Hugging Face's logo

mlfoundations-dev
/
OH_original_wo_cot_alpaca

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
16bfd7b
•
1 Parent(s): 62db6ed

Training in progress, epoch 1

Browse files
Files changed (13) hide show
  1. model-00001-of-00004.safetensors +1 -1
  2. model-00001-of-00004.safetensors.sagemaker-uploaded +0 -0
  3. model-00002-of-00004.safetensors +1 -1
  4. model-00002-of-00004.safetensors.sagemaker-uploaded +0 -0
  5. model-00003-of-00004.safetensors +1 -1
  6. model-00003-of-00004.safetensors.sagemaker-uploaded +0 -0
  7. model-00004-of-00004.safetensors +1 -1
  8. model-00004-of-00004.safetensors.sagemaker-uploaded +0 -0
  9. special_tokens_map.json.sagemaker-uploaded +0 -0
  10. tokenizer.json.sagemaker-uploaded +0 -0
  11. tokenizer_config.json.sagemaker-uploaded +0 -0
  12. trainer_log.jsonl +34 -0
  13. training_args.bin.sagemaker-uploaded +0 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eccc3ae12511dc23170e3783eae1f139e1a6687e873cc323284a1801d1a0da17
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:057206701d62c0c59d953a233b36f93174b36fcf7e0afd4e761a6228150f21f2
3
  size 4976698672
model-00001-of-00004.safetensors.sagemaker-uploaded ADDED
File without changes
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48af1d5cd63ff1f312c7dca40700aa62f7f71f9dd5a32b08befc1b75cf5dc015
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6b5ff288d81bf477881a93bf69009391023a631777a40bf69a7d1827d27ee2e
3
  size 4999802720
model-00002-of-00004.safetensors.sagemaker-uploaded ADDED
File without changes
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c042171d994f812fed8d11f60d114421d2fa37346b2b81e4bb02502a171b58d7
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f03af56fc3843d6b61b62bbea3cd89d7e0ceb84f80aa75904cea3468dc92c1ad
3
  size 4915916176
model-00003-of-00004.safetensors.sagemaker-uploaded ADDED
File without changes
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f19a808820b3d3f8f9005bdb6ef7b09fb9cb145e083324799edb05ff93dd619
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bc939ee78ac3fbf4e67adfe1ee28122e53061c502d22d539723e3e8b69e56bf
3
  size 1168138808
model-00004-of-00004.safetensors.sagemaker-uploaded ADDED
File without changes
special_tokens_map.json.sagemaker-uploaded ADDED
File without changes
tokenizer.json.sagemaker-uploaded ADDED
File without changes
tokenizer_config.json.sagemaker-uploaded ADDED
File without changes
trainer_log.jsonl CHANGED
@@ -33,3 +33,37 @@
33
  {"current_steps": 330, "total_steps": 996, "loss": 0.6024, "learning_rate": 5e-06, "epoch": 0.9917355371900827, "percentage": 33.13, "elapsed_time": "1:30:23", "remaining_time": "3:02:25"}
34
  {"current_steps": 332, "total_steps": 996, "eval_loss": 0.602512001991272, "epoch": 0.9977460555972952, "percentage": 33.33, "elapsed_time": "1:33:03", "remaining_time": "3:06:06"}
35
  {"current_steps": 340, "total_steps": 996, "loss": 0.5718, "learning_rate": 5e-06, "epoch": 1.0217881292261457, "percentage": 34.14, "elapsed_time": "1:36:00", "remaining_time": "3:05:15"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  {"current_steps": 330, "total_steps": 996, "loss": 0.6024, "learning_rate": 5e-06, "epoch": 0.9917355371900827, "percentage": 33.13, "elapsed_time": "1:30:23", "remaining_time": "3:02:25"}
34
  {"current_steps": 332, "total_steps": 996, "eval_loss": 0.602512001991272, "epoch": 0.9977460555972952, "percentage": 33.33, "elapsed_time": "1:33:03", "remaining_time": "3:06:06"}
