Hugging Face's logo

mlfoundations-dev
/
distill_r1_code_evol_instruct_baseline

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
1
sedrickkeh commited on
Commit
689c7b6
·
verified ·
1 Parent(s): b29e2f9

Training in progress, epoch 2

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 +25 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f202d7d5d0880c511995507672249920e10e2c4199f16828fdad8e624d26466
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7f95f2b7fe665991d2f3e9bf5ad974d8592e171d0603fd86e01ab1bd29b43cd
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:f4196ddb45a80b02cc623a943c059a4cda7f2e07bb9274e3eb620fe037159235
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f4f8e92cc5657759ebd11e257c8f7c10877e32d397e1a0515de6e67bb10e9df
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f7d46e33e7e93c21857dbe51a2ee74205969aad4688f84555fa3bd64d2e1d7e
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f48db334f461aefd806b2f01199d653adfc66451a1099376a116e1012ed3649
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1305bab33395113f4887660f7d9f85e36789862a324e137b6bdb4f3bd7403141
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2fb1bb683ce03e5a59d78731790f3a7af87892a5986b0212f02c6f0ac522319
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -52,3 +52,28 @@
52
  {"current_steps": 52, "total_steps": 78, "loss": 0.8499, "lr": 3.0348748417303826e-06, "epoch": 1.9936102236421727, "percentage": 66.67, "elapsed_time": "0:36:41", "remaining_time": "0:18:20"}
53
  {"current_steps": 53, "total_steps": 78, "loss": 1.4672, "lr": 2.83058130441221e-06, "epoch": 2.0319488817891376, "percentage": 67.95, "elapsed_time": "0:38:34", "remaining_time": "0:18:11"}
54
  {"current_steps": 54, "total_steps": 78, "loss": 0.7681, "lr": 2.6306566876350072e-06, "epoch": 2.070287539936102, "percentage": 69.23, "elapsed_time": "0:39:18", "remaining_time": "0:17:28"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
52
  {"current_steps": 52, "total_steps": 78, "loss": 0.8499, "lr": 3.0348748417303826e-06, "epoch": 1.9936102236421727, "percentage": 66.67, "elapsed_time": "0:36:41", "remaining_time": "0:18:20"}
53
  {"current_steps": 53, "total_steps": 78, "loss": 1.4672, "lr": 2.83058130441221e-06, "epoch": 2.0319488817891376, "percentage": 67.95, "elapsed_time": "0:38:34", "remaining_time": "0:18:11"}
54
  {"current_steps": 54, "total_steps": 78, "loss": 0.7681, "lr": 2.6306566876350072e-06, "epoch": 2.070287539936102, "percentage": 69.23, "elapsed_time": "0:39:18", "remaining_time": "0:17:28"}
55
+ {"current_steps": 55, "total_steps": 78, "loss": 0.7296, "lr": 2.43550361297047e-06, "epoch": 2.108626198083067, "percentage": 70.51, "elapsed_time": "0:39:58", "remaining_time": "0:16:43"}
56
+ {"current_steps": 56, "total_steps": 78, "loss": 0.7339, "lr": 2.245515092739488e-06, "epoch": 2.146964856230032, "percentage": 71.79, "elapsed_time": "0:40:34", "remaining_time": "0:15:56"}
57
+ {"current_steps": 57, "total_steps": 78, "loss": 0.7905, "lr": 2.061073738537635e-06, "epoch": 2.1853035143769968, "percentage": 73.08, "elapsed_time": "0:41:14", "remaining_time": "0:15:11"}
58
+ {"current_steps": 58, "total_steps": 78, "loss": 0.7852, "lr": 1.8825509907063328e-06, "epoch": 2.2236421725239617, "percentage": 74.36, "elapsed_time": "0:41:57", "remaining_time": "0:14:28"}
59
+ {"current_steps": 59, "total_steps": 78, "loss": 0.7263, "lr": 1.7103063703014372e-06, "epoch": 2.2619808306709266, "percentage": 75.64, "elapsed_time": "0:42:34", "remaining_time": "0:13:42"}
60
+ {"current_steps": 60, "total_steps": 78, "loss": 0.7394, "lr": 1.544686755065677e-06, "epoch": 2.3003194888178915, "percentage": 76.92, "elapsed_time": "0:43:10", "remaining_time": "0:12:57"}
