Hugging Face's logo

mlfoundations-dev
/
oh_v1-2_only_unnatural_instructions

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
ca07b4d
•
1 Parent(s): 980b9a2

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 sha256:5ad4a27a3ffc5fe88551541cf51996db6f5586b1c1990383ebee054a58b8caae
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e278196f77030c08b2661e1c034390d9552eb2dba015afc75d196c33567ae578
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:a4a53cf2ae934ae760cd5961a1c03e919231a1e9c78557038ec3d96302d92775
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ca236b305303f8b77165a2618b2c966db07eddc00b64a6165e872c8567b5c2c
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:da9580890aa9630f8344a68f381165664cbdff91e7066c1d7c0defb9d04658da
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79a0551f5a95039859ccc7bfb5e8fc5ae85320375813c8ed168dd8880d7633f4
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f9d38b61f6abffdf10d32aa874319562c76e9edc572183dc72deaf33dbc86df
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b6ca3c4456a66d154ef8b30da09706bda04c0998dd597a947d45f37d480d91e
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,3 +1,5 @@
1
  {"current_steps": 6, "total_steps": 18, "eval_loss": 0.8220317959785461, "epoch": 0.9056603773584906, "percentage": 33.33, "elapsed_time": "0:03:24", "remaining_time": "0:06:48"}
2
  {"current_steps": 10, "total_steps": 18, "loss": 1.0972, "learning_rate": 5e-06, "epoch": 1.5660377358490565, "percentage": 55.56, "elapsed_time": "0:06:27", "remaining_time": "0:05:09"}
3
  {"current_steps": 12, "total_steps": 18, "eval_loss": 0.6778215765953064, "epoch": 1.8679245283018868, "percentage": 66.67, "elapsed_time": "0:07:48", "remaining_time": "0:03:54"}
 
 
 
1
  {"current_steps": 6, "total_steps": 18, "eval_loss": 0.8220317959785461, "epoch": 0.9056603773584906, "percentage": 33.33, "elapsed_time": "0:03:24", "remaining_time": "0:06:48"}
2
  {"current_steps": 10, "total_steps": 18, "loss": 1.0972, "learning_rate": 5e-06, "epoch": 1.5660377358490565, "percentage": 55.56, "elapsed_time": "0:06:27", "remaining_time": "0:05:09"}
3
  {"current_steps": 12, "total_steps": 18, "eval_loss": 0.6778215765953064, "epoch": 1.8679245283018868, "percentage": 66.67, "elapsed_time": "0:07:48", "remaining_time": "0:03:54"}
4
+ {"current_steps": 18, "total_steps": 18, "eval_loss": 0.6227314472198486, "epoch": 2.830188679245283, "percentage": 100.0, "elapsed_time": "0:12:35", "remaining_time": "0:00:00"}
5
+ {"current_steps": 18, "total_steps": 18, "epoch": 2.830188679245283, "percentage": 100.0, "elapsed_time": "0:13:28", "remaining_time": "0:00:00"}