Training in progress, step 87, 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 319876032
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e52643d7157f114660b6525b688616d8c10e2ea82d4b4d13691403a68a37c041
|
3 |
size 319876032
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 640009682
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6a73c72a73c3334d4f9833d3678ab644b30b28f010c471dd0699e868fb78fb2
|
3 |
size 640009682
|
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:d2d3140cfd5ff38cfbf3050180a18592da0802ab8e303fc19c6368d1c426a1d0
|
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 sha256:677f84d029e79278b29fc723536495e22e1eaf0d2461735dd4bca627866b6546
|
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 +277,27 @@
|
|
277 |
"eval_samples_per_second": 4.7,
|
278 |
"eval_steps_per_second": 2.35,
|
279 |
"step": 80
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
280 |
}
|
281 |
],
|
282 |
"logging_steps": 3,
|
@@ -291,12 +312,12 @@
|
|
291 |
"should_evaluate": false,
|
292 |
"should_log": false,
|
293 |
"should_save": true,
|
294 |
-
"should_training_stop":
|
295 |
},
|
296 |
"attributes": {}
|
297 |
}
|
298 |
},
|
299 |
-
"total_flos": 4.
|
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": 3.022702702702703,
|
5 |
"eval_steps": 8,
|
6 |
+
"global_step": 87,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
277 |
"eval_samples_per_second": 4.7,
|
278 |
"eval_steps_per_second": 2.35,
|
279 |
"step": 80
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 2.810810810810811,
|
283 |
+
"grad_norm": 12.35340690612793,
|
284 |
+
"learning_rate": 2.9486109317369944e-06,
|
285 |
+
"loss": 3.0625,
|
286 |
+
"step": 81
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 2.9145945945945946,
|
290 |
+
"grad_norm": 10.495280265808105,
|
291 |
+
"learning_rate": 7.408114099011792e-07,
|
292 |
+
"loss": 2.8662,
|
293 |
+
"step": 84
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 3.022702702702703,
|
297 |
+
"grad_norm": 10.368959426879883,
|
298 |
+
"learning_rate": 0.0,
|
299 |
+
"loss": 3.0789,
|
300 |
+
"step": 87
|
301 |
}
|
302 |
],
|
303 |
"logging_steps": 3,
|
|
|
312 |
"should_evaluate": false,
|
313 |
"should_log": false,
|
314 |
"should_save": true,
|
315 |
+
"should_training_stop": true
|
316 |
},
|
317 |
"attributes": {}
|
318 |
}
|
319 |
},
|
320 |
+
"total_flos": 4.57542115497345e+17,
|
321 |
"train_batch_size": 2,
|
322 |
"trial_name": null,
|
323 |
"trial_params": null
|