Hugging Face's logo

mlfoundations-dev
/
hp_ablations_qwen_adambeta2_0.999_dcftv1.2

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
ed27ef4
·
verified ·
1 Parent(s): 6029d88

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:e59722e0352928ff852c67dd3d4718361958c9aa52b753c8181d115795d3ac02
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc353c4eebdb2b4a2f9fc885deb363bf06eb4568e4e22bd02362b83ae16a7a4d
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41c81659b0f14128e2d4e9519c4831a9b65de745f24ffbcd5b180e7c95681888
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6a54fe114690478c32eee22793954cae10f9b74971eeedfb6bcf0c0b4ffff3a
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a4d26b93031fdeb02794575bd48a7c73b01e3010c7b73c63c3db39e399de6e0
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a08165934ba590ca10ee3423a2f0e7bf831c5d3abb14e3b7e3d8f71ce40c2b27
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1176842fdab8b72e987b5f3954ac2c03b7f8cc154b7da05b76ef561929db5ac1
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e47ffdca08244c77085c9ad6d3ef3715083bea83f4d3f0b48fa4b485bfe32061
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -33,3 +33,38 @@
33
  {"current_steps": 330, "total_steps": 1023, "loss": 0.6402, "learning_rate": 5e-06, "epoch": 0.9656181419166057, "percentage": 32.26, "elapsed_time": "4:47:44", "remaining_time": "10:04:15"}
34
  {"current_steps": 340, "total_steps": 1023, "loss": 0.6362, "learning_rate": 5e-06, "epoch": 0.9948792977322605, "percentage": 33.24, "elapsed_time": "4:56:28", "remaining_time": "9:55:33"}
35
  {"current_steps": 341, "total_steps": 1023, "eval_loss": 0.6406816840171814, "epoch": 0.9978054133138259, "percentage": 33.33, "elapsed_time": "5:03:22", "remaining_time": "10:06:45"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  {"current_steps": 330, "total_steps": 1023, "loss": 0.6402, "learning_rate": 5e-06, "epoch": 0.9656181419166057, "percentage": 32.26, "elapsed_time": "4:47:44", "remaining_time": "10:04:15"}
34
  {"current_steps": 340, "total_steps": 1023, "loss": 0.6362, "learning_rate": 5e-06, "epoch": 0.9948792977322605, "percentage": 33.24, "elapsed_time": "4:56:28", "remaining_time": "9:55:33"}
35
  {"current_steps": 341, "total_steps": 1023, "eval_loss": 0.6406816840171814, "epoch": 0.9978054133138259, "percentage": 33.33, "elapsed_time": "5:03:22", "remaining_time": "10:06:45"}
36
+ {"current_steps": 350, "total_steps": 1023, "loss": 0.6514, "learning_rate": 5e-06, "epoch": 1.025237746891002, "percentage": 34.21, "elapsed_time": "5:11:58", "remaining_time": "9:59:53"}
37
+ {"current_steps": 360, "total_steps": 1023, "loss": 0.6056, "learning_rate": 5e-06, "epoch": 1.054498902706657, "percentage": 35.19, "elapsed_time": "5:20:42", "remaining_time": "9:50:38"}
38
+ {"current_steps": 370, "total_steps": 1023, "loss": 0.6089, "learning_rate": 5e-06, "epoch": 1.0837600585223117, "percentage": 36.17, "elapsed_time": "5:29:26", "remaining_time": "9:41:24"}
39
