Training in progress, step 9590, 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 sha256:4f30379653ae6a625ca63d25202e05aa35be3af62d47a4a047fee625e3203fa7
|
| 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 sha256:62e3833087632582b5453ae4b2f2ce425eaa3c3af290f9a19c6eacc08b43c534
|
| 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 sha256:7ad3cb3a2e8cb522c9e2e2ed8d40e9484fb261fb36dde6166a01a0424c5e1c1b
|
| 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,
|
|
@@ -17252,6 +17252,24 @@
|
|
| 17252 |
"mean_token_accuracy": 0.6391745179891586,
|
| 17253 |
"num_tokens": 34936386.0,
|
| 17254 |
"step": 9580
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17255 |
}
|
| 17256 |
],
|
| 17257 |
"logging_steps": 5,
|
|
@@ -17271,7 +17289,7 @@
|
|
| 17271 |
"attributes": {}
|
| 17272 |
}
|
| 17273 |
},
|
| 17274 |
-
"total_flos": 1.
|
| 17275 |
"train_batch_size": 4,
|
| 17276 |
"trial_name": null,
|
| 17277 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 73.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9590,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17252 |
"mean_token_accuracy": 0.6391745179891586,
|
| 17253 |
"num_tokens": 34936386.0,
|
| 17254 |
"step": 9580
|
| 17255 |
+
},
|
| 17256 |
+
{
|
| 17257 |
+
"epoch": 73.73076923076923,
|
| 17258 |
+
"grad_norm": 0.0,
|
| 17259 |
+
"learning_rate": 2.08e-06,
|
| 17260 |
+
"loss": 1.729,
|
| 17261 |
+
"mean_token_accuracy": 0.6509798347949982,
|
| 17262 |
+
"num_tokens": 34954716.0,
|
| 17263 |
+
"step": 9585
|
| 17264 |
+
},
|
| 17265 |
+
{
|
| 17266 |
+
"epoch": 73.76923076923077,
|
| 17267 |
+
"grad_norm": 0.0,
|
| 17268 |
+
"learning_rate": 2.055e-06,
|
| 17269 |
+
"loss": 1.6906,
|
| 17270 |
+
"mean_token_accuracy": 0.6624141722917557,
|
| 17271 |
+
"num_tokens": 34973992.0,
|
| 17272 |
+
"step": 9590
|
| 17273 |
}
|
| 17274 |
],
|
| 17275 |
"logging_steps": 5,
|
|
|
|
| 17289 |
"attributes": {}
|
| 17290 |
}
|
| 17291 |
},
|
| 17292 |
+
"total_flos": 1.7735843399063962e+18,
|
| 17293 |
"train_batch_size": 4,
|
| 17294 |
"trial_name": null,
|
| 17295 |
"trial_params": null
|