Hugging Face's logo

mlfoundations-dev
/
oh_v3-1_only_airoboros

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
esfrankel17 commited on
Commit
0b82567
•
1 Parent(s): 8ec2ca9

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 +2 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9006e6684d0e04c5c4dc9af7998a1272b7e41ed004275ae0ac0c602f8edeedea
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:064843fdd202f923a17d6b23dfdd83bf1704b4dc40476dd0d973421c42ea4af6
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:d8a517368f97f910053e7b46f10786e0c812e64df7e8e2be417e1c64a6746f8d
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05e9af8806620d65be64b2c9555838a129c7b0310fcf44bedf667dd258c43fb2
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:bc45d33fb3ae9d248cbe1e814a00962a7ae9e3c5bbaac9da669547a4c859d573
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35bbf4a8a2627505f83d512bbeb6a96732e3e80aea4764c0e9a24df35cbc620e
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:925f95910a51b7fa512e2746c1d4b58cad6c8f13138c743f6d303fdc8239be41
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5593fa10ba8c2eaf4349e7420e4995d40981fc3177768c1e886ba8a4a2369e72
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,3 +1,5 @@
1
  {"current_steps": 10, "total_steps": 48, "loss": 0.8943, "learning_rate": 5e-06, "epoch": 0.625, "percentage": 20.83, "elapsed_time": "0:05:23", "remaining_time": "0:20:28"}
2
  {"current_steps": 16, "total_steps": 48, "eval_loss": 0.8237837553024292, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:08:43", "remaining_time": "0:17:27"}
3
  {"current_steps": 20, "total_steps": 48, "loss": 0.7853, "learning_rate": 5e-06, "epoch": 1.25, "percentage": 41.67, "elapsed_time": "0:11:47", "remaining_time": "0:16:30"}
 
 
 
1
  {"current_steps": 10, "total_steps": 48, "loss": 0.8943, "learning_rate": 5e-06, "epoch": 0.625, "percentage": 20.83, "elapsed_time": "0:05:23", "remaining_time": "0:20:28"}
2
  {"current_steps": 16, "total_steps": 48, "eval_loss": 0.8237837553024292, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:08:43", "remaining_time": "0:17:27"}
3
  {"current_steps": 20, "total_steps": 48, "loss": 0.7853, "learning_rate": 5e-06, "epoch": 1.25, "percentage": 41.67, "elapsed_time": "0:11:47", "remaining_time": "0:16:30"}
4
+ {"current_steps": 30, "total_steps": 48, "loss": 0.7293, "learning_rate": 5e-06, "epoch": 1.875, "percentage": 62.5, "elapsed_time": "0:17:07", "remaining_time": "0:10:16"}
5
+ {"current_steps": 32, "total_steps": 48, "eval_loss": 0.7811707258224487, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:18:22", "remaining_time": "0:09:11"}