Hugging Face's logo

mlfoundations-dev
/
qwen2-5_multiple_samples_shortest_seed_code

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
1
gsmyrnis commited on
Commit
2a24c21
·
verified ·
1 Parent(s): b610f7f

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 +26 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57f0920b36fd01f89630ca8186ab3f270e1c12166b99b86597afeac0064ec600
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0008a25331e9f9f848ed856dbc501ddaf1f803fb6960d3222ab280ed1bd5eac6
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:d62de1b27a6b270a755246ddf41e3d160f9733e06fc7b1ba9f8e1adbaf98388f
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:647cacda9c72fc48963dd65e50fa3a814d770bdf67529a5ba79a26f56a93259b
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:490de428b8daad4e12f6c44c460b7f0a6b1eb61f495e9cabb397b9fe21d742ee
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cc19bdab55d8e51b173dee00c33c2989253321d5d2eb3813fd16d2637889c31
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:addae06df4feeefe451bcda2aad9ae1c0748917eee3734a75e26b36785c769d0
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72f80d3f5bb7225f07e2642df17ae2e9240180d1c33e86b7f7d4c9efecae7b6c
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -39,3 +39,29 @@
39
  {"current_steps": 39, "total_steps": 78, "loss": 0.7777, "lr": 5.892784473993184e-06, "epoch": 1.481012658227848, "percentage": 50.0, "elapsed_time": "0:08:41", "remaining_time": "0:08:41"}
40
  {"current_steps": 40, "total_steps": 78, "loss": 0.8305, "lr": 5.671166329088278e-06, "epoch": 1.518987341772152, "percentage": 51.28, "elapsed_time": "0:08:55", "remaining_time": "0:08:28"}
41
  {"current_steps": 41, "total_steps": 78, "loss": 0.8163, "lr": 5.448196544517168e-06, "epoch": 1.5569620253164556, "percentage": 52.56, "elapsed_time": "0:09:06", "remaining_time": "0:08:13"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39
  {"current_steps": 39, "total_steps": 78, "loss": 0.7777, "lr": 5.892784473993184e-06, "epoch": 1.481012658227848, "percentage": 50.0, "elapsed_time": "0:08:41", "remaining_time": "0:08:41"}
40
  {"current_steps": 40, "total_steps": 78, "loss": 0.8305, "lr": 5.671166329088278e-06, "epoch": 1.518987341772152, "percentage": 51.28, "elapsed_time": "0:08:55", "remaining_time": "0:08:28"}
41
  {"current_steps": 41, "total_steps": 78, "loss": 0.8163, "lr": 5.448196544517168e-06, "epoch": 1.5569620253164556, "percentage": 52.56, "elapsed_time": "0:09:06", "remaining_time": "0:08:13"}
42
+ {"current_steps": 42, "total_steps": 78, "loss": 0.7768, "lr": 5.224324151752575e-06, "epoch": 1.5949367088607596, "percentage": 53.85, "elapsed_time": "0:09:20", "remaining_time": "0:08:00"}
43
+ {"current_steps": 43, "total_steps": 78, "loss": 0.7422, "lr": 5e-06, "epoch": 1.6329113924050633, "percentage": 55.13, "elapsed_time": "0:09:30", "remaining_time": "0:07:44"}
44
+ {"current_steps": 44, "total_steps": 78, "loss": 0.8107, "lr": 4.775675848247427e-06, "epoch": 1.6708860759493671, "percentage": 56.41, "elapsed_time": "0:09:44", "remaining_time": "0:07:31"}
45
+ {"current_steps": 45, "total_steps": 78, "loss": 0.7577, "lr": 4.551803455482833e-06, "epoch": 1.7088607594936709, "percentage": 57.69, "elapsed_time": "0:09:55", "remaining_time": "0:07:16"}
46
+ {"current_steps": 46, "total_steps": 78, "loss": 0.808, "lr": 4.3288336709117246e-06, "epoch": 1.7468354430379747, "percentage": 58.97, "elapsed_time": "0:10:04", "remaining_time": "0:07:00"}
47
+ {"current_steps": 47, "total_steps": 78, "loss": 0.7899, "lr": 4.107215526006818e-06, "epoch": 1.7848101265822784, "percentage": 60.26, "elapsed_time": "0:10:17", "remaining_time": "0:06:47"}
48
+ {"current_steps": 48, "total_steps": 78, "loss": 0.7518, "lr": 3.887395330218429e-06, "epoch": 1.8227848101265822, "percentage": 61.54, "elapsed_time": "0:10:29", "remaining_time": "0:06:33"}
