Training in progress, step 4240, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:264163bedd6cf50c2c1a056a70e215214987823273fbde7150fffdc53a4606a8
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da8fa5349dd48cf5c502759d5411954f18f916ddbd7b47736b986d8327475b10
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c56e55da639eadd520ca7d7bcdb6a8ccfd87bdc26812839a3bd2a73e41b88a23
|
| 3 |
size 14645
|
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:a2d3806b12b198a8bf57aa549906940d46b230459777d6bd8b9ee4b17f71b4a8
|
| 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": 0.
|
| 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,
|
|
@@ -4248,6 +4248,16 @@
|
|
| 4248 |
"mean_token_accuracy": 0.7552115090191365,
|
| 4249 |
"num_tokens": 19697922.0,
|
| 4250 |
"step": 4230
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4251 |
}
|
| 4252 |
],
|
| 4253 |
"logging_steps": 10,
|
|
@@ -4267,7 +4277,7 @@
|
|
| 4267 |
"attributes": {}
|
| 4268 |
}
|
| 4269 |
},
|
| 4270 |
-
"total_flos": 9.
|
| 4271 |
"train_batch_size": 4,
|
| 4272 |
"trial_name": null,
|
| 4273 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.9045333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4240,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4248 |
"mean_token_accuracy": 0.7552115090191365,
|
| 4249 |
"num_tokens": 19697922.0,
|
| 4250 |
"step": 4230
|
| 4251 |
+
},
|
| 4252 |
+
{
|
| 4253 |
+
"entropy": 0.8659336932003499,
|
| 4254 |
+
"epoch": 0.9045333333333333,
|
| 4255 |
+
"grad_norm": 0.33948129415512085,
|
| 4256 |
+
"learning_rate": 6.029285945529699e-05,
|
| 4257 |
+
"loss": 0.9698437690734864,
|
| 4258 |
+
"mean_token_accuracy": 0.7807855561375618,
|
| 4259 |
+
"num_tokens": 19742041.0,
|
| 4260 |
+
"step": 4240
|
| 4261 |
}
|
| 4262 |
],
|
| 4263 |
"logging_steps": 10,
|
|
|
|
| 4277 |
"attributes": {}
|
| 4278 |
}
|
| 4279 |
},
|
| 4280 |
+
"total_flos": 9.342916062918451e+16,
|
| 4281 |
"train_batch_size": 4,
|
| 4282 |
"trial_name": null,
|
| 4283 |
"trial_params": null
|