Training in progress, step 20, 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 63592
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:499771e88547b22802709960f69a875a4f624bcd729ecd56ef9b0ba30cafe1a3
|
3 |
size 63592
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 132798
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0472fbdf9f8c9f7c1d16a8a393dcc92c03c7f39914cc8ad49d7207f5d03fe09f
|
3 |
size 132798
|
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:c41518eb99b623bce607db707194b2f2e941b0b6cbb96b7c5e477827474964db
|
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 sha256:532138a5ca880d8da393ae449e5715b2766def36b8838785ca08d07228b119b7
|
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": 2,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -213,6 +213,28 @@
|
|
213 |
"eval_samples_per_second": 108.174,
|
214 |
"eval_steps_per_second": 54.091,
|
215 |
"step": 18
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
216 |
}
|
217 |
],
|
218 |
"logging_steps": 1,
|
@@ -227,12 +249,12 @@
|
|
227 |
"should_evaluate": false,
|
228 |
"should_log": false,
|
229 |
"should_save": true,
|
230 |
-
"should_training_stop":
|
231 |
},
|
232 |
"attributes": {}
|
233 |
}
|
234 |
},
|
235 |
-
"total_flos":
|
236 |
"train_batch_size": 2,
|
237 |
"trial_name": null,
|
238 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0006815122757398668,
|
5 |
"eval_steps": 2,
|
6 |
+
"global_step": 20,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
213 |
"eval_samples_per_second": 108.174,
|
214 |
"eval_steps_per_second": 54.091,
|
215 |
"step": 18
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 0.0006474366619528734,
|
219 |
+
"grad_norm": 2.549006938934326,
|
220 |
+
"learning_rate": 2.4471741852423237e-06,
|
221 |
+
"loss": 44.2642,
|
222 |
+
"step": 19
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"epoch": 0.0006815122757398668,
|
226 |
+
"grad_norm": 2.272350549697876,
|
227 |
+
"learning_rate": 0.0,
|
228 |
+
"loss": 44.2192,
|
229 |
+
"step": 20
|
230 |
+
},
|
231 |
+
{
|
232 |
+
"epoch": 0.0006815122757398668,
|
233 |
+
"eval_loss": 11.079532623291016,
|
234 |
+
"eval_runtime": 114.2157,
|
235 |
+
"eval_samples_per_second": 108.19,
|
236 |
+
"eval_steps_per_second": 54.099,
|
237 |
+
"step": 20
|
238 |
}
|
239 |
],
|
240 |
"logging_steps": 1,
|
|
|
249 |
"should_evaluate": false,
|
250 |
"should_log": false,
|
251 |
"should_save": true,
|
252 |
+
"should_training_stop": true
|
253 |
},
|
254 |
"attributes": {}
|
255 |
}
|
256 |
},
|
257 |
+
"total_flos": 55215390720.0,
|
258 |
"train_batch_size": 2,
|
259 |
"trial_name": null,
|
260 |
"trial_params": null
|