Hugging Face's logo

mlfoundations-dev
/
llama3-1_8b_mlfoundations-dev-stackoverflow_25000tasks__5p

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
EtashGuha commited on
Commit
8a31104
·
verified ·
1 Parent(s): 111de6a

Training in progress, epoch 2

Browse files
Files changed (6) 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 +6 -8
  6. training_args.bin +2 -2
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:554244aec94ede1891c5897e8d55405ef0f2b242dcdd03f8a07024370aded9b5
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:804e363529e21bdaf1f7469db91c0fa9a1da7fb05400023d116072d9bf2c4324
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89b60273e59ccbbde7feee830b59d8f891e32439b261f4448b6ff13b0a9d3a8c
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5950f979d31bba204382183973fef4d01f6d748a2c749800f450d0ae0cfc07eb
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7750bc12cd1cceccc1a830075e2fe088f4c73614d11b60a76cf28833be552823
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2237b53060776270c01ad983a7825623a57773279c42ea3c83ed3bc16eaf82be
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e238d204f725fb028400a531a16690e989becb5c29fff3f4821303047fbc5d4
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:861870c54645f7427a6feb633a6050efb447083d8033f3557e46e8506928092c
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,8 +1,6 @@
1
- {"current_steps": 10, "total_steps": 102, "loss": 0.8622, "lr": 5e-06, "epoch": 0.29357798165137616, "percentage": 9.8, "elapsed_time": "0:26:38", "remaining_time": "4:05:06"}
2
- {"current_steps": 20, "total_steps": 102, "loss": 0.7615, "lr": 5e-06, "epoch": 0.5871559633027523, "percentage": 19.61, "elapsed_time": "0:53:06", "remaining_time": "3:37:45"}
3
- {"current_steps": 30, "total_steps": 102, "loss": 0.7229, "lr": 5e-06, "epoch": 0.8807339449541285, "percentage": 29.41, "elapsed_time": "1:19:24", "remaining_time": "3:10:34"}
4
- {"current_steps": 34, "total_steps": 102, "eval_loss": 0.6932151913642883, "epoch": 0.998165137614679, "percentage": 33.33, "elapsed_time": "1:31:54", "remaining_time": "3:03:49"}
5
- {"current_steps": 40, "total_steps": 102, "loss": 0.684, "lr": 5e-06, "epoch": 1.1743119266055047, "percentage": 39.22, "elapsed_time": "1:48:54", "remaining_time": "2:48:47"}
6
- {"current_steps": 50, "total_steps": 102, "loss": 0.6549, "lr": 5e-06, "epoch": 1.4678899082568808, "percentage": 49.02, "elapsed_time": "2:15:00", "remaining_time": "2:20:24"}
7
- {"current_steps": 60, "total_steps": 102, "loss": 0.6412, "lr": 5e-06, "epoch": 1.761467889908257, "percentage": 58.82, "elapsed_time": "2:41:06", "remaining_time": "1:52:46"}
8
- {"current_steps": 68, "total_steps": 102, "eval_loss": 0.6560695171356201, "epoch": 1.996330275229358, "percentage": 66.67, "elapsed_time": "3:04:05", "remaining_time": "1:32:02"}
 
1
+ {"current_steps": 70, "total_steps": 102, "loss": 0.5857, "lr": 5e-06, "epoch": 2.0587155963302752, "percentage": 68.63, "elapsed_time": "0:05:21", "remaining_time": "0:02:26"}
2
+ {"current_steps": 80, "total_steps": 102, "loss": 0.5754, "lr": 5e-06, "epoch": 2.3522935779816514, "percentage": 78.43, "elapsed_time": "0:31:29", "remaining_time": "0:08:39"}
3
+ {"current_steps": 90, "total_steps": 102, "loss": 0.5682, "lr": 5e-06, "epoch": 2.6458715596330276, "percentage": 88.24, "elapsed_time": "0:57:37", "remaining_time": "0:07:41"}
4
+ {"current_steps": 100, "total_steps": 102, "loss": 0.5675, "lr": 5e-06, "epoch": 2.9394495412844037, "percentage": 98.04, "elapsed_time": "1:23:47", "remaining_time": "0:01:40"}
5
+ {"current_steps": 102, "total_steps": 102, "eval_loss": 0.6488585472106934, "epoch": 2.998165137614679, "percentage": 100.0, "elapsed_time": "1:32:28", "remaining_time": "0:00:00"}
6
+ {"current_steps": 102, "total_steps": 102, "epoch": 2.998165137614679, "percentage": 100.0, "elapsed_time": "1:33:25", "remaining_time": "0:00:00"}
 
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a34674721ecfcc2f44c115367ce714e9869079705d21c70d681f0c20c4bb1144
3
- size 7288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f123e6ad90565d18e6479e4fdb911ad1ba5f8292e2d098b95a8395e4513a8a29
3
+ size 7480