+ {"current_steps": 380, "total_steps": 1023, "loss": 0.6064, "learning_rate": 5e-06, "epoch": 1.1130212143379663, "percentage": 37.15, "elapsed_time": "5:38:10", "remaining_time": "9:32:14"}
40
+ {"current_steps": 390, "total_steps": 1023, "loss": 0.6117, "learning_rate": 5e-06, "epoch": 1.142282370153621, "percentage": 38.12, "elapsed_time": "5:46:55", "remaining_time": "9:23:05"}
41
+ {"current_steps": 400, "total_steps": 1023, "loss": 0.6132, "learning_rate": 5e-06, "epoch": 1.1715435259692757, "percentage": 39.1, "elapsed_time": "5:55:38", "remaining_time": "9:13:55"}
42
+ {"current_steps": 410, "total_steps": 1023, "loss": 0.6128, "learning_rate": 5e-06, "epoch": 1.2008046817849305, "percentage": 40.08, "elapsed_time": "6:04:23", "remaining_time": "9:04:47"}
43
+ {"current_steps": 420, "total_steps": 1023, "loss": 0.601, "learning_rate": 5e-06, "epoch": 1.2300658376005853, "percentage": 41.06, "elapsed_time": "6:13:05", "remaining_time": "8:55:39"}
44
+ {"current_steps": 430, "total_steps": 1023, "loss": 0.6111, "learning_rate": 5e-06, "epoch": 1.2593269934162399, "percentage": 42.03, "elapsed_time": "6:21:49", "remaining_time": "8:46:33"}
45
+ {"current_steps": 440, "total_steps": 1023, "loss": 0.6037, "learning_rate": 5e-06, "epoch": 1.2885881492318947, "percentage": 43.01, "elapsed_time": "6:30:33", "remaining_time": "8:37:29"}
46
+ {"current_steps": 450, "total_steps": 1023, "loss": 0.6075, "learning_rate": 5e-06, "epoch": 1.3178493050475493, "percentage": 43.99, "elapsed_time": "6:39:18", "remaining_time": "8:28:26"}
47
+ {"current_steps": 460, "total_steps": 1023, "loss": 0.6052, "learning_rate": 5e-06, "epoch": 1.347110460863204, "percentage": 44.97, "elapsed_time": "6:48:01", "remaining_time": "8:19:23"}
48
+ {"current_steps": 470, "total_steps": 1023, "loss": 0.6025, "learning_rate": 5e-06, "epoch": 1.3763716166788589, "percentage": 45.94, "elapsed_time": "6:56:44", "remaining_time": "8:10:20"}
49
+ {"current_steps": 480, "total_steps": 1023, "loss": 0.6034, "learning_rate": 5e-06, "epoch": 1.4056327724945135, "percentage": 46.92, "elapsed_time": "7:05:28", "remaining_time": "8:01:19"}
50
+ {"current_steps": 490, "total_steps": 1023, "loss": 0.6097, "learning_rate": 5e-06, "epoch": 1.4348939283101683, "percentage": 47.9, "elapsed_time": "7:14:11", "remaining_time": "7:52:17"}
51
+ {"current_steps": 500, "total_steps": 1023, "loss": 0.5981, "learning_rate": 5e-06, "epoch": 1.464155084125823, "percentage": 48.88, "elapsed_time": "7:22:55", "remaining_time": "7:43:17"}
52
+ {"current_steps": 510, "total_steps": 1023, "loss": 0.6061, "learning_rate": 5e-06, "epoch": 1.4934162399414777, "percentage": 49.85, "elapsed_time": "7:31:36", "remaining_time": "7:34:16"}
53
+ {"current_steps": 520, "total_steps": 1023, "loss": 0.6084, "learning_rate": 5e-06, "epoch": 1.5226773957571325, "percentage": 50.83, "elapsed_time": "7:40:20", "remaining_time": "7:25:17"}
54
+ {"current_steps": 530, "total_steps": 1023, "loss": 0.6071, "learning_rate": 5e-06, "epoch": 1.5519385515727873, "percentage": 51.81, "elapsed_time": "7:49:04", "remaining_time": "7:16:19"}
55
