Hugging Face's logo

mlfoundations-dev
/
stackoverflow_25000tasks_1p

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
53631bb
·
verified ·
1 Parent(s): 3818671

Training in progress, epoch 3

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 sha256:9ef8be544c5d80c32f98ef58511791955817d4f50b33d4c1515f3406eb09a276
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7024b009e8683d680218157d3bb020902cdd7e9d243eb9eea55c2cd8d362d881
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:dcef32c0aed8b5282ea9aabf6cc121db83c46a53a0e8be12e701b6cb1dd7f392
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94ee4efe48208eba1bc0df29db9af9d2f048eaea9c6a664e2da6e57623bbe540
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37d49827660d7ec5f43815d8ea52b3c6e28ef97f2bd99c8e824663cc91a9019a
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee6372c021e80ba099d42c03d410e80ce16e26dd902701cfb2f403564a723bd2
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21a632c80027233d4ebbb4e1112f441db424d57fcb46699d6d8ddf6c480071d7
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db59e757977f1ddd2b1eaec8f7f63efdf8a3883e5c7134d7a826abad0089e9bc
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -7,3 +7,8 @@
7
  {"current_steps": 60, "total_steps": 105, "loss": 0.7716, "lr": 5e-06, "epoch": 1.7142857142857144, "percentage": 57.14, "elapsed_time": "0:33:48", "remaining_time": "0:25:21"}
8
  {"current_steps": 70, "total_steps": 105, "loss": 0.7678, "lr": 5e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:39:09", "remaining_time": "0:19:34"}
9
  {"current_steps": 70, "total_steps": 105, "eval_loss": 0.7982695698738098, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:39:34", "remaining_time": "0:19:47"}
 
 
 
 
 
 
7
  {"current_steps": 60, "total_steps": 105, "loss": 0.7716, "lr": 5e-06, "epoch": 1.7142857142857144, "percentage": 57.14, "elapsed_time": "0:33:48", "remaining_time": "0:25:21"}
8
  {"current_steps": 70, "total_steps": 105, "loss": 0.7678, "lr": 5e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:39:09", "remaining_time": "0:19:34"}
9
  {"current_steps": 70, "total_steps": 105, "eval_loss": 0.7982695698738098, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:39:34", "remaining_time": "0:19:47"}
10
+ {"current_steps": 80, "total_steps": 105, "loss": 0.7122, "lr": 5e-06, "epoch": 2.2857142857142856, "percentage": 76.19, "elapsed_time": "0:46:10", "remaining_time": "0:14:25"}
11
+ {"current_steps": 90, "total_steps": 105, "loss": 0.7064, "lr": 5e-06, "epoch": 2.571428571428571, "percentage": 85.71, "elapsed_time": "0:51:31", "remaining_time": "0:08:35"}
12
+ {"current_steps": 100, "total_steps": 105, "loss": 0.7049, "lr": 5e-06, "epoch": 2.857142857142857, "percentage": 95.24, "elapsed_time": "0:56:51", "remaining_time": "0:02:50"}
13
+ {"current_steps": 105, "total_steps": 105, "eval_loss": 0.7967763543128967, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:01:13", "remaining_time": "0:00:00"}
14
+ {"current_steps": 105, "total_steps": 105, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:02:26", "remaining_time": "0:00:00"}