Hugging Face's logo

mlfoundations-dev
/
oh_v1.3_camel_math_x2

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
sedrickkeh commited on
Commit
c85c040
·
verified ·
1 Parent(s): aa07270

Training in progress, epoch 2

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 +30 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c00c78626761b7857a6c762b4490502825b9f32acb17f9f7da7857d2b404d10
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcc494c6530a3f10e8c9ae0c1563ca0d60651a6031f0b8393c16d1c1d7353eb8
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:917b14250ada4bbe9328d25596d8c1bc3637ebf66da74c2327070f4ab64c6b5e
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc6d849bc0e5b1f0a49d5d5ad0c92be4f6ad5771f6fcbb781e25350fbb9ca9c7
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07f08f7718c7ef4168210053521dfc45da118c0a6950e8485dc5e8361b275002
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbc1c7869c15b35a66df791ccbf72298ff9c3b2cc2b8ffbe5b0e6d5e21c0aff3
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:94f6474b0c16a552d4016412803244ef45beee98ffd2fb999af804f04dc6da28
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0c9e54f365fd0633331d6b896f0552cc48bb592709df54429bf47806d5275cd
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -28,3 +28,33 @@
28
  {"current_steps": 280, "total_steps": 870, "loss": 0.7281, "lr": 5e-06, "epoch": 0.963855421686747, "percentage": 32.18, "elapsed_time": "4:29:13", "remaining_time": "9:27:17"}
29
  {"current_steps": 290, "total_steps": 870, "loss": 0.73, "lr": 5e-06, "epoch": 0.9982788296041308, "percentage": 33.33, "elapsed_time": "4:38:49", "remaining_time": "9:17:38"}
30
  {"current_steps": 290, "total_steps": 870, "eval_loss": 0.7240723967552185, "epoch": 0.9982788296041308, "percentage": 33.33, "elapsed_time": "4:44:28", "remaining_time": "9:28:57"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28
  {"current_steps": 280, "total_steps": 870, "loss": 0.7281, "lr": 5e-06, "epoch": 0.963855421686747, "percentage": 32.18, "elapsed_time": "4:29:13", "remaining_time": "9:27:17"}
29
  {"current_steps": 290, "total_steps": 870, "loss": 0.73, "lr": 5e-06, "epoch": 0.9982788296041308, "percentage": 33.33, "elapsed_time": "4:38:49", "remaining_time": "9:17:38"}
30
  {"current_steps": 290, "total_steps": 870, "eval_loss": 0.7240723967552185, "epoch": 0.9982788296041308, "percentage": 33.33, "elapsed_time": "4:44:28", "remaining_time": "9:28:57"}
31
+ {"current_steps": 300, "total_steps": 870, "loss": 0.7164, "lr": 5e-06, "epoch": 1.0327022375215147, "percentage": 34.48, "elapsed_time": "4:54:50", "remaining_time": "9:20:12"}
32
+ {"current_steps": 310, "total_steps": 870, "loss": 0.6796, "lr": 5e-06, "epoch": 1.0671256454388984, "percentage": 35.63, "elapsed_time": "5:04:29", "remaining_time": "9:10:02"}
33
+ {"current_steps": 320, "total_steps": 870, "loss": 0.6731, "lr": 5e-06, "epoch": 1.1015490533562822, "percentage": 36.78, "elapsed_time": "5:14:07", "remaining_time": "8:59:54"}
34
+ {"current_steps": 330, "total_steps": 870, "loss": 0.6804, "lr": 5e-06, "epoch": 1.1359724612736661, "percentage": 37.93, "elapsed_time": "5:23:46", "remaining_time": "8:49:49"}
35
+ {"current_steps": 340, "total_steps": 870, "loss": 0.676, "lr": 5e-06, "epoch": 1.1703958691910499, "percentage": 39.08, "elapsed_time": "5:33:25", "remaining_time": "8:39:44"}
36
+ {"current_steps": 350, "total_steps": 870, "loss": 0.6758, "lr": 5e-06, "epoch": 1.2048192771084336, "percentage": 40.23, "elapsed_time": "5:43:03", "remaining_time": "8:29:41"}
37
+ {"current_steps": 360, "total_steps": 870, "loss": 0.6812, "lr": 5e-06, "epoch": 1.2392426850258176, "percentage": 41.38, "elapsed_time": "5:52:42", "remaining_time": "8:19:40"}
38
+ {"current_steps": 370, "total_steps": 870, "loss": 0.6829, "lr": 5e-06, "epoch": 1.2736660929432013, "percentage": 42.53, "elapsed_time": "6:02:21", "remaining_time": "8:09:40"}
39
