 |
+
},
|
| 17283 |
+
{
|
| 17284 |
+
"epoch": 73.84615384615384,
|
| 17285 |
+
"grad_norm": 0.0,
|
| 17286 |
+
"learning_rate": 2.005e-06,
|
| 17287 |
+
"loss": 1.763,
|
| 17288 |
+
"mean_token_accuracy": 0.6461809724569321,
|
| 17289 |
+
"num_tokens": 35010375.0,
|
| 17290 |
+
"step": 9600
|
| 17291 |
}
|
| 17292 |
],
|
| 17293 |
"logging_steps": 5,
|
|
|
|
| 17307 |
"attributes": {}
|
| 17308 |
}
|
| 17309 |
},
|
| 17310 |
+
"total_flos": 1.7754579338320282e+18,
|
| 17311 |
"train_batch_size": 4,
|
| 17312 |
"trial_name": null,
|
| 17313 |
"trial_params": null
|