Hugging Face's logo

mlfoundations-dev
/
hp_ablations_qwen_scheduler_cosine_warmup0.05_minlr1e-7_dcftv1.2

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
e1a4cee
·
verified ·
1 Parent(s): 9eb4819

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 +35 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be8808014a00f81d10c4432679f99f1a634ff2df875a31ab9081f5eaa5004752
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac5877e6f66b7438a386ae4edebd95df52d4227e701a77706c1f5b7718e77bc3
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c590a646528b28c2a882941ec1a79295c478164500ba1c150daebcd04e41ea5
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5cb21f965af87a82c953aed95ba5f824fb852eaa01c649909c6bdf470392fef
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:947bf386185a1808fc27093b9496c79c0c70a9dfba27f7411284b2dbf781b4cd
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:110e5a63e41b13dbf0f7ccd43de109ba8b8ce1b96c750cc33b01778e797e8541
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ca3e467e32930e3b5cf3671bc5b427f7692673572379a6bf78e4395a6e7aaf0
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55b11c69a93911e8dfb130505fa49a40831173bd3aaaea5a3a13d03429cb1945
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -33,3 +33,38 @@
33
  {"current_steps": 330, "total_steps": 1023, "loss": 0.6415, "learning_rate": 4.074006031596782e-06, "epoch": 0.9656181419166057, "percentage": 32.26, "elapsed_time": "4:49:38", "remaining_time": "10:08:14"}
34
  {"current_steps": 340, "total_steps": 1023, "loss": 0.6375, "learning_rate": 4.0111539508990635e-06, "epoch": 0.9948792977322605, "percentage": 33.24, "elapsed_time": "4:58:25", "remaining_time": "9:59:28"}
35
  {"current_steps": 341, "total_steps": 1023, "eval_loss": 0.642014741897583, "epoch": 0.9978054133138259, "percentage": 33.33, "elapsed_time": "5:05:23", "remaining_time": "10:10:46"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  {"current_steps": 330, "total_steps": 1023, "loss": 0.6415, "learning_rate": 4.074006031596782e-06, "epoch": 0.9656181419166057, "percentage": 32.26, "elapsed_time": "4:49:38", "remaining_time": "10:08:14"}
34
  {"current_steps": 340, "total_steps": 1023, "loss": 0.6375, "learning_rate": 4.0111539508990635e-06, "epoch": 0.9948792977322605, "percentage": 33.24, "elapsed_time": "4:58:25", "remaining_time": "9:59:28"}
35
  {"current_steps": 341, "total_steps": 1023, "eval_loss": 0.642014741897583, "epoch": 0.9978054133138259, "percentage": 33.33, "elapsed_time": "5:05:23", "remaining_time": "10:10:46"}
36
+ {"current_steps": 350, "total_steps": 1023, "loss": 0.6554, "learning_rate": 3.946772476218427e-06, "epoch": 1.025237746891002, "percentage": 34.21, "elapsed_time": "5:14:03", "remaining_time": "10:03:52"}
37
+ {"current_steps": 360, "total_steps": 1023, "loss": 0.61, "learning_rate": 3.880928995826948e-06, "epoch": 1.054498902706657, "percentage": 35.19, "elapsed_time": "5:22:51", "remaining_time": "9:54:35"}
38
+ {"current_steps": 370, "total_steps": 1023, "loss": 0.6134, "learning_rate": 3.813692428282223e-06, "epoch": 1.0837600585223117, "percentage": 36.17, "elapsed_time": "5:31:39", "remaining_time": "9:45:19"}
39
+ {"current_steps": 380, "total_steps": 1023, "loss": 0.6107, "learning_rate": 3.7451331502901254e-06, "epoch": 1.1130212143379663, "percentage": 37.15, "elapsed_time": "5:40:26", "remaining_time": "9:36:04"}
