Training in progress, step 86, 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 97728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1a9c52ed13da5612a14112158920cca2f09b9a89974273eb5e0bb27768cd11a
|
3 |
size 97728
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 212298
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9682ca5fb57b1689756727eac9a7184e622c893fdee97446f578996d94aefd55
|
3 |
size 212298
|
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:a062223c58d6bce32f13c4933c306b16cc26ff4708e733ebc3ca0df52404bb19
|
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 sha256:12f81afce521056555d6c5a2a40e41e87a722cdb1ae567ea49429c16d514f88b
|
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": 8,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -277,6 +277,20 @@
|
|
277 |
"eval_samples_per_second": 134.151,
|
278 |
"eval_steps_per_second": 67.767,
|
279 |
"step": 80
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
280 |
}
|
281 |
],
|
282 |
"logging_steps": 3,
|
@@ -291,12 +305,12 @@
|
|
291 |
"should_evaluate": false,
|
292 |
"should_log": false,
|
293 |
"should_save": true,
|
294 |
-
"should_training_stop":
|
295 |
},
|
296 |
"attributes": {}
|
297 |
}
|
298 |
},
|
299 |
-
"total_flos":
|
300 |
"train_batch_size": 2,
|
301 |
"trial_name": null,
|
302 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.060175054704595,
|
5 |
"eval_steps": 8,
|
6 |
+
"global_step": 86,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
277 |
"eval_samples_per_second": 134.151,
|
278 |
"eval_steps_per_second": 67.767,
|
279 |
"step": 80
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 2.8687089715536107,
|
283 |
+
"grad_norm": 0.08289742469787598,
|
284 |
+
"learning_rate": 2.818843167645835e-06,
|
285 |
+
"loss": 10.2928,
|
286 |
+
"step": 81
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 2.973741794310722,
|
290 |
+
"grad_norm": 0.08898758143186569,
|
291 |
+
"learning_rate": 4.5280774269154115e-07,
|
292 |
+
"loss": 10.5421,
|
293 |
+
"step": 84
|
294 |
}
|
295 |
],
|
296 |
"logging_steps": 3,
|
|
|
305 |
"should_evaluate": false,
|
306 |
"should_log": false,
|
307 |
"should_save": true,
|
308 |
+
"should_training_stop": true
|
309 |
},
|
310 |
"attributes": {}
|
311 |
}
|
312 |
},
|
313 |
+
"total_flos": 36914181439488.0,
|
314 |
"train_batch_size": 2,
|
315 |
"trial_name": null,
|
316 |
"trial_params": null
|