Training in progress, step 5680, 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 sha256:342934d55e3b05aa81e9dc41c070fb64b84c3f8fc42ef7dcce552fed42457663
|
| 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:a2223b0771c029d7bb75c2da86dcea7ccf1f2e5b0ba8dc8ca174c1b88b09fa7d
|
| 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 sha256:040218c6a5d5e8590c1b6801457d7767285c4d0412314c429a781f9d61793a10
|
| 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": 43.
|
| 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,
|
|
@@ -10214,6 +10214,24 @@
|
|
| 10214 |
"mean_token_accuracy": 0.6582222819328308,
|
| 10215 |
"num_tokens": 20681100.0,
|
| 10216 |
"step": 5670
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10217 |
}
|
| 10218 |
],
|
| 10219 |
"logging_steps": 5,
|
|
@@ -10233,7 +10251,7 @@
|
|
| 10233 |
"attributes": {}
|
| 10234 |
}
|
| 10235 |
},
|
| 10236 |
-
"total_flos": 1.
|
| 10237 |
"train_batch_size": 4,
|
| 10238 |
"trial_name": null,
|
| 10239 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 43.69230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5680,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10214 |
"mean_token_accuracy": 0.6582222819328308,
|
| 10215 |
"num_tokens": 20681100.0,
|
| 10216 |
"step": 5670
|
| 10217 |
+
},
|
| 10218 |
+
{
|
| 10219 |
+
"epoch": 43.65384615384615,
|
| 10220 |
+
"grad_norm": 0.0,
|
| 10221 |
+
"learning_rate": 2.163e-05,
|
| 10222 |
+
"loss": 1.7536,
|
| 10223 |
+
"mean_token_accuracy": 0.6478887408971786,
|
| 10224 |
+
"num_tokens": 20699280.0,
|
| 10225 |
+
"step": 5675
|
| 10226 |
+
},
|
| 10227 |
+
{
|
| 10228 |
+
"epoch": 43.69230769230769,
|
| 10229 |
+
"grad_norm": 0.0,
|
| 10230 |
+
"learning_rate": 2.1605e-05,
|
| 10231 |
+
"loss": 1.7702,
|
| 10232 |
+
"mean_token_accuracy": 0.6438897788524628,
|
| 10233 |
+
"num_tokens": 20717346.0,
|
| 10234 |
+
"step": 5680
|
| 10235 |
}
|
| 10236 |
],
|
| 10237 |
"logging_steps": 5,
|
|
|
|
| 10251 |
"attributes": {}
|
| 10252 |
}
|
| 10253 |
},
|
| 10254 |
+
"total_flos": 1.0499258342788301e+18,
|
| 10255 |
"train_batch_size": 4,
|
| 10256 |
"trial_name": null,
|
| 10257 |
"trial_params": null
|