40
+ {"current_steps": 390, "total_steps": 1023, "loss": 0.616, "learning_rate": 3.675322923041302e-06, "epoch": 1.142282370153621, "percentage": 38.12, "elapsed_time": "5:49:14", "remaining_time": "9:26:50"}
41
+ {"current_steps": 400, "total_steps": 1023, "loss": 0.6174, "learning_rate": 3.6043348170985315e-06, "epoch": 1.1715435259692757, "percentage": 39.1, "elapsed_time": "5:58:01", "remaining_time": "9:17:37"}
42
+ {"current_steps": 410, "total_steps": 1023, "loss": 0.617, "learning_rate": 3.532243135913563e-06, "epoch": 1.2008046817849305, "percentage": 40.08, "elapsed_time": "6:06:49", "remaining_time": "9:08:26"}
43
+ {"current_steps": 420, "total_steps": 1023, "loss": 0.605, "learning_rate": 3.4591233380534793e-06, "epoch": 1.2300658376005853, "percentage": 41.06, "elapsed_time": "6:15:36", "remaining_time": "8:59:15"}
44
+ {"current_steps": 430, "total_steps": 1023, "loss": 0.6151, "learning_rate": 3.3850519582180026e-06, "epoch": 1.2593269934162399, "percentage": 42.03, "elapsed_time": "6:24:23", "remaining_time": "8:50:06"}
45
+ {"current_steps": 440, "total_steps": 1023, "loss": 0.6076, "learning_rate": 3.3101065271304066e-06, "epoch": 1.2885881492318947, "percentage": 43.01, "elapsed_time": "6:33:10", "remaining_time": "8:40:57"}
46
+ {"current_steps": 450, "total_steps": 1023, "loss": 0.6115, "learning_rate": 3.2343654903858873e-06, "epoch": 1.3178493050475493, "percentage": 43.99, "elapsed_time": "6:41:58", "remaining_time": "8:31:50"}
47
+ {"current_steps": 460, "total_steps": 1023, "loss": 0.609, "learning_rate": 3.157908126342339e-06, "epoch": 1.347110460863204, "percentage": 44.97, "elapsed_time": "6:50:44", "remaining_time": "8:22:42"}
48
+ {"current_steps": 470, "total_steps": 1023, "loss": 0.6063, "learning_rate": 3.0808144631394693e-06, "epoch": 1.3763716166788589, "percentage": 45.94, "elapsed_time": "6:59:31", "remaining_time": "8:13:36"}
49
+ {"current_steps": 480, "total_steps": 1023, "loss": 0.607, "learning_rate": 3.0031651949331216e-06, "epoch": 1.4056327724945135, "percentage": 46.92, "elapsed_time": "7:08:17", "remaining_time": "8:04:30"}
50
+ {"current_steps": 490, "total_steps": 1023, "loss": 0.6132, "learning_rate": 2.9250415974324696e-06, "epoch": 1.4348939283101683, "percentage": 47.9, "elapsed_time": "7:17:04", "remaining_time": "7:55:26"}
51
+ {"current_steps": 500, "total_steps": 1023, "loss": 0.6017, "learning_rate": 2.8465254428285066e-06, "epoch": 1.464155084125823, "percentage": 48.88, "elapsed_time": "7:25:52", "remaining_time": "7:46:23"}
52
+ {"current_steps": 510, "total_steps": 1023, "loss": 0.6097, "learning_rate": 2.767698914202857e-06, "epoch": 1.4934162399414777, "percentage": 49.85, "elapsed_time": "7:34:39", "remaining_time": "7:37:20"}
53
+ {"current_steps": 520, "total_steps": 1023, "loss": 0.612, "learning_rate": 2.688644519506513e-06, "epoch": 1.5226773957571325, "percentage": 50.83, "elapsed_time": "7:43:26", "remaining_time": "7:28:17"}
54
+ {"current_steps": 530, "total_steps": 1023, "loss": 0.6106, "learning_rate": 2.6094450051985314e-06, "epoch": 1.5519385515727873, "percentage": 51.81, "elapsed_time": "7:52:13", "remaining_time": "7:19:15"}
55
