Hugging Face's logo

mlfoundations-dev
/
stackoverflow_25000tasks_.25p

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
0ec13a8
•
1 Parent(s): 28b7751

Training in progress, epoch 2

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:c436287614ea7344f6925269eee6d9eb0de00dfb3c74882b9035990cc286f0b6
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1004c4b77b4357e38431ed8384917afcb12176beaaba3c637391a9ba34ebc61f
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51d5c63ce358b6f047cfac90cbe6a7f27e6d35e3d6e5b94892622c0b70a9f354
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:405bf97b3a07577918595f1d8a125b6c893ce44d4625c8e74308bc764beaef03
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:b2d07ddc81c5d74d0d07252d1fec54b4408be78a06eaeb4df6820b19de2c00af
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac98d46a96d1c4e02c5b9af019663a8d574918878f5b7a8df03bf1b5d83c55d5
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8aa9bdeade6c4d5de38afc8e4c8a53c35f43a9c599c62dd585f9aefc1bf968c6
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:657df44d7c1eaf030e08512a6603fb4abfe38e7a632e1ae2af4c636ead63a13e
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -7,3 +7,7 @@
7
  {"current_steps": 60, "total_steps": 99, "loss": 0.5827, "lr": 5e-06, "epoch": 1.7910447761194028, "percentage": 60.61, "elapsed_time": "0:33:29", "remaining_time": "0:21:45"}
8
  {"current_steps": 67, "total_steps": 99, "eval_loss": 0.6018304228782654, "epoch": 2.0, "percentage": 67.68, "elapsed_time": "0:37:31", "remaining_time": "0:17:55"}
9
  {"current_steps": 70, "total_steps": 99, "loss": 0.5874, "lr": 5e-06, "epoch": 2.08955223880597, "percentage": 70.71, "elapsed_time": "0:40:22", "remaining_time": "0:16:43"}
 
 
 
 
 
7
  {"current_steps": 60, "total_steps": 99, "loss": 0.5827, "lr": 5e-06, "epoch": 1.7910447761194028, "percentage": 60.61, "elapsed_time": "0:33:29", "remaining_time": "0:21:45"}
8
  {"current_steps": 67, "total_steps": 99, "eval_loss": 0.6018304228782654, "epoch": 2.0, "percentage": 67.68, "elapsed_time": "0:37:31", "remaining_time": "0:17:55"}
9
  {"current_steps": 70, "total_steps": 99, "loss": 0.5874, "lr": 5e-06, "epoch": 2.08955223880597, "percentage": 70.71, "elapsed_time": "0:40:22", "remaining_time": "0:16:43"}
10
+ {"current_steps": 80, "total_steps": 99, "loss": 0.5198, "lr": 5e-06, "epoch": 2.388059701492537, "percentage": 80.81, "elapsed_time": "0:45:38", "remaining_time": "0:10:50"}
11
+ {"current_steps": 90, "total_steps": 99, "loss": 0.5126, "lr": 5e-06, "epoch": 2.6865671641791042, "percentage": 90.91, "elapsed_time": "0:50:54", "remaining_time": "0:05:05"}
12
+ {"current_steps": 99, "total_steps": 99, "eval_loss": 0.5868151187896729, "epoch": 2.955223880597015, "percentage": 100.0, "elapsed_time": "0:57:20", "remaining_time": "0:00:00"}
13
+ {"current_steps": 99, "total_steps": 99, "epoch": 2.955223880597015, "percentage": 100.0, "elapsed_time": "0:58:35", "remaining_time": "0:00:00"}