Training in progress, step 4600, 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 250422888
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1167462a1140ec7ca60ec445b82d4f5c4cb233b860d0b32ce4f7f9f8c856d3d6
|
3 |
size 250422888
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 127492797
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7014aec77ff4b43b381a086a86109461df29f30d8f4fc67270ace3176132763
|
3 |
size 127492797
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12dd8844032d3c501d84e3c3a845474f98a7bc04f5d31907f21670b057dc207c
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:793c554376f8e7f2de92b146fd20e985a7a5b03ad4002c60e108f3677dee0ff3
|
3 |
size 627
|
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": 200,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -293,13 +293,26 @@
|
|
293 |
"eval_samples_per_second": 7.923,
|
294 |
"eval_steps_per_second": 0.517,
|
295 |
"step": 4400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
296 |
}
|
297 |
],
|
298 |
"logging_steps": 200,
|
299 |
"max_steps": 4920,
|
300 |
"num_train_epochs": 15,
|
301 |
"save_steps": 200,
|
302 |
-
"total_flos": 1.
|
303 |
"trial_name": null,
|
304 |
"trial_params": null
|
305 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 14.024390243902438,
|
5 |
"eval_steps": 200,
|
6 |
+
"global_step": 4600,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
293 |
"eval_samples_per_second": 7.923,
|
294 |
"eval_steps_per_second": 0.517,
|
295 |
"step": 4400
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"epoch": 14.02,
|
299 |
+
"learning_rate": 0.0002,
|
300 |
+
"loss": 0.0286,
|
301 |
+
"step": 4600
|
302 |
+
},
|
303 |
+
{
|
304 |
+
"epoch": 14.02,
|
305 |
+
"eval_runtime": 34.8156,
|
306 |
+
"eval_samples_per_second": 7.927,
|
307 |
+
"eval_steps_per_second": 0.517,
|
308 |
+
"step": 4600
|
309 |
}
|
310 |
],
|
311 |
"logging_steps": 200,
|
312 |
"max_steps": 4920,
|
313 |
"num_train_epochs": 15,
|
314 |
"save_steps": 200,
|
315 |
+
"total_flos": 1.4816796692447232e+18,
|
316 |
"trial_name": null,
|
317 |
"trial_params": null
|
318 |
}
|