Hugging Face's logo

mlfoundations-dev
/
evol_tt_1s

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
fddba74
·
verified ·
1 Parent(s): bb6fde7

Training in progress, epoch 1

Browse files
Files changed (5) hide show
  1. model-00001-of-00004.safetensors +1 -1
  2. model-00002-of-00004.safetensors +1 -1
  3. model-00003-of-00004.safetensors +1 -1
  4. model-00004-of-00004.safetensors +1 -1
  5. trainer_log.jsonl +4 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2d1f1b2461980003438c1fd22dfd69598963e7342198c0895f3296f9c5f7567
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a4fc851056ed32ddb74aff0b18c7565c4baa8ad27d490c7f8ae6f14be3c288b
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cbb8f18ac3eb0c3a1a5ba486c2ddca8f505f84d196b9f9fb7b5c3ea049eeaba9
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f04d7219ca34270fec402aa6578a16ee53688fd502c4ab6a0fa13bc050acbff1
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e64b400287587da9d44f8c8e6312f6793b90779957d60ca0cea75d6d416f20b8
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b7e6bad13973f3bac3674b0826f87fb25d8578aa5dd4004091b87a32a40decc
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:433e33d154eb39421b577ed3880b6fa04c3df799a94fd7ae157273bd9fc8c581
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d7b48178fdce6b7fad3228def2d215340199fbf040ca7e132f5cdc0c79ab348
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -2,3 +2,7 @@
2
  {"current_steps": 20, "total_steps": 87, "loss": 1.1372, "lr": 5e-06, "epoch": 0.6866952789699571, "percentage": 22.99, "elapsed_time": "0:19:25", "remaining_time": "1:05:05"}
3
  {"current_steps": 29, "total_steps": 87, "eval_loss": 1.0878669023513794, "epoch": 0.9957081545064378, "percentage": 33.33, "elapsed_time": "0:28:48", "remaining_time": "0:57:36"}
4
  {"current_steps": 30, "total_steps": 87, "loss": 1.1935, "lr": 5e-06, "epoch": 1.0300429184549356, "percentage": 34.48, "elapsed_time": "0:30:46", "remaining_time": "0:58:29"}
 
 
 
 
 
2
  {"current_steps": 20, "total_steps": 87, "loss": 1.1372, "lr": 5e-06, "epoch": 0.6866952789699571, "percentage": 22.99, "elapsed_time": "0:19:25", "remaining_time": "1:05:05"}
3
  {"current_steps": 29, "total_steps": 87, "eval_loss": 1.0878669023513794, "epoch": 0.9957081545064378, "percentage": 33.33, "elapsed_time": "0:28:48", "remaining_time": "0:57:36"}
4
  {"current_steps": 30, "total_steps": 87, "loss": 1.1935, "lr": 5e-06, "epoch": 1.0300429184549356, "percentage": 34.48, "elapsed_time": "0:30:46", "remaining_time": "0:58:29"}
5
+ {"current_steps": 40, "total_steps": 87, "loss": 1.0502, "lr": 5e-06, "epoch": 1.3733905579399142, "percentage": 45.98, "elapsed_time": "0:40:28", "remaining_time": "0:47:33"}
6
+ {"current_steps": 50, "total_steps": 87, "loss": 1.0329, "lr": 5e-06, "epoch": 1.7167381974248928, "percentage": 57.47, "elapsed_time": "0:50:09", "remaining_time": "0:37:06"}
7
+ {"current_steps": 58, "total_steps": 87, "eval_loss": 1.0472540855407715, "epoch": 1.9914163090128756, "percentage": 66.67, "elapsed_time": "0:58:40", "remaining_time": "0:29:20"}
8
+ {"current_steps": 60, "total_steps": 87, "loss": 1.0996, "lr": 5e-06, "epoch": 2.060085836909871, "percentage": 68.97, "elapsed_time": "1:01:34", "remaining_time": "0:27:42"}