Hugging Face's logo

mlfoundations-dev
/
oh_v1-2_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
c3e85f2
•
1 Parent(s): d57f18e

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 sha256:30aa85b4e6388dacd03671cd73cc9ddc9162a8cecbbf1eb84af20f93681c789d
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e72e3ec6d227dca3105bd89f997651174137fdda81d13b8972f5c625cf32ea93
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:298447e6fee102e3781875b6bde3bd72edde1ac742b2bf7708ceb99615113a1e
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23dd78540e7b27073ff1dfe271d4f2241926f0020f720caf75a7ca1d54fd2b0e
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2582c5286b0bf204914ea3bda35849a1bbd65f7586f54201a5fa63889e593173
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d602b4dfc503bf2aa3753099aec4754620e21bcf6dd862e073a2cdd41b3d57f
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1373843a8bea78560ee3de776bb4c1d267447d07c189d6ac4892c7e8c67aabfc
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b759152114108d18b408ce32caf481c06f929af58e209597bbbf33b76887a9fc
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,3 +1,5 @@
1
  {"current_steps": 5, "total_steps": 15, "eval_loss": 0.948443591594696, "epoch": 0.9248554913294798, "percentage": 33.33, "elapsed_time": "0:24:42", "remaining_time": "0:49:25"}
2
  {"current_steps": 10, "total_steps": 15, "loss": 0.9953, "learning_rate": 5e-06, "epoch": 1.8497109826589595, "percentage": 66.67, "elapsed_time": "0:46:39", "remaining_time": "0:23:19"}
3
  {"current_steps": 10, "total_steps": 15, "eval_loss": 0.8798985481262207, "epoch": 1.8497109826589595, "percentage": 66.67, "elapsed_time": "0:50:36", "remaining_time": "0:25:18"}
 
 
 
1
  {"current_steps": 5, "total_steps": 15, "eval_loss": 0.948443591594696, "epoch": 0.9248554913294798, "percentage": 33.33, "elapsed_time": "0:24:42", "remaining_time": "0:49:25"}
2
  {"current_steps": 10, "total_steps": 15, "loss": 0.9953, "learning_rate": 5e-06, "epoch": 1.8497109826589595, "percentage": 66.67, "elapsed_time": "0:46:39", "remaining_time": "0:23:19"}
3
  {"current_steps": 10, "total_steps": 15, "eval_loss": 0.8798985481262207, "epoch": 1.8497109826589595, "percentage": 66.67, "elapsed_time": "0:50:36", "remaining_time": "0:25:18"}
4
+ {"current_steps": 15, "total_steps": 15, "eval_loss": 0.8367447257041931, "epoch": 2.7745664739884393, "percentage": 100.0, "elapsed_time": "1:12:20", "remaining_time": "0:00:00"}
5
+ {"current_steps": 15, "total_steps": 15, "epoch": 2.7745664739884393, "percentage": 100.0, "elapsed_time": "1:13:11", "remaining_time": "0:00:00"}