Hugging Face's logo

mlfoundations-dev
/
a1_science_stackexchange_physics_1k

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
sedrickkeh commited on
Commit
21c2a8f
·
verified ·
1 Parent(s): fd5175f

Training in progress, epoch 4

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 +10 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:121c80c503762c402a7d9be1b5766544189ef409a2cb08abae58bde349dddfb1
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bdd15f99c20bc14223ed7a4a6bfee8b874fd7c7a9875181df65c36bfe07aa59
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84e0b941918976592ef8ea9dbe5d6b3044c3ab29d310727172697864a96b163c
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:361a46af8fd1ecffd9a394d819193a95bdf72611d80f07a81a928c371af0f6c0
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f508f19bd95737d11fa1808930ccc95cef79384d796d5417e97722f9ab6a9b0
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b667f897c30d9218cb943558233071f7e495b967e09e9982869ed5cdc718477f
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3adf977d60a2928dc538af274765d5557fcc0ea08cc593745736c79c30f81a4c
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7353e2b52fcc29959444c93e2908a9dd7a8a7b9c7cbf6898ec52e072f0fe7c5
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -44,3 +44,13 @@
44
  {"current_steps": 44, "total_steps": 70, "loss": 0.3311, "lr": 7.291595318569951e-06, "epoch": 4.224, "percentage": 62.86, "elapsed_time": "0:32:33", "remaining_time": "0:19:14"}
45
  {"current_steps": 45, "total_steps": 70, "loss": 0.3051, "lr": 6.815133497483157e-06, "epoch": 4.32, "percentage": 64.29, "elapsed_time": "0:33:15", "remaining_time": "0:18:28"}
46
  {"current_steps": 46, "total_steps": 70, "loss": 0.3002, "lr": 6.34658975633605e-06, "epoch": 4.416, "percentage": 65.71, "elapsed_time": "0:33:58", "remaining_time": "0:17:43"}
 
 
 
 
 
 
 
 
 
 
 
44
  {"current_steps": 44, "total_steps": 70, "loss": 0.3311, "lr": 7.291595318569951e-06, "epoch": 4.224, "percentage": 62.86, "elapsed_time": "0:32:33", "remaining_time": "0:19:14"}
45
  {"current_steps": 45, "total_steps": 70, "loss": 0.3051, "lr": 6.815133497483157e-06, "epoch": 4.32, "percentage": 64.29, "elapsed_time": "0:33:15", "remaining_time": "0:18:28"}
46
  {"current_steps": 46, "total_steps": 70, "loss": 0.3002, "lr": 6.34658975633605e-06, "epoch": 4.416, "percentage": 65.71, "elapsed_time": "0:33:58", "remaining_time": "0:17:43"}
47
+ {"current_steps": 47, "total_steps": 70, "loss": 0.2833, "lr": 5.887128968693887e-06, "epoch": 4.5120000000000005, "percentage": 67.14, "elapsed_time": "0:34:39", "remaining_time": "0:16:57"}
48
+ {"current_steps": 48, "total_steps": 70, "loss": 0.2563, "lr": 5.43789342646837e-06, "epoch": 4.608, "percentage": 68.57, "elapsed_time": "0:35:16", "remaining_time": "0:16:10"}
49
+ {"current_steps": 49, "total_steps": 70, "loss": 0.2832, "lr": 5.000000000000003e-06, "epoch": 4.704, "percentage": 70.0, "elapsed_time": "0:36:02", "remaining_time": "0:15:26"}
50
+ {"current_steps": 50, "total_steps": 70, "loss": 0.2656, "lr": 4.5745373613424075e-06, "epoch": 4.8, "percentage": 71.43, "elapsed_time": "0:36:37", "remaining_time": "0:14:39"}
51
+ {"current_steps": 51, "total_steps": 70, "loss": 0.2866, "lr": 4.162563277652104e-06, "epoch": 4.896, "percentage": 72.86, "elapsed_time": "0:37:10", "remaining_time": "0:13:50"}
52
+ {"current_steps": 52, "total_steps": 70, "loss": 0.2686, "lr": 3.7651019814126656e-06, "epoch": 4.992, "percentage": 74.29, "elapsed_time": "0:38:01", "remaining_time": "0:13:09"}
53
+ {"current_steps": 53, "total_steps": 70, "loss": 0.2992, "lr": 3.3831416240314085e-06, "epoch": 5.088, "percentage": 75.71, "elapsed_time": "0:39:44", "remaining_time": "0:12:44"}
54
+ {"current_steps": 54, "total_steps": 70, "loss": 0.2236, "lr": 3.017631819139273e-06, "epoch": 5.184, "percentage": 77.14, "elapsed_time": "0:40:29", "remaining_time": "0:11:59"}
55
+ {"current_steps": 55, "total_steps": 70, "loss": 0.2247, "lr": 2.669481281701739e-06, "epoch": 5.28, "percentage": 78.57, "elapsed_time": "0:41:07", "remaining_time": "0:11:12"}
56
+ {"current_steps": 56, "total_steps": 70, "loss": 0.252, "lr": 2.339555568810221e-06, "epoch": 5.376, "percentage": 80.0, "elapsed_time": "0:41:49", "remaining_time": "0:10:27"}