Training in progress, step 270, 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 671149168
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9705f7ae34a9127883339815be4f2d08207c2af681ff054c6933e8b09a47858d
|
3 |
size 671149168
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5d9f59c570e4bd56548c981ef621e7a145fff5ee47529db6689edc4b5bf34e0
|
3 |
+
size 341314644
|
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 sha256:1fa940aa5ec0447264b2f42f46360367d5ca92d2fcd9b227cc7ebce57225d800
|
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:c9d09a80a2b21c682a84a5679c6174cd4f966b400b1091a2da7f8e60859bc411
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.009549448266625404,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-250",
|
4 |
-
"epoch":
|
5 |
"eval_steps": 50,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -230,6 +230,20 @@
|
|
230 |
"eval_samples_per_second": 11.694,
|
231 |
"eval_steps_per_second": 2.975,
|
232 |
"step": 250
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
233 |
}
|
234 |
],
|
235 |
"logging_steps": 10,
|
@@ -253,12 +267,12 @@
|
|
253 |
"should_evaluate": false,
|
254 |
"should_log": false,
|
255 |
"should_save": true,
|
256 |
-
"should_training_stop":
|
257 |
},
|
258 |
"attributes": {}
|
259 |
}
|
260 |
},
|
261 |
-
"total_flos":
|
262 |
"train_batch_size": 4,
|
263 |
"trial_name": null,
|
264 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.009549448266625404,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-250",
|
4 |
+
"epoch": 1.0018552875695732,
|
5 |
"eval_steps": 50,
|
6 |
+
"global_step": 270,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
230 |
"eval_samples_per_second": 11.694,
|
231 |
"eval_steps_per_second": 2.975,
|
232 |
"step": 250
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"epoch": 0.9647495361781077,
|
236 |
+
"grad_norm": 0.4870620369911194,
|
237 |
+
"learning_rate": 1.0534807653234672e-06,
|
238 |
+
"loss": 0.0192,
|
239 |
+
"step": 260
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 1.0018552875695732,
|
243 |
+
"grad_norm": 0.4801085591316223,
|
244 |
+
"learning_rate": 0.0,
|
245 |
+
"loss": 0.0222,
|
246 |
+
"step": 270
|
247 |
}
|
248 |
],
|
249 |
"logging_steps": 10,
|
|
|
267 |
"should_evaluate": false,
|
268 |
"should_log": false,
|
269 |
"should_save": true,
|
270 |
+
"should_training_stop": true
|
271 |
},
|
272 |
"attributes": {}
|
273 |
}
|
274 |
},
|
275 |
+
"total_flos": 7.38529128700969e+16,
|
276 |
"train_batch_size": 4,
|
277 |
"trial_name": null,
|
278 |
"trial_params": null
|