Training in progress, step 3100, 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 8137792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29c3e63c37a46335fe496807a96b638e34df01531ad06a9d033a92bb2b6114dc
|
| 3 |
size 8137792
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16386426
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:581543136e90329a56f15bebdbb06eb038e189f68098df554de9fa01eafc031b
|
| 3 |
size 16386426
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15006
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f65be2b2cdf376107318ecd5cf6f00a331abea7e87187632ce7ced767025e11
|
| 3 |
size 15006
|
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 sha256:651a79a3a0db621d243879bf98062166313dbd06aa2c69308c07f63ea2919d42
|
| 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":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -265,6 +265,13 @@
|
|
| 265 |
"eval_samples_per_second": 19.904,
|
| 266 |
"eval_steps_per_second": 2.489,
|
| 267 |
"step": 3000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 268 |
}
|
| 269 |
],
|
| 270 |
"logging_steps": 100,
|
|
@@ -284,7 +291,7 @@
|
|
| 284 |
"attributes": {}
|
| 285 |
}
|
| 286 |
},
|
| 287 |
-
"total_flos": 4.
|
| 288 |
"train_batch_size": 8,
|
| 289 |
"trial_name": null,
|
| 290 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.19903140134354,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 3100,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 265 |
"eval_samples_per_second": 19.904,
|
| 266 |
"eval_steps_per_second": 2.489,
|
| 267 |
"step": 3000
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 6.19903140134354,
|
| 271 |
+
"grad_norm": 0.1689419448375702,
|
| 272 |
+
"learning_rate": 7.933333333333334e-05,
|
| 273 |
+
"loss": 1.2739,
|
| 274 |
+
"step": 3100
|
| 275 |
}
|
| 276 |
],
|
| 277 |
"logging_steps": 100,
|
|
|
|
| 291 |
"attributes": {}
|
| 292 |
}
|
| 293 |
},
|
| 294 |
+
"total_flos": 4.838269165611516e+18,
|
| 295 |
"train_batch_size": 8,
|
| 296 |
"trial_name": null,
|
| 297 |
"trial_params": null
|