61
+ {"current_steps": 61, "total_steps": 78, "loss": 0.7811, "lr": 1.3860256808630429e-06, "epoch": 2.3386581469648564, "percentage": 78.21, "elapsed_time": "0:43:55", "remaining_time": "0:12:14"}
62
+ {"current_steps": 62, "total_steps": 78, "loss": 0.6595, "lr": 1.234642669981946e-06, "epoch": 2.376996805111821, "percentage": 79.49, "elapsed_time": "0:44:37", "remaining_time": "0:11:30"}
63
+ {"current_steps": 63, "total_steps": 78, "loss": 0.9082, "lr": 1.0908425876598512e-06, "epoch": 2.415335463258786, "percentage": 80.77, "elapsed_time": "0:45:21", "remaining_time": "0:10:48"}
64
+ {"current_steps": 64, "total_steps": 78, "loss": 0.7043, "lr": 9.549150281252633e-07, "epoch": 2.4536741214057507, "percentage": 82.05, "elapsed_time": "0:46:00", "remaining_time": "0:10:03"}
65
+ {"current_steps": 65, "total_steps": 78, "loss": 0.7529, "lr": 8.271337313934869e-07, "epoch": 2.4920127795527156, "percentage": 83.33, "elapsed_time": "0:46:36", "remaining_time": "0:09:19"}
66
+ {"current_steps": 66, "total_steps": 78, "loss": 0.7902, "lr": 7.077560319906696e-07, "epoch": 2.5303514376996805, "percentage": 84.62, "elapsed_time": "0:47:15", "remaining_time": "0:08:35"}
67
+ {"current_steps": 67, "total_steps": 78, "loss": 0.7202, "lr": 5.9702234071631e-07, "epoch": 2.5686900958466454, "percentage": 85.9, "elapsed_time": "0:47:54", "remaining_time": "0:07:51"}
68
+ {"current_steps": 68, "total_steps": 78, "loss": 0.8864, "lr": 4.951556604879049e-07, "epoch": 2.6070287539936103, "percentage": 87.18, "elapsed_time": "0:48:49", "remaining_time": "0:07:10"}
69
+ {"current_steps": 69, "total_steps": 78, "loss": 0.7205, "lr": 4.0236113724274716e-07, "epoch": 2.6453674121405752, "percentage": 88.46, "elapsed_time": "0:49:25", "remaining_time": "0:06:26"}
70
+ {"current_steps": 70, "total_steps": 78, "loss": 0.72, "lr": 3.18825646801314e-07, "epoch": 2.68370607028754, "percentage": 89.74, "elapsed_time": "0:50:01", "remaining_time": "0:05:43"}
71
+ {"current_steps": 71, "total_steps": 78, "loss": 0.7959, "lr": 2.447174185242324e-07, "epoch": 2.722044728434505, "percentage": 91.03, "elapsed_time": "0:50:41", "remaining_time": "0:04:59"}
72
+ {"current_steps": 72, "total_steps": 78, "loss": 0.7179, "lr": 1.801856965207338e-07, "epoch": 2.7603833865814695, "percentage": 92.31, "elapsed_time": "0:51:27", "remaining_time": "0:04:17"}
73
+ {"current_steps": 73, "total_steps": 78, "loss": 0.6673, "lr": 1.253604390908819e-07, "epoch": 2.7987220447284344, "percentage": 93.59, "elapsed_time": "0:52:04", "remaining_time": "0:03:34"}
74
+ {"current_steps": 74, "total_steps": 78, "loss": 0.8126, "lr": 8.035205700685167e-08, "epoch": 2.8370607028753994, "percentage": 94.87, "elapsed_time": "0:52:47", "remaining_time": "0:02:51"}
75
+ {"current_steps": 75, "total_steps": 78, "loss": 0.7562, "lr": 4.52511911603265e-08, "epoch": 2.8753993610223643, "percentage": 96.15, "elapsed_time": "0:53:28", "remaining_time": "0:02:08"}
76
+ {"current_steps": 76, "total_steps": 78, "loss": 0.7857, "lr": 2.012853002380466e-08, "epoch": 2.913738019169329, "percentage": 97.44, "elapsed_time": "0:54:11", "remaining_time": "0:01:25"}
77
+ {"current_steps": 77, "total_steps": 78, "loss": 0.7503, "lr": 5.034667293427053e-09, "epoch": 2.952076677316294, "percentage": 98.72, "elapsed_time": "0:54:45", "remaining_time": "0:00:42"}
78
+ {"current_steps": 78, "total_steps": 78, "loss": 0.7684, "lr": 0.0, "epoch": 2.9904153354632586, "percentage": 100.0, "elapsed_time": "0:55:27", "remaining_time": "0:00:00"}
79
+ {"current_steps": 78, "total_steps": 78, "epoch": 2.9904153354632586, "percentage": 100.0, "elapsed_time": "0:57:36", "remaining_time": "0:00:00"}