Hugging Face's logo

mlfoundations-dev
/
instruction_filtering_embedding_filter_math

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
5ee0d42
·
verified ·
1 Parent(s): 074e722

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 +27 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:575542e118912eb3d8c11fedc11f50d1f21f6fe65e272a56af0c110a4a9880bc
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1eccae707abdf33dbc513fca4f8b4efcddfc5fe625a75ad38c1981f45e2d0964
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:b65f5ad8f4274430c91dac29e9fdf824a13b06c4ad44d7ba46f7d9ca1f1c4cad
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74a92d252c8112f5c1527ea5fdf74afbf1d752db176eeca6773d065f44dba10a
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:f7f1aed1a908dbe868bf82fb253a69a931b0e69399d2f4079b7b657d2b6b5315
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d7aae57ebcb4a17eb296dcbbd26f2b386f474cdf976979a90761c8585532c1b
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:ba85fac4d0b7a2ddb4f0a3c5de2481d80fd8e6edae03cdc6ff5bdbca4b89d634
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a711efd53ffa0d75f573dc28753c1431f776c81adbad7d7573bc99c1c95c1190
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -30,3 +30,30 @@
30
  {"current_steps": 30, "total_steps": 78, "loss": 0.753, "lr": 7.754484907260513e-06, "epoch": 1.139240506329114, "percentage": 38.46, "elapsed_time": "0:11:21", "remaining_time": "0:18:10"}
31
  {"current_steps": 31, "total_steps": 78, "loss": 0.8569, "lr": 7.564496387029532e-06, "epoch": 1.1772151898734178, "percentage": 39.74, "elapsed_time": "0:11:43", "remaining_time": "0:17:46"}
32
  {"current_steps": 32, "total_steps": 78, "loss": 0.8048, "lr": 7.369343312364994e-06, "epoch": 1.2151898734177216, "percentage": 41.03, "elapsed_time": "0:12:05", "remaining_time": "0:17:23"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
30
  {"current_steps": 30, "total_steps": 78, "loss": 0.753, "lr": 7.754484907260513e-06, "epoch": 1.139240506329114, "percentage": 38.46, "elapsed_time": "0:11:21", "remaining_time": "0:18:10"}
31
  {"current_steps": 31, "total_steps": 78, "loss": 0.8569, "lr": 7.564496387029532e-06, "epoch": 1.1772151898734178, "percentage": 39.74, "elapsed_time": "0:11:43", "remaining_time": "0:17:46"}
32
  {"current_steps": 32, "total_steps": 78, "loss": 0.8048, "lr": 7.369343312364994e-06, "epoch": 1.2151898734177216, "percentage": 41.03, "elapsed_time": "0:12:05", "remaining_time": "0:17:23"}
33
+ {"current_steps": 33, "total_steps": 78, "loss": 0.7587, "lr": 7.169418695587791e-06, "epoch": 1.2531645569620253, "percentage": 42.31, "elapsed_time": "0:12:26", "remaining_time": "0:16:57"}
34
+ {"current_steps": 34, "total_steps": 78, "loss": 0.7822, "lr": 6.965125158269619e-06, "epoch": 1.2911392405063291, "percentage": 43.59, "elapsed_time": "0:12:47", "remaining_time": "0:16:32"}
35
+ {"current_steps": 35, "total_steps": 78, "loss": 0.8097, "lr": 6.7568741204067145e-06, "epoch": 1.3291139240506329, "percentage": 44.87, "elapsed_time": "0:13:08", "remaining_time": "0:16:08"}
36
+ {"current_steps": 36, "total_steps": 78, "loss": 0.7314, "lr": 6.545084971874738e-06, "epoch": 1.3670886075949367, "percentage": 46.15, "elapsed_time": "0:13:29", "remaining_time": "0:15:43"}
37
+ {"current_steps": 37, "total_steps": 78, "loss": 0.7242, "lr": 6.330184227833376e-06, "epoch": 1.4050632911392404, "percentage": 47.44, "elapsed_time": "0:13:48", "remaining_time": "0:15:18"}
38
+ {"current_steps": 38, "total_steps": 78, "loss": 0.7153, "lr": 6.112604669781572e-06, "epoch": 1.4430379746835442, "percentage": 48.72, "elapsed_time": "0:14:06", "remaining_time": "0:14:50"}
39
+ {"current_steps": 39, "total_steps": 78, "loss": 0.7422, "lr": 5.892784473993184e-06, "epoch": 1.481012658227848, "percentage": 50.0, "elapsed_time": "0:14:26", "remaining_time": "0:14:26"}
40
