Training in progress, step 39, 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 73911112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc83c1975c88628e75d88aeff663229b3fbf8d943db400ac9d72cdcf2bb25a14
|
3 |
size 73911112
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 37430836
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:806760f9dc53a51525f42428757487044f6c0c32b297800c006f40dda5152cd8
|
3 |
size 37430836
|
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 sha256:92b44dea3ad58c35a851c6c3b01ef1e891935a61fd8de378737c8e03c1674ab0
|
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": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -273,6 +273,13 @@
|
|
273 |
"learning_rate": 7.6e-05,
|
274 |
"loss": 1.3434,
|
275 |
"step": 38
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
276 |
}
|
277 |
],
|
278 |
"logging_steps": 1,
|
@@ -292,7 +299,7 @@
|
|
292 |
"attributes": {}
|
293 |
}
|
294 |
},
|
295 |
-
"total_flos": 4.
|
296 |
"train_batch_size": 4,
|
297 |
"trial_name": null,
|
298 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.10699588477366255,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 39,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
273 |
"learning_rate": 7.6e-05,
|
274 |
"loss": 1.3434,
|
275 |
"step": 38
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.10699588477366255,
|
279 |
+
"grad_norm": 0.16371050477027893,
|
280 |
+
"learning_rate": 7.800000000000001e-05,
|
281 |
+
"loss": 1.4134,
|
282 |
+
"step": 39
|
283 |
}
|
284 |
],
|
285 |
"logging_steps": 1,
|
|
|
299 |
"attributes": {}
|
300 |
}
|
301 |
},
|
302 |
+
"total_flos": 4.819057491549389e+16,
|
303 |
"train_batch_size": 4,
|
304 |
"trial_name": null,
|
305 |
"trial_params": null
|