Training in progress, step 4250, 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 sha256:0c4e11c1a46f9f109cb7ba38e56ab82215c2b48355ee32883a96bffeeba80b3a
|
| 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 sha256:88190cfb1563f790352d127bd91a0a8c464222e483c32ff4500e5750d29298e6
|
| 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 sha256:4b68fd0029e7b261e63271307deb9f4836f5f68bdb71f73d7c4d4addbb5ece23
|
| 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 sha256:893524f66429fdbfbd92fa63a34c02cb9fec44170efb9ec59a0ac5b90c37545c
|
| 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,
|
|
@@ -4258,6 +4258,16 @@
|
|
| 4258 |
"mean_token_accuracy": 0.7807855561375618,
|
| 4259 |
"num_tokens": 19742041.0,
|
| 4260 |
"step": 4240
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4261 |
}
|
| 4262 |
],
|
| 4263 |
"logging_steps": 10,
|
|
@@ -4277,7 +4287,7 @@
|
|
| 4277 |
"attributes": {}
|
| 4278 |
}
|
| 4279 |
},
|
| 4280 |
-
"total_flos": 9.
|
| 4281 |
"train_batch_size": 4,
|
| 4282 |
"trial_name": null,
|
| 4283 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.9066666666666666,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4250,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4258 |
"mean_token_accuracy": 0.7807855561375618,
|
| 4259 |
"num_tokens": 19742041.0,
|
| 4260 |
"step": 4240
|
| 4261 |
+
},
|
| 4262 |
+
{
|
| 4263 |
+
"entropy": 0.9663250721991062,
|
| 4264 |
+
"epoch": 0.9066666666666666,
|
| 4265 |
+
"grad_norm": 0.2511708438396454,
|
| 4266 |
+
"learning_rate": 6.012343353484271e-05,
|
| 4267 |
+
"loss": 1.0937541007995606,
|
| 4268 |
+
"mean_token_accuracy": 0.7600424617528916,
|
| 4269 |
+
"num_tokens": 19789800.0,
|
| 4270 |
+
"step": 4250
|
| 4271 |
}
|
| 4272 |
],
|
| 4273 |
"logging_steps": 10,
|
|
|
|
| 4287 |
"attributes": {}
|
| 4288 |
}
|
| 4289 |
},
|
| 4290 |
+
"total_flos": 9.365159157174682e+16,
|
| 4291 |
"train_batch_size": 4,
|
| 4292 |
"trial_name": null,
|
| 4293 |
"trial_params": null
|