Commit
•
1f152b3
1
Parent(s):
05d3d05
Training in progress, step 7200, 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 167832240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44d89401fbca2f40400fdb6834e3a677208e11f52a19bc9be25c0057ea983475
|
3 |
size 167832240
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 84581014
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:beb9c6d2d11b4f177cc3790b2f12ad1c1f9399706b529d0ac545ef06d5c76f4d
|
3 |
size 84581014
|
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 sha256:4e5ea69d1327aa2a2f41dcf01d7f65a4507c296565311e90ac8dee9f26a318d8
|
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 sha256:90eed9268b685a4adc40e6fe34acc82bd73b63bdc872d5161958be86a1c224ff
|
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": 2000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -252,6 +252,13 @@
|
|
252 |
"learning_rate": 1.9999946677254565e-05,
|
253 |
"loss": 1.5163,
|
254 |
"step": 7000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
255 |
}
|
256 |
],
|
257 |
"logging_steps": 200,
|
@@ -259,7 +266,7 @@
|
|
259 |
"num_input_tokens_seen": 0,
|
260 |
"num_train_epochs": 5,
|
261 |
"save_steps": 200,
|
262 |
-
"total_flos": 9.
|
263 |
"train_batch_size": 1,
|
264 |
"trial_name": null,
|
265 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.005354374040209862,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 7200,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
252 |
"learning_rate": 1.9999946677254565e-05,
|
253 |
"loss": 1.5163,
|
254 |
"step": 7000
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.01,
|
258 |
+
"grad_norm": 3.813724994659424,
|
259 |
+
"learning_rate": 1.999994358178185e-05,
|
260 |
+
"loss": 1.5569,
|
261 |
+
"step": 7200
|
262 |
}
|
263 |
],
|
264 |
"logging_steps": 200,
|
|
|
266 |
"num_input_tokens_seen": 0,
|
267 |
"num_train_epochs": 5,
|
268 |
"save_steps": 200,
|
269 |
+
"total_flos": 9.451356004088218e+16,
|
270 |
"train_batch_size": 1,
|
271 |
"trial_name": null,
|
272 |
"trial_params": null
|