Hugging Face's logo

mlfoundations-dev
/
OH_original_wo_gpt4_llm

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
c5bb390
•
1 Parent(s): 03bf6e0

Training in progress, epoch 2

Browse files
Files changed (14) 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. model.safetensors.index.json.sagemaker-uploaded +0 -0
  10. special_tokens_map.json.sagemaker-uploaded +0 -0
  11. tokenizer.json.sagemaker-uploaded +0 -0
  12. tokenizer_config.json.sagemaker-uploaded +0 -0
  13. trainer_log.jsonl +35 -0
  14. 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 sha256:92f13fd9e8df1121edbac74cdba6d5160f11a8230286ad557fa40d3b79e1273f
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6176883e169a945e453837134d51f29148dbc77ad3b52fd09d05461ed61cb63d
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 sha256:2fed9e7f8a169bc8c579a9b673c90b817c68fbce36dcd5b786b88e0260b6b466
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89456a61867544fa85b673c2b864c16bc004a177f7d059037351e7cd871f3b3d
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:e6e4a66880110d0c65ed70fb9ac12b43a2738671f74b5615867993df7d1cfe91
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b47e1ab9136b4363bc65786d00001dcc437722e64ceb00b6f5b86471c8d18af
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 sha256:44ac9349ce10f0a57dcf7d9e1cc754f466c566092f32ffdc37c5d609dd8609a1
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d6a81ab513214aeb9d017727c3f6153db07432387a3ba08feb315162d39baae
3
  size 1168138808
model-00004-of-00004.safetensors.sagemaker-uploaded ADDED
File without changes
model.safetensors.index.json.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
@@ -32,3 +32,38 @@
32
  {"current_steps": 320, "total_steps": 996, "loss": 0.6128, "learning_rate": 5e-06, "epoch": 0.9624060150375939, "percentage": 32.13, "elapsed_time": "1:30:37", "remaining_time": "3:11:26"}
33
  {"current_steps": 330, "total_steps": 996, "loss": 0.6043, "learning_rate": 5e-06, "epoch": 0.9924812030075187, "percentage": 33.13, "elapsed_time": "1:33:27", "remaining_time": "3:08:36"}
34
  {"current_steps": 332, "total_steps": 996, "eval_loss": 0.6096732020378113, "epoch": 0.9984962406015038, "percentage": 33.33, "elapsed_time": "1:36:05", "remaining_time": "3:12:11"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
32
  {"current_steps": 320, "total_steps": 996, "loss": 0.6128, "learning_rate": 5e-06, "epoch": 0.9624060150375939, "percentage": 32.13, "elapsed_time": "1:30:37", "remaining_time": "3:11:26"}
33
  {"current_steps": 330, "total_steps": 996, "loss": 0.6043, "learning_rate": 5e-06, "epoch": 0.9924812030075187, "percentage": 33.13, "elapsed_time": "1:33:27", "remaining_time": "3:08:36"}
34
  {"current_steps": 332, "total_steps": 996, "eval_loss": 0.6096732020378113, "epoch": 0.9984962406015038, "percentage": 33.33, "elapsed_time": "1:36:05", "remaining_time": "3:12:11"}
35
+ {"current_steps": 340, "total_steps": 996, "loss": 0.58, "learning_rate": 5e-06, "epoch": 1.0225563909774436, "percentage": 34.14, "elapsed_time": "1:39:11", "remaining_time": "3:11:23"}
36
+ {"current_steps": 350, "total_steps": 996, "loss": 0.5596, "learning_rate": 5e-06, "epoch": 1.0526315789473684, "percentage": 35.14, "elapsed_time": "1:42:00", "remaining_time": "3:08:17"}
37
+ {"current_steps": 360, "total_steps": 996, "loss": 0.5591, "learning_rate": 5e-06, "epoch": 1.0827067669172932, "percentage": 36.14, "elapsed_time": "1:44:49", "remaining_time": "3:05:11"}
38
+ {"current_steps": 370, "total_steps": 996, "loss": 0.5553, "learning_rate": 5e-06, "epoch": 1.112781954887218, "percentage": 37.15, "elapsed_time": "1:47:38", "remaining_time": "3:02:07"}
39
+ {"current_steps": 380, "total_steps": 996, "loss": 0.5564, "learning_rate": 5e-06, "epoch": 1.1428571428571428, "percentage": 38.15, "elapsed_time": "1:50:27", "remaining_time": "2:59:02"}
40
+ {"current_steps": 390, "total_steps": 996, "loss": 0.5605, "learning_rate": 5e-06, "epoch": 1.1729323308270676, "percentage": 39.16, "elapsed_time": "1:53:15", "remaining_time": "2:55:59"}
41
+ {"current_steps": 400, "total_steps": 996, "loss": 0.5519, "learning_rate": 5e-06, "epoch": 1.2030075187969924, "percentage": 40.16, "elapsed_time": "1:56:04", "remaining_time": "2:52:57"}
42
+ {"current_steps": 410, "total_steps": 996, "loss": 0.5574, "learning_rate": 5e-06, "epoch": 1.2330827067669172, "percentage": 41.16, "elapsed_time": "1:58:53", "remaining_time": "2:49:55"}
43
+ {"current_steps": 420, "total_steps": 996, "loss": 0.5541, "learning_rate": 5e-06, "epoch": 1.263157894736842, "percentage": 42.17, "elapsed_time": "2:01:42", "remaining_time": "2:46:54"}
44
+ {"current_steps": 430, "total_steps": 996, "loss": 0.5582, "learning_rate": 5e-06, "epoch": 1.2932330827067668, "percentage": 43.17, "elapsed_time": "2:04:30", "remaining_time": "2:43:53"}
45
+ {"current_steps": 440, "total_steps": 996, "loss": 0.5532, "learning_rate": 5e-06, "epoch": 1.3233082706766917, "percentage": 44.18, "elapsed_time": "2:07:18", "remaining_time": "2:40:52"}
46
+