35
  {"current_steps": 340, "total_steps": 996, "loss": 0.5718, "learning_rate": 5e-06, "epoch": 1.0217881292261457, "percentage": 34.14, "elapsed_time": "1:36:00", "remaining_time": "3:05:15"}
36
+ {"current_steps": 350, "total_steps": 996, "loss": 0.5559, "learning_rate": 5e-06, "epoch": 1.051840721262209, "percentage": 35.14, "elapsed_time": "1:38:45", "remaining_time": "3:02:15"}
37
+ {"current_steps": 360, "total_steps": 996, "loss": 0.5565, "learning_rate": 5e-06, "epoch": 1.081893313298272, "percentage": 36.14, "elapsed_time": "1:41:27", "remaining_time": "2:59:15"}
38
+ {"current_steps": 370, "total_steps": 996, "loss": 0.5559, "learning_rate": 5e-06, "epoch": 1.111945905334335, "percentage": 37.15, "elapsed_time": "1:44:09", "remaining_time": "2:56:14"}
39
+ {"current_steps": 380, "total_steps": 996, "loss": 0.5548, "learning_rate": 5e-06, "epoch": 1.1419984973703983, "percentage": 38.15, "elapsed_time": "1:46:53", "remaining_time": "2:53:15"}
40
+ {"current_steps": 390, "total_steps": 996, "loss": 0.5616, "learning_rate": 5e-06, "epoch": 1.1720510894064613, "percentage": 39.16, "elapsed_time": "1:49:36", "remaining_time": "2:50:19"}
41
+ {"current_steps": 400, "total_steps": 996, "loss": 0.553, "learning_rate": 5e-06, "epoch": 1.2021036814425243, "percentage": 40.16, "elapsed_time": "1:52:20", "remaining_time": "2:47:23"}
42
+ {"current_steps": 410, "total_steps": 996, "loss": 0.5534, "learning_rate": 5e-06, "epoch": 1.2321562734785876, "percentage": 41.16, "elapsed_time": "1:55:03", "remaining_time": "2:44:27"}
43
+ {"current_steps": 420, "total_steps": 996, "loss": 0.5596, "learning_rate": 5e-06, "epoch": 1.2622088655146506, "percentage": 42.17, "elapsed_time": "1:57:47", "remaining_time": "2:41:32"}
44
+ {"current_steps": 430, "total_steps": 996, "loss": 0.5559, "learning_rate": 5e-06, "epoch": 1.2922614575507136, "percentage": 43.17, "elapsed_time": "2:00:30", "remaining_time": "2:38:37"}
45
+ {"current_steps": 440, "total_steps": 996, "loss": 0.559, "learning_rate": 5e-06, "epoch": 1.322314049586777, "percentage": 44.18, "elapsed_time": "2:03:16", "remaining_time": "2:35:46"}
46
+ {"current_steps": 450, "total_steps": 996, "loss": 0.559, "learning_rate": 5e-06, "epoch": 1.35236664162284, "percentage": 45.18, "elapsed_time": "2:06:01", "remaining_time": "2:32:54"}
47
+ {"current_steps": 460, "total_steps": 996, "loss": 0.5552, "learning_rate": 5e-06, "epoch": 1.382419233658903, "percentage": 46.18, "elapsed_time": "2:08:44", "remaining_time": "2:30:01"}
48
+ {"current_steps": 470, "total_steps": 996, "loss": 0.5562, "learning_rate": 5e-06, "epoch": 1.4124718256949662, "percentage": 47.19, "elapsed_time": "2:11:29", "remaining_time": "2:27:09"}
49
+ {"current_steps": 480, "total_steps": 996, "loss": 0.5444, "learning_rate": 5e-06, "epoch": 1.4425244177310292, "percentage": 48.19, "elapsed_time": "2:14:15", "remaining_time": "2:24:19"}
50
+ {"current_steps": 490, "total_steps": 996, "loss": 0.553, "learning_rate": 5e-06, "epoch": 1.4725770097670925, "percentage": 49.2, "elapsed_time": "2:16:59", "remaining_time": "2:21:28"}
51
+ {"current_steps": 500, "total_steps": 996, "loss": 0.5615, "learning_rate": 5e-06, "epoch": 1.5026296018031555, "percentage": 50.2, "elapsed_time": "2:19:43", "remaining_time": "2:18:36"}
52
+ {"current_steps": 510, "total_steps": 996, "loss": 0.5588, "learning_rate": 5e-06, "epoch": 1.5326821938392188, "percentage": 51.2, "elapsed_time": "2:22:26", "remaining_time": "2:15:44"}
