Hugging Face's logo

mlfoundations-dev
/
stackoverflow_25000tasks_.5p

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
4d52995
·
verified ·
1 Parent(s): 0994446

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 +5 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7220b0dd55b55641e4f10f6e45f269d6417f765a3fce5f7a8eaf903428a9e7bf
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31cbeaced4db6417ec4c3e9aa8073320c7b06e3b4f9280e8e2e4631c4aae31ca
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:18b9f983a59336078def85f399c3058dfbed1ee1838faa3e9faa5d54c1ff850d
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9f26491751efab177b230eeb9d914219072386eb8208ac88b21521aa0d2deba
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:fdfc24dda9f26a5d9647241c04f05657431284abff90b25eb9c9475595cc654b
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e6a02f41f4bb3ac8b3f1f3ddd5d4a689b9dc82556a403ea7e1643c669674f10
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89a4063778cf3965565485bd16316063c5935532097121aa32a5320a5e1adfef
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1a80f43c137a079b0ae7b0c05ac92a44aa70e185a54dbe7c23da762291dbdfc
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -2,3 +2,8 @@
2
  {"current_steps": 20, "total_steps": 102, "loss": 0.7583, "lr": 5e-06, "epoch": 0.5860805860805861, "percentage": 19.61, "elapsed_time": "0:10:43", "remaining_time": "0:43:58"}
3
  {"current_steps": 30, "total_steps": 102, "loss": 0.7171, "lr": 5e-06, "epoch": 0.8791208791208791, "percentage": 29.41, "elapsed_time": "0:16:01", "remaining_time": "0:38:27"}
4
  {"current_steps": 34, "total_steps": 102, "eval_loss": 0.6949356198310852, "epoch": 0.9963369963369964, "percentage": 33.33, "elapsed_time": "0:18:35", "remaining_time": "0:37:10"}
 
 
 
 
 
 
2
  {"current_steps": 20, "total_steps": 102, "loss": 0.7583, "lr": 5e-06, "epoch": 0.5860805860805861, "percentage": 19.61, "elapsed_time": "0:10:43", "remaining_time": "0:43:58"}
3
  {"current_steps": 30, "total_steps": 102, "loss": 0.7171, "lr": 5e-06, "epoch": 0.8791208791208791, "percentage": 29.41, "elapsed_time": "0:16:01", "remaining_time": "0:38:27"}
4
  {"current_steps": 34, "total_steps": 102, "eval_loss": 0.6949356198310852, "epoch": 0.9963369963369964, "percentage": 33.33, "elapsed_time": "0:18:35", "remaining_time": "0:37:10"}
5
+ {"current_steps": 40, "total_steps": 102, "loss": 0.7449, "lr": 5e-06, "epoch": 1.1721611721611722, "percentage": 39.22, "elapsed_time": "0:22:53", "remaining_time": "0:35:28"}
6
+ {"current_steps": 50, "total_steps": 102, "loss": 0.6554, "lr": 5e-06, "epoch": 1.4652014652014653, "percentage": 49.02, "elapsed_time": "0:28:11", "remaining_time": "0:29:19"}
7
+ {"current_steps": 60, "total_steps": 102, "loss": 0.6415, "lr": 5e-06, "epoch": 1.7582417582417582, "percentage": 58.82, "elapsed_time": "0:33:31", "remaining_time": "0:23:28"}
8
+ {"current_steps": 68, "total_steps": 102, "eval_loss": 0.6563424468040466, "epoch": 1.9926739926739927, "percentage": 66.67, "elapsed_time": "0:38:18", "remaining_time": "0:19:09"}
9
+ {"current_steps": 70, "total_steps": 102, "loss": 0.6776, "lr": 5e-06, "epoch": 2.051282051282051, "percentage": 68.63, "elapsed_time": "0:40:31", "remaining_time": "0:18:31"}