Training in progress, step 2370, 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 sha256:0a1e5e6d00eec84e86b3b134a3d2a61035fe74d0079fd2f477a0029039585ae7
|
| 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:a376cbdca5fa0e9995180c984e796f6092c2d85ac532eb60c26d6c7bcbb1b54e
|
| 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 sha256:93e6370d871fd46e9e3e3656a7bf30e20bc64a060a0cc81c8447bff418d2dff2
|
| 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": 18.
|
| 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,
|
|
@@ -4256,6 +4256,24 @@
|
|
| 4256 |
"mean_token_accuracy": 0.6549855172634125,
|
| 4257 |
"num_tokens": 8606513.0,
|
| 4258 |
"step": 2360
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4259 |
}
|
| 4260 |
],
|
| 4261 |
"logging_steps": 5,
|
|
@@ -4275,7 +4293,7 @@
|
|
| 4275 |
"attributes": {}
|
| 4276 |
}
|
| 4277 |
},
|
| 4278 |
-
"total_flos": 4.
|
| 4279 |
"train_batch_size": 4,
|
| 4280 |
"trial_name": null,
|
| 4281 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 18.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2370,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4256 |
"mean_token_accuracy": 0.6549855172634125,
|
| 4257 |
"num_tokens": 8606513.0,
|
| 4258 |
"step": 2360
|
| 4259 |
+
},
|
| 4260 |
+
{
|
| 4261 |
+
"epoch": 18.192307692307693,
|
| 4262 |
+
"grad_norm": 0.0,
|
| 4263 |
+
"learning_rate": 3.818e-05,
|
| 4264 |
+
"loss": 1.7534,
|
| 4265 |
+
"mean_token_accuracy": 0.6542291522026062,
|
| 4266 |
+
"num_tokens": 8624369.0,
|
| 4267 |
+
"step": 2365
|
| 4268 |
+
},
|
| 4269 |
+
{
|
| 4270 |
+
"epoch": 18.23076923076923,
|
| 4271 |
+
"grad_norm": 0.0,
|
| 4272 |
+
"learning_rate": 3.8155e-05,
|
| 4273 |
+
"loss": 1.696,
|
| 4274 |
+
"mean_token_accuracy": 0.6589814841747283,
|
| 4275 |
+
"num_tokens": 8643122.0,
|
| 4276 |
+
"step": 2370
|
| 4277 |
}
|
| 4278 |
],
|
| 4279 |
"logging_steps": 5,
|
|
|
|
| 4293 |
"attributes": {}
|
| 4294 |
}
|
| 4295 |
},
|
| 4296 |
+
"total_flos": 4.3797020460171264e+17,
|
| 4297 |
"train_batch_size": 4,
|
| 4298 |
"trial_name": null,
|
| 4299 |
"trial_params": null
|