+ {"current_steps": 380, "total_steps": 870, "loss": 0.6787, "lr": 5e-06, "epoch": 1.3080895008605853, "percentage": 43.68, "elapsed_time": "6:11:59", "remaining_time": "7:59:40"}
40
+ {"current_steps": 390, "total_steps": 870, "loss": 0.6793, "lr": 5e-06, "epoch": 1.342512908777969, "percentage": 44.83, "elapsed_time": "6:21:37", "remaining_time": "7:49:41"}
41
+ {"current_steps": 400, "total_steps": 870, "loss": 0.6774, "lr": 5e-06, "epoch": 1.3769363166953528, "percentage": 45.98, "elapsed_time": "6:31:16", "remaining_time": "7:39:44"}
42
+ {"current_steps": 410, "total_steps": 870, "loss": 0.6812, "lr": 5e-06, "epoch": 1.4113597246127367, "percentage": 47.13, "elapsed_time": "6:40:53", "remaining_time": "7:29:46"}
43
+ {"current_steps": 420, "total_steps": 870, "loss": 0.6747, "lr": 5e-06, "epoch": 1.4457831325301205, "percentage": 48.28, "elapsed_time": "6:50:32", "remaining_time": "7:19:51"}
44
+ {"current_steps": 430, "total_steps": 870, "loss": 0.6764, "lr": 5e-06, "epoch": 1.4802065404475044, "percentage": 49.43, "elapsed_time": "7:00:11", "remaining_time": "7:09:57"}
45
+ {"current_steps": 440, "total_steps": 870, "loss": 0.6744, "lr": 5e-06, "epoch": 1.5146299483648882, "percentage": 50.57, "elapsed_time": "7:09:49", "remaining_time": "7:00:03"}
46
+ {"current_steps": 450, "total_steps": 870, "loss": 0.6728, "lr": 5e-06, "epoch": 1.549053356282272, "percentage": 51.72, "elapsed_time": "7:19:27", "remaining_time": "6:50:09"}
47
+ {"current_steps": 460, "total_steps": 870, "loss": 0.6761, "lr": 5e-06, "epoch": 1.5834767641996557, "percentage": 52.87, "elapsed_time": "7:29:05", "remaining_time": "6:40:16"}
48
+ {"current_steps": 470, "total_steps": 870, "loss": 0.6792, "lr": 5e-06, "epoch": 1.6179001721170396, "percentage": 54.02, "elapsed_time": "7:38:43", "remaining_time": "6:30:24"}
49
+ {"current_steps": 480, "total_steps": 870, "loss": 0.6768, "lr": 5e-06, "epoch": 1.6523235800344234, "percentage": 55.17, "elapsed_time": "7:48:22", "remaining_time": "6:20:33"}
50
+ {"current_steps": 490, "total_steps": 870, "loss": 0.677, "lr": 5e-06, "epoch": 1.6867469879518073, "percentage": 56.32, "elapsed_time": "7:58:00", "remaining_time": "6:10:41"}
51
+ {"current_steps": 500, "total_steps": 870, "loss": 0.6799, "lr": 5e-06, "epoch": 1.721170395869191, "percentage": 57.47, "elapsed_time": "8:07:38", "remaining_time": "6:00:51"}
52
+ {"current_steps": 510, "total_steps": 870, "loss": 0.6773, "lr": 5e-06, "epoch": 1.7555938037865748, "percentage": 58.62, "elapsed_time": "8:17:16", "remaining_time": "5:51:00"}
53
+ {"current_steps": 520, "total_steps": 870, "loss": 0.6761, "lr": 5e-06, "epoch": 1.7900172117039586, "percentage": 59.77, "elapsed_time": "8:26:54", "remaining_time": "5:41:11"}
54
+ {"current_steps": 530, "total_steps": 870, "loss": 0.6736, "lr": 5e-06, "epoch": 1.8244406196213425, "percentage": 60.92, "elapsed_time": "8:36:32", "remaining_time": "5:31:22"}
55
+ {"current_steps": 540, "total_steps": 870, "loss": 0.6724, "lr": 5e-06, "epoch": 1.8588640275387265, "percentage": 62.07, "elapsed_time": "8:46:11", "remaining_time": "5:21:33"}
56
+ {"current_steps": 550, "total_steps": 870, "loss": 0.6745, "lr": 5e-06, "epoch": 1.8932874354561102, "percentage": 63.22, "elapsed_time": "8:55:49", "remaining_time": "5:11:44"}
57
+ {"current_steps": 560, "total_steps": 870, "loss": 0.6744, "lr": 5e-06, "epoch": 1.927710843373494, "percentage": 64.37, "elapsed_time": "9:05:26", "remaining_time": "5:01:56"}
58
+ {"current_steps": 570, "total_steps": 870, "loss": 0.6755, "lr": 5e-06, "epoch": 1.9621342512908777, "percentage": 65.52, "elapsed_time": "9:15:04", "remaining_time": "4:52:08"}
59
+ {"current_steps": 580, "total_steps": 870, "loss": 0.6787, "lr": 5e-06, "epoch": 1.9965576592082617, "percentage": 66.67, "elapsed_time": "9:24:41", "remaining_time": "4:42:20"}
60
+ {"current_steps": 581, "total_steps": 870, "eval_loss": 0.7113586664199829, "epoch": 2.0, "percentage": 66.78, "elapsed_time": "9:30:46", "remaining_time": "4:43:54"}