Training in progress, step 99, 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 1279641042
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a54c22f7979a7e29404c8001f24a0a2613650b3b8e6075655254ee2c5200856
|
| 3 |
size 1279641042
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83eafbac03a7476b4d49b130d5ab2826387f76bc6958b712aec2504a5656c396
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1eef4c60eef56c59d148e4191bea64e9a3bf517b29f5a413c536dcdc8e61edf1
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 9,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -221,6 +221,21 @@
|
|
| 221 |
"eval_samples_per_second": 10.39,
|
| 222 |
"eval_steps_per_second": 1.299,
|
| 223 |
"step": 90
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 224 |
}
|
| 225 |
],
|
| 226 |
"logging_steps": 5,
|
|
@@ -240,7 +255,7 @@
|
|
| 240 |
"attributes": {}
|
| 241 |
}
|
| 242 |
},
|
| 243 |
-
"total_flos": 2.
|
| 244 |
"train_batch_size": 8,
|
| 245 |
"trial_name": null,
|
| 246 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.03173076923076923,
|
| 5 |
"eval_steps": 9,
|
| 6 |
+
"global_step": 99,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 221 |
"eval_samples_per_second": 10.39,
|
| 222 |
"eval_steps_per_second": 1.299,
|
| 223 |
"step": 90
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 0.030448717948717948,
|
| 227 |
+
"grad_norm": NaN,
|
| 228 |
+
"learning_rate": 1.4411039697577175e-06,
|
| 229 |
+
"loss": 0.0,
|
| 230 |
+
"step": 95
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.03173076923076923,
|
| 234 |
+
"eval_loss": NaN,
|
| 235 |
+
"eval_runtime": 1067.8009,
|
| 236 |
+
"eval_samples_per_second": 10.389,
|
| 237 |
+
"eval_steps_per_second": 1.299,
|
| 238 |
+
"step": 99
|
| 239 |
}
|
| 240 |
],
|
| 241 |
"logging_steps": 5,
|
|
|
|
| 255 |
"attributes": {}
|
| 256 |
}
|
| 257 |
},
|
| 258 |
+
"total_flos": 2.634381633037271e+17,
|
| 259 |
"train_batch_size": 8,
|
| 260 |
"trial_name": null,
|
| 261 |
"trial_params": null
|