Training in progress, step 48, 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 119801528
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8797b11fba1c776461c64fac15227ef0fc26a31acbcdda387be97c0acb3e8ad
|
3 |
size 119801528
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 61392180
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eff3672abc803688ec5ba9ab44e8e2853724d32aae0a0ca4c8d389803b95f499
|
3 |
size 61392180
|
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:e6b350e124f8515e039f82ad9e125d1357ef6447ccdac17782950e7d733cdabe
|
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 sha256:2ced73b1ccbf53fea32ffc203f6798f09cca12df450e0857df5f8eeced13fd9b
|
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": 4,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -201,6 +201,28 @@
|
|
201 |
"eval_samples_per_second": 17.202,
|
202 |
"eval_steps_per_second": 2.549,
|
203 |
"step": 44
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
204 |
}
|
205 |
],
|
206 |
"logging_steps": 3,
|
@@ -215,12 +237,12 @@
|
|
215 |
"should_evaluate": false,
|
216 |
"should_log": false,
|
217 |
"should_save": true,
|
218 |
-
"should_training_stop":
|
219 |
},
|
220 |
"attributes": {}
|
221 |
}
|
222 |
},
|
223 |
-
"total_flos": 3.
|
224 |
"train_batch_size": 8,
|
225 |
"trial_name": null,
|
226 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0476190476190474,
|
5 |
"eval_steps": 4,
|
6 |
+
"global_step": 48,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
201 |
"eval_samples_per_second": 17.202,
|
202 |
"eval_steps_per_second": 2.549,
|
203 |
"step": 44
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 2.857142857142857,
|
207 |
+
"grad_norm": 1.786447286605835,
|
208 |
+
"learning_rate": 7.649933515167407e-07,
|
209 |
+
"loss": 2.4978,
|
210 |
+
"step": 45
|
211 |
+
},
|
212 |
+
{
|
213 |
+
"epoch": 3.0476190476190474,
|
214 |
+
"grad_norm": 1.427016019821167,
|
215 |
+
"learning_rate": 0.0,
|
216 |
+
"loss": 2.406,
|
217 |
+
"step": 48
|
218 |
+
},
|
219 |
+
{
|
220 |
+
"epoch": 3.0476190476190474,
|
221 |
+
"eval_loss": 2.2569899559020996,
|
222 |
+
"eval_runtime": 1.5743,
|
223 |
+
"eval_samples_per_second": 17.151,
|
224 |
+
"eval_steps_per_second": 2.541,
|
225 |
+
"step": 48
|
226 |
}
|
227 |
],
|
228 |
"logging_steps": 3,
|
|
|
237 |
"should_evaluate": false,
|
238 |
"should_log": false,
|
239 |
"should_save": true,
|
240 |
+
"should_training_stop": true
|
241 |
},
|
242 |
"attributes": {}
|
243 |
}
|
244 |
},
|
245 |
+
"total_flos": 3.4688261230166016e+16,
|
246 |
"train_batch_size": 8,
|
247 |
"trial_name": null,
|
248 |
"trial_params": null
|