53
+ {"current_steps": 520, "total_steps": 996, "loss": 0.5515, "learning_rate": 5e-06, "epoch": 1.5627347858752816, "percentage": 52.21, "elapsed_time": "2:25:08", "remaining_time": "2:12:51"}
54
+ {"current_steps": 530, "total_steps": 996, "loss": 0.5602, "learning_rate": 5e-06, "epoch": 1.5927873779113448, "percentage": 53.21, "elapsed_time": "2:27:52", "remaining_time": "2:10:01"}
55
+ {"current_steps": 540, "total_steps": 996, "loss": 0.5687, "learning_rate": 5e-06, "epoch": 1.622839969947408, "percentage": 54.22, "elapsed_time": "2:30:37", "remaining_time": "2:07:11"}
56
+ {"current_steps": 550, "total_steps": 996, "loss": 0.5522, "learning_rate": 5e-06, "epoch": 1.6528925619834711, "percentage": 55.22, "elapsed_time": "2:33:21", "remaining_time": "2:04:21"}
57
+ {"current_steps": 560, "total_steps": 996, "loss": 0.5539, "learning_rate": 5e-06, "epoch": 1.6829451540195342, "percentage": 56.22, "elapsed_time": "2:36:06", "remaining_time": "2:01:32"}
58
+ {"current_steps": 570, "total_steps": 996, "loss": 0.5486, "learning_rate": 5e-06, "epoch": 1.7129977460555974, "percentage": 57.23, "elapsed_time": "2:38:51", "remaining_time": "1:58:43"}
59
+ {"current_steps": 580, "total_steps": 996, "loss": 0.5515, "learning_rate": 5e-06, "epoch": 1.7430503380916604, "percentage": 58.23, "elapsed_time": "2:41:34", "remaining_time": "1:55:53"}
60
+ {"current_steps": 590, "total_steps": 996, "loss": 0.5529, "learning_rate": 5e-06, "epoch": 1.7731029301277235, "percentage": 59.24, "elapsed_time": "2:44:17", "remaining_time": "1:53:03"}
61
+ {"current_steps": 600, "total_steps": 996, "loss": 0.5563, "learning_rate": 5e-06, "epoch": 1.8031555221637867, "percentage": 60.24, "elapsed_time": "2:47:00", "remaining_time": "1:50:13"}
62
+ {"current_steps": 610, "total_steps": 996, "loss": 0.5548, "learning_rate": 5e-06, "epoch": 1.8332081141998497, "percentage": 61.24, "elapsed_time": "2:49:44", "remaining_time": "1:47:24"}
63
+ {"current_steps": 620, "total_steps": 996, "loss": 0.5517, "learning_rate": 5e-06, "epoch": 1.8632607062359128, "percentage": 62.25, "elapsed_time": "2:52:28", "remaining_time": "1:44:36"}
64
+ {"current_steps": 630, "total_steps": 996, "loss": 0.5566, "learning_rate": 5e-06, "epoch": 1.893313298271976, "percentage": 63.25, "elapsed_time": "2:55:13", "remaining_time": "1:41:47"}
65
+ {"current_steps": 640, "total_steps": 996, "loss": 0.5565, "learning_rate": 5e-06, "epoch": 1.923365890308039, "percentage": 64.26, "elapsed_time": "2:57:56", "remaining_time": "1:38:58"}
66
+ {"current_steps": 650, "total_steps": 996, "loss": 0.5543, "learning_rate": 5e-06, "epoch": 1.953418482344102, "percentage": 65.26, "elapsed_time": "3:00:39", "remaining_time": "1:36:10"}
67
+ {"current_steps": 660, "total_steps": 996, "loss": 0.5526, "learning_rate": 5e-06, "epoch": 1.9834710743801653, "percentage": 66.27, "elapsed_time": "3:03:22", "remaining_time": "1:33:21"}
68
+ {"current_steps": 665, "total_steps": 996, "eval_loss": 0.5943902730941772, "epoch": 1.998497370398197, "percentage": 66.77, "elapsed_time": "3:06:47", "remaining_time": "1:32:58"}
69
+ {"current_steps": 670, "total_steps": 996, "loss": 0.5296, "learning_rate": 5e-06, "epoch": 2.0135236664162286, "percentage": 67.27, "elapsed_time": "3:09:06", "remaining_time": "1:32:01"}
training_args.bin.sagemaker-uploaded ADDED
File without changes