49
+ {"current_steps": 49, "total_steps": 78, "loss": 0.8113, "lr": 3.669815772166625e-06, "epoch": 1.8607594936708862, "percentage": 62.82, "elapsed_time": "0:10:44", "remaining_time": "0:06:21"}
50
+ {"current_steps": 50, "total_steps": 78, "loss": 0.765, "lr": 3.4549150281252635e-06, "epoch": 1.8987341772151898, "percentage": 64.1, "elapsed_time": "0:10:54", "remaining_time": "0:06:06"}
51
+ {"current_steps": 51, "total_steps": 78, "loss": 0.7156, "lr": 3.2431258795932863e-06, "epoch": 1.9367088607594938, "percentage": 65.38, "elapsed_time": "0:11:07", "remaining_time": "0:05:53"}
52
+ {"current_steps": 52, "total_steps": 78, "loss": 0.7184, "lr": 3.0348748417303826e-06, "epoch": 1.9746835443037973, "percentage": 66.67, "elapsed_time": "0:11:16", "remaining_time": "0:05:38"}
53
+ {"current_steps": 53, "total_steps": 78, "loss": 1.214, "lr": 2.83058130441221e-06, "epoch": 2.0126582278481013, "percentage": 67.95, "elapsed_time": "0:12:31", "remaining_time": "0:05:54"}
54
+ {"current_steps": 54, "total_steps": 78, "loss": 0.7168, "lr": 2.6306566876350072e-06, "epoch": 2.050632911392405, "percentage": 69.23, "elapsed_time": "0:12:43", "remaining_time": "0:05:39"}
55
+ {"current_steps": 55, "total_steps": 78, "loss": 0.6855, "lr": 2.43550361297047e-06, "epoch": 2.088607594936709, "percentage": 70.51, "elapsed_time": "0:12:53", "remaining_time": "0:05:23"}
56
+ {"current_steps": 56, "total_steps": 78, "loss": 0.6483, "lr": 2.245515092739488e-06, "epoch": 2.1265822784810124, "percentage": 71.79, "elapsed_time": "0:13:06", "remaining_time": "0:05:09"}
57
+ {"current_steps": 57, "total_steps": 78, "loss": 0.7646, "lr": 2.061073738537635e-06, "epoch": 2.1645569620253164, "percentage": 73.08, "elapsed_time": "0:13:16", "remaining_time": "0:04:53"}
58
+ {"current_steps": 58, "total_steps": 78, "loss": 0.7752, "lr": 1.8825509907063328e-06, "epoch": 2.2025316455696204, "percentage": 74.36, "elapsed_time": "0:13:25", "remaining_time": "0:04:37"}
59
+ {"current_steps": 59, "total_steps": 78, "loss": 0.6389, "lr": 1.7103063703014372e-06, "epoch": 2.240506329113924, "percentage": 75.64, "elapsed_time": "0:13:36", "remaining_time": "0:04:23"}
60
+ {"current_steps": 60, "total_steps": 78, "loss": 0.7054, "lr": 1.544686755065677e-06, "epoch": 2.278481012658228, "percentage": 76.92, "elapsed_time": "0:13:52", "remaining_time": "0:04:09"}
61
+ {"current_steps": 61, "total_steps": 78, "loss": 0.8011, "lr": 1.3860256808630429e-06, "epoch": 2.3164556962025316, "percentage": 78.21, "elapsed_time": "0:14:01", "remaining_time": "0:03:54"}
62
+ {"current_steps": 62, "total_steps": 78, "loss": 0.6654, "lr": 1.234642669981946e-06, "epoch": 2.3544303797468356, "percentage": 79.49, "elapsed_time": "0:14:14", "remaining_time": "0:03:40"}
63
+ {"current_steps": 63, "total_steps": 78, "loss": 0.7555, "lr": 1.0908425876598512e-06, "epoch": 2.392405063291139, "percentage": 80.77, "elapsed_time": "0:14:27", "remaining_time": "0:03:26"}
64
+ {"current_steps": 64, "total_steps": 78, "loss": 0.7548, "lr": 9.549150281252633e-07, "epoch": 2.430379746835443, "percentage": 82.05, "elapsed_time": "0:14:40", "remaining_time": "0:03:12"}
65
+ {"current_steps": 65, "total_steps": 78, "loss": 0.6397, "lr": 8.271337313934869e-07, "epoch": 2.4683544303797467, "percentage": 83.33, "elapsed_time": "0:14:53", "remaining_time": "0:02:58"}
66
+ {"current_steps": 66, "total_steps": 78, "loss": 0.7229, "lr": 7.077560319906696e-07, "epoch": 2.5063291139240507, "percentage": 84.62, "elapsed_time": "0:15:07", "remaining_time": "0:02:44"}
67
+ {"current_steps": 67, "total_steps": 78, "loss": 0.7062, "lr": 5.9702234071631e-07, "epoch": 2.5443037974683547, "percentage": 85.9, "elapsed_time": "0:15:22", "remaining_time": "0:02:31"}