+ {"current_steps": 40, "total_steps": 78, "loss": 0.8014, "lr": 5.671166329088278e-06, "epoch": 1.518987341772152, "percentage": 51.28, "elapsed_time": "0:14:46", "remaining_time": "0:14:02"}
41
+ {"current_steps": 41, "total_steps": 78, "loss": 0.8311, "lr": 5.448196544517168e-06, "epoch": 1.5569620253164556, "percentage": 52.56, "elapsed_time": "0:15:06", "remaining_time": "0:13:38"}
42
+ {"current_steps": 42, "total_steps": 78, "loss": 0.8408, "lr": 5.224324151752575e-06, "epoch": 1.5949367088607596, "percentage": 53.85, "elapsed_time": "0:15:29", "remaining_time": "0:13:16"}
43
+ {"current_steps": 43, "total_steps": 78, "loss": 0.7371, "lr": 5e-06, "epoch": 1.6329113924050633, "percentage": 55.13, "elapsed_time": "0:15:48", "remaining_time": "0:12:51"}
44
+ {"current_steps": 44, "total_steps": 78, "loss": 0.7699, "lr": 4.775675848247427e-06, "epoch": 1.6708860759493671, "percentage": 56.41, "elapsed_time": "0:16:09", "remaining_time": "0:12:29"}
45
+ {"current_steps": 45, "total_steps": 78, "loss": 0.8093, "lr": 4.551803455482833e-06, "epoch": 1.7088607594936709, "percentage": 57.69, "elapsed_time": "0:16:29", "remaining_time": "0:12:05"}
46
+ {"current_steps": 46, "total_steps": 78, "loss": 0.7687, "lr": 4.3288336709117246e-06, "epoch": 1.7468354430379747, "percentage": 58.97, "elapsed_time": "0:16:53", "remaining_time": "0:11:44"}
47
+ {"current_steps": 47, "total_steps": 78, "loss": 0.702, "lr": 4.107215526006818e-06, "epoch": 1.7848101265822784, "percentage": 60.26, "elapsed_time": "0:17:15", "remaining_time": "0:11:22"}
48
+ {"current_steps": 48, "total_steps": 78, "loss": 0.7357, "lr": 3.887395330218429e-06, "epoch": 1.8227848101265822, "percentage": 61.54, "elapsed_time": "0:17:36", "remaining_time": "0:11:00"}
49
+ {"current_steps": 49, "total_steps": 78, "loss": 0.8004, "lr": 3.669815772166625e-06, "epoch": 1.8607594936708862, "percentage": 62.82, "elapsed_time": "0:17:56", "remaining_time": "0:10:37"}
50
+ {"current_steps": 50, "total_steps": 78, "loss": 0.7447, "lr": 3.4549150281252635e-06, "epoch": 1.8987341772151898, "percentage": 64.1, "elapsed_time": "0:18:16", "remaining_time": "0:10:14"}
51
+ {"current_steps": 51, "total_steps": 78, "loss": 0.7281, "lr": 3.2431258795932863e-06, "epoch": 1.9367088607594938, "percentage": 65.38, "elapsed_time": "0:18:33", "remaining_time": "0:09:49"}
52
+ {"current_steps": 52, "total_steps": 78, "loss": 0.7758, "lr": 3.0348748417303826e-06, "epoch": 1.9746835443037973, "percentage": 66.67, "elapsed_time": "0:18:51", "remaining_time": "0:09:25"}
53
+ {"current_steps": 53, "total_steps": 78, "loss": 1.108, "lr": 2.83058130441221e-06, "epoch": 2.0126582278481013, "percentage": 67.95, "elapsed_time": "0:20:05", "remaining_time": "0:09:28"}
54
+ {"current_steps": 54, "total_steps": 78, "loss": 0.7447, "lr": 2.6306566876350072e-06, "epoch": 2.050632911392405, "percentage": 69.23, "elapsed_time": "0:20:24", "remaining_time": "0:09:04"}
55
+ {"current_steps": 55, "total_steps": 78, "loss": 0.6326, "lr": 2.43550361297047e-06, "epoch": 2.088607594936709, "percentage": 70.51, "elapsed_time": "0:20:45", "remaining_time": "0:08:40"}
56
+ {"current_steps": 56, "total_steps": 78, "loss": 0.6769, "lr": 2.245515092739488e-06, "epoch": 2.1265822784810124, "percentage": 71.79, "elapsed_time": "0:21:07", "remaining_time": "0:08:18"}
57
+ {"current_steps": 57, "total_steps": 78, "loss": 0.7686, "lr": 2.061073738537635e-06, "epoch": 2.1645569620253164, "percentage": 73.08, "elapsed_time": "0:21:28", "remaining_time": "0:07:54"}
58
+ {"current_steps": 58, "total_steps": 78, "loss": 0.6645, "lr": 1.8825509907063328e-06, "epoch": 2.2025316455696204, "percentage": 74.36, "elapsed_time": "0:21:45", "remaining_time": "0:07:30"}
59
+ {"current_steps": 59, "total_steps": 78, "loss": 0.7499, "lr": 1.7103063703014372e-06, "epoch": 2.240506329113924, "percentage": 75.64, "elapsed_time": "0:22:05", "remaining_time": "0:07:06"}