+ {"current_steps": 540, "total_steps": 1023, "loss": 0.6172, "learning_rate": 2.5301832696350766e-06, "epoch": 1.5811997073884418, "percentage": 52.79, "elapsed_time": "8:01:00", "remaining_time": "7:10:13"}
56
+ {"current_steps": 550, "total_steps": 1023, "loss": 0.608, "learning_rate": 2.4509422762994763e-06, "epoch": 1.6104608632040964, "percentage": 53.76, "elapsed_time": "8:09:47", "remaining_time": "7:01:12"}
57
+ {"current_steps": 560, "total_steps": 1023, "loss": 0.6098, "learning_rate": 2.371804966964112e-06, "epoch": 1.6397220190197512, "percentage": 54.74, "elapsed_time": "8:18:35", "remaining_time": "6:52:13"}
58
+ {"current_steps": 570, "total_steps": 1023, "loss": 0.6003, "learning_rate": 2.292854174875026e-06, "epoch": 1.668983174835406, "percentage": 55.72, "elapsed_time": "8:27:23", "remaining_time": "6:43:14"}
59
+ {"current_steps": 580, "total_steps": 1023, "loss": 0.6098, "learning_rate": 2.214172538050132e-06, "epoch": 1.6982443306510606, "percentage": 56.7, "elapsed_time": "8:36:11", "remaining_time": "6:34:15"}
60
+ {"current_steps": 590, "total_steps": 1023, "loss": 0.6096, "learning_rate": 2.1358424127817636e-06, "epoch": 1.7275054864667154, "percentage": 57.67, "elapsed_time": "8:44:58", "remaining_time": "6:25:16"}
61
+ {"current_steps": 600, "total_steps": 1023, "loss": 0.6067, "learning_rate": 2.0579457874341145e-06, "epoch": 1.7567666422823702, "percentage": 58.65, "elapsed_time": "8:53:46", "remaining_time": "6:16:18"}
62
+ {"current_steps": 610, "total_steps": 1023, "loss": 0.6091, "learning_rate": 1.980564196625778e-06, "epoch": 1.7860277980980248, "percentage": 59.63, "elapsed_time": "9:02:33", "remaining_time": "6:07:20"}
63
+ {"current_steps": 620, "total_steps": 1023, "loss": 0.6094, "learning_rate": 1.9037786358872403e-06, "epoch": 1.8152889539136796, "percentage": 60.61, "elapsed_time": "9:11:20", "remaining_time": "5:58:22"}
64
+ {"current_steps": 630, "total_steps": 1023, "loss": 0.6087, "learning_rate": 1.8276694768826186e-06, "epoch": 1.8445501097293344, "percentage": 61.58, "elapsed_time": "9:20:07", "remaining_time": "5:49:24"}
65
+ {"current_steps": 640, "total_steps": 1023, "loss": 0.6034, "learning_rate": 1.752316383284421e-06, "epoch": 1.873811265544989, "percentage": 62.56, "elapsed_time": "9:28:53", "remaining_time": "5:40:27"}
66
+ {"current_steps": 650, "total_steps": 1023, "loss": 0.6091, "learning_rate": 1.6777982273893492e-06, "epoch": 1.9030724213606436, "percentage": 63.54, "elapsed_time": "9:37:41", "remaining_time": "5:31:30"}
67
+ {"current_steps": 660, "total_steps": 1023, "loss": 0.6097, "learning_rate": 1.6041930075624462e-06, "epoch": 1.9323335771762986, "percentage": 64.52, "elapsed_time": "9:46:28", "remaining_time": "5:22:33"}
68
+ {"current_steps": 670, "total_steps": 1023, "loss": 0.5985, "learning_rate": 1.531577766595981e-06, "epoch": 1.9615947329919532, "percentage": 65.49, "elapsed_time": "9:55:14", "remaining_time": "5:13:36"}
69
+ {"current_steps": 680, "total_steps": 1023, "loss": 0.613, "learning_rate": 1.4600285110685461e-06, "epoch": 1.9908558888076078, "percentage": 66.47, "elapsed_time": "10:04:00", "remaining_time": "5:04:40"}
70
+ {"current_steps": 682, "total_steps": 1023, "eval_loss": 0.6351438164710999, "epoch": 1.9967081199707388, "percentage": 66.67, "elapsed_time": "10:12:10", "remaining_time": "5:06:05"}