+ {"current_steps": 540, "total_steps": 1023, "loss": 0.6136, "learning_rate": 5e-06, "epoch": 1.5811997073884418, "percentage": 52.79, "elapsed_time": "7:57:47", "remaining_time": "7:07:21"}
56
+ {"current_steps": 550, "total_steps": 1023, "loss": 0.6047, "learning_rate": 5e-06, "epoch": 1.6104608632040964, "percentage": 53.76, "elapsed_time": "8:06:30", "remaining_time": "6:58:24"}
57
+ {"current_steps": 560, "total_steps": 1023, "loss": 0.6064, "learning_rate": 5e-06, "epoch": 1.6397220190197512, "percentage": 54.74, "elapsed_time": "8:15:13", "remaining_time": "6:49:26"}
58
+ {"current_steps": 570, "total_steps": 1023, "loss": 0.597, "learning_rate": 5e-06, "epoch": 1.668983174835406, "percentage": 55.72, "elapsed_time": "8:23:55", "remaining_time": "6:40:29"}
59
+ {"current_steps": 580, "total_steps": 1023, "loss": 0.6064, "learning_rate": 5e-06, "epoch": 1.6982443306510606, "percentage": 56.7, "elapsed_time": "8:32:39", "remaining_time": "6:31:33"}
60
+ {"current_steps": 590, "total_steps": 1023, "loss": 0.6066, "learning_rate": 5e-06, "epoch": 1.7275054864667154, "percentage": 57.67, "elapsed_time": "8:41:22", "remaining_time": "6:22:37"}
61
+ {"current_steps": 600, "total_steps": 1023, "loss": 0.6034, "learning_rate": 5e-06, "epoch": 1.7567666422823702, "percentage": 58.65, "elapsed_time": "8:50:04", "remaining_time": "6:13:41"}
62
+ {"current_steps": 610, "total_steps": 1023, "loss": 0.6059, "learning_rate": 5e-06, "epoch": 1.7860277980980248, "percentage": 59.63, "elapsed_time": "8:58:46", "remaining_time": "6:04:46"}
63
+ {"current_steps": 620, "total_steps": 1023, "loss": 0.6063, "learning_rate": 5e-06, "epoch": 1.8152889539136796, "percentage": 60.61, "elapsed_time": "9:07:30", "remaining_time": "5:55:52"}
64
+ {"current_steps": 630, "total_steps": 1023, "loss": 0.6054, "learning_rate": 5e-06, "epoch": 1.8445501097293344, "percentage": 61.58, "elapsed_time": "9:16:13", "remaining_time": "5:46:58"}
65
+ {"current_steps": 640, "total_steps": 1023, "loss": 0.6002, "learning_rate": 5e-06, "epoch": 1.873811265544989, "percentage": 62.56, "elapsed_time": "9:24:57", "remaining_time": "5:38:05"}
66
+ {"current_steps": 650, "total_steps": 1023, "loss": 0.6059, "learning_rate": 5e-06, "epoch": 1.9030724213606436, "percentage": 63.54, "elapsed_time": "9:33:41", "remaining_time": "5:29:12"}
67
+ {"current_steps": 660, "total_steps": 1023, "loss": 0.6064, "learning_rate": 5e-06, "epoch": 1.9323335771762986, "percentage": 64.52, "elapsed_time": "9:42:23", "remaining_time": "5:20:19"}
68
+ {"current_steps": 670, "total_steps": 1023, "loss": 0.5953, "learning_rate": 5e-06, "epoch": 1.9615947329919532, "percentage": 65.49, "elapsed_time": "9:51:05", "remaining_time": "5:11:25"}
69
+ {"current_steps": 680, "total_steps": 1023, "loss": 0.6098, "learning_rate": 5e-06, "epoch": 1.9908558888076078, "percentage": 66.47, "elapsed_time": "9:59:49", "remaining_time": "5:02:33"}
70
+ {"current_steps": 682, "total_steps": 1023, "eval_loss": 0.6332319378852844, "epoch": 1.9967081199707388, "percentage": 66.67, "elapsed_time": "10:07:54", "remaining_time": "5:03:57"}