Hugging Face's logo

mlfoundations-dev
/
oh_v3-1_only_glaive_code_assistant

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
esfrankel17 commited on
Commit
9bba250
·
verified ·
1 Parent(s): ec42cc9

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 +12 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d52f3daad590a6a35272bced54452a55c845d9738ff1956e0358ef6a91f6e57
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b347e7656cb3329f1dc5e252d10969d8d91dfd1b39d67fa706d556dfef2ea944
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:d944cb1319eab8ad672d1bb7b1f063017e27a6951b96665436a249334fac408d
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8441a81ae53f602927f7cc608cf5b60828ff51f0385a143c17f83e7ea3067376
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33d900c9defb21a50ef4db6947d5ff76181d72436a3952fc050c569cfd852b49
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:143536cdbd9e21bf79fd7363820d31539be7987f0cd3e89115bd517327646db8
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b0ff075fb8825ecbe8fe6264b875dbee5fc8072e312e4c2a7e2d11ca093c878
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c5808ddd16216fde11bb479bb5862fc7182bf6b4e6da37e968d6a28a23832e8
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -10,3 +10,15 @@
10
  {"current_steps": 100, "total_steps": 330, "loss": 0.594, "learning_rate": 5e-06, "epoch": 0.903954802259887, "percentage": 30.3, "elapsed_time": "0:51:30", "remaining_time": "1:58:28"}
11
  {"current_steps": 110, "total_steps": 330, "loss": 0.5971, "learning_rate": 5e-06, "epoch": 0.9943502824858758, "percentage": 33.33, "elapsed_time": "0:56:38", "remaining_time": "1:53:17"}
12
  {"current_steps": 110, "total_steps": 330, "eval_loss": 0.593043327331543, "epoch": 0.9943502824858758, "percentage": 33.33, "elapsed_time": "0:58:13", "remaining_time": "1:56:27"}
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  {"current_steps": 100, "total_steps": 330, "loss": 0.594, "learning_rate": 5e-06, "epoch": 0.903954802259887, "percentage": 30.3, "elapsed_time": "0:51:30", "remaining_time": "1:58:28"}
11
  {"current_steps": 110, "total_steps": 330, "loss": 0.5971, "learning_rate": 5e-06, "epoch": 0.9943502824858758, "percentage": 33.33, "elapsed_time": "0:56:38", "remaining_time": "1:53:17"}
12
  {"current_steps": 110, "total_steps": 330, "eval_loss": 0.593043327331543, "epoch": 0.9943502824858758, "percentage": 33.33, "elapsed_time": "0:58:13", "remaining_time": "1:56:27"}
13
+ {"current_steps": 120, "total_steps": 330, "loss": 0.5786, "learning_rate": 5e-06, "epoch": 1.0847457627118644, "percentage": 36.36, "elapsed_time": "1:04:15", "remaining_time": "1:52:26"}
14
+ {"current_steps": 130, "total_steps": 330, "loss": 0.5597, "learning_rate": 5e-06, "epoch": 1.1751412429378532, "percentage": 39.39, "elapsed_time": "1:09:22", "remaining_time": "1:46:44"}
15
+ {"current_steps": 140, "total_steps": 330, "loss": 0.556, "learning_rate": 5e-06, "epoch": 1.2655367231638417, "percentage": 42.42, "elapsed_time": "1:14:30", "remaining_time": "1:41:07"}
16
+ {"current_steps": 150, "total_steps": 330, "loss": 0.5637, "learning_rate": 5e-06, "epoch": 1.3559322033898304, "percentage": 45.45, "elapsed_time": "1:19:38", "remaining_time": "1:35:34"}
17
+ {"current_steps": 160, "total_steps": 330, "loss": 0.5552, "learning_rate": 5e-06, "epoch": 1.4463276836158192, "percentage": 48.48, "elapsed_time": "1:24:45", "remaining_time": "1:30:02"}
18
+ {"current_steps": 170, "total_steps": 330, "loss": 0.557, "learning_rate": 5e-06, "epoch": 1.536723163841808, "percentage": 51.52, "elapsed_time": "1:29:52", "remaining_time": "1:24:35"}
19
+ {"current_steps": 180, "total_steps": 330, "loss": 0.5561, "learning_rate": 5e-06, "epoch": 1.6271186440677967, "percentage": 54.55, "elapsed_time": "1:35:01", "remaining_time": "1:19:10"}
20
+ {"current_steps": 190, "total_steps": 330, "loss": 0.5583, "learning_rate": 5e-06, "epoch": 1.7175141242937855, "percentage": 57.58, "elapsed_time": "1:40:09", "remaining_time": "1:13:48"}
21
+ {"current_steps": 200, "total_steps": 330, "loss": 0.5572, "learning_rate": 5e-06, "epoch": 1.807909604519774, "percentage": 60.61, "elapsed_time": "1:45:19", "remaining_time": "1:08:27"}
22
+ {"current_steps": 210, "total_steps": 330, "loss": 0.5549, "learning_rate": 5e-06, "epoch": 1.8983050847457628, "percentage": 63.64, "elapsed_time": "1:50:29", "remaining_time": "1:03:08"}
23
+ {"current_steps": 220, "total_steps": 330, "loss": 0.5574, "learning_rate": 5e-06, "epoch": 1.9887005649717513, "percentage": 66.67, "elapsed_time": "1:55:38", "remaining_time": "0:57:49"}
24
+ {"current_steps": 221, "total_steps": 330, "eval_loss": 0.580794095993042, "epoch": 1.9977401129943502, "percentage": 66.97, "elapsed_time": "1:57:27", "remaining_time": "0:57:55"}