Hugging Face's logo

mlfoundations-dev
/
multiple_samples_ground_truth_numina_aime

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
5958f4e
·
verified ·
1 Parent(s): dd54e27

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 +12 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88d9853b50fedfd085a56b8b5c514828e632b3623fc1032220551e1e02f933e5
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f9e5557c81a313ce6a67896e0d639d08dc85467e9c136cd5cfd3ada14e0832c
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8cf86c6179a5a59d0018e7f3c1eefa8ebeda3cb3743a1104c9749e046b7c43fa
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb5691f3d722dd4a4b973808747ee24c8966189cc055a57d19639ea9ea8fd359
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d4bd59dfac413584c46ea6da76e22303f6710ada932795fa8637807f1441781
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c272204d45711bdab899460374f5b8081107db05c9679ca041508d3553c1ebd
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13067522065f80d18728ddd25e1bcd6cee7e8ae73579daa5a64bdcb0e8351483
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1c3c4778e33e8e2da0ea9a0c626153b30d042546fcf0661393adc39e17cae41
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -35,3 +35,15 @@
35
  {"current_steps": 35, "total_steps": 48, "loss": 0.7111, "lr": 2.0907054222102367e-06, "epoch": 2.1875, "percentage": 72.92, "elapsed_time": "0:18:41", "remaining_time": "0:06:56"}
36
  {"current_steps": 36, "total_steps": 48, "loss": 0.6825, "lr": 1.8016348922055448e-06, "epoch": 2.25, "percentage": 75.0, "elapsed_time": "0:19:13", "remaining_time": "0:06:24"}
37
  {"current_steps": 37, "total_steps": 48, "loss": 0.6869, "lr": 1.5296290238968303e-06, "epoch": 2.3125, "percentage": 77.08, "elapsed_time": "0:19:45", "remaining_time": "0:05:52"}
 
 
 
 
 
 
 
 
 
 
 
 
 
35
  {"current_steps": 35, "total_steps": 48, "loss": 0.7111, "lr": 2.0907054222102367e-06, "epoch": 2.1875, "percentage": 72.92, "elapsed_time": "0:18:41", "remaining_time": "0:06:56"}
36
  {"current_steps": 36, "total_steps": 48, "loss": 0.6825, "lr": 1.8016348922055448e-06, "epoch": 2.25, "percentage": 75.0, "elapsed_time": "0:19:13", "remaining_time": "0:06:24"}
37
  {"current_steps": 37, "total_steps": 48, "loss": 0.6869, "lr": 1.5296290238968303e-06, "epoch": 2.3125, "percentage": 77.08, "elapsed_time": "0:19:45", "remaining_time": "0:05:52"}
38
+ {"current_steps": 38, "total_steps": 48, "loss": 0.6477, "lr": 1.2761390862810907e-06, "epoch": 2.375, "percentage": 79.17, "elapsed_time": "0:20:17", "remaining_time": "0:05:20"}
39
+ {"current_steps": 39, "total_steps": 48, "loss": 0.7017, "lr": 1.04251755785373e-06, "epoch": 2.4375, "percentage": 81.25, "elapsed_time": "0:20:47", "remaining_time": "0:04:47"}
40
+ {"current_steps": 40, "total_steps": 48, "loss": 0.6958, "lr": 8.30010910550611e-07, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "0:21:08", "remaining_time": "0:04:13"}
41
+ {"current_steps": 41, "total_steps": 48, "loss": 0.6983, "lr": 6.397529592809615e-07, "epoch": 2.5625, "percentage": 85.42, "elapsed_time": "0:21:39", "remaining_time": "0:03:41"}
42
+ {"current_steps": 42, "total_steps": 48, "loss": 0.6935, "lr": 4.727588125342669e-07, "epoch": 2.625, "percentage": 87.5, "elapsed_time": "0:22:04", "remaining_time": "0:03:09"}
43
+ {"current_steps": 43, "total_steps": 48, "loss": 0.7581, "lr": 3.299194563372604e-07, "epoch": 2.6875, "percentage": 89.58, "elapsed_time": "0:22:38", "remaining_time": "0:02:37"}
44
+ {"current_steps": 44, "total_steps": 48, "loss": 0.7712, "lr": 2.1199700045797077e-07, "epoch": 2.75, "percentage": 91.67, "elapsed_time": "0:23:02", "remaining_time": "0:02:05"}
45
+ {"current_steps": 45, "total_steps": 48, "loss": 0.7006, "lr": 1.196206122203647e-07, "epoch": 2.8125, "percentage": 93.75, "elapsed_time": "0:23:28", "remaining_time": "0:01:33"}
46
+ {"current_steps": 46, "total_steps": 48, "loss": 0.7299, "lr": 5.3283159624448745e-08, "epoch": 2.875, "percentage": 95.83, "elapsed_time": "0:23:55", "remaining_time": "0:01:02"}
47
+ {"current_steps": 47, "total_steps": 48, "loss": 0.7749, "lr": 1.333858168224178e-08, "epoch": 2.9375, "percentage": 97.92, "elapsed_time": "0:24:25", "remaining_time": "0:00:31"}
48
+ {"current_steps": 48, "total_steps": 48, "loss": 0.666, "lr": 0.0, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:24:49", "remaining_time": "0:00:00"}
49
+ {"current_steps": 48, "total_steps": 48, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:26:36", "remaining_time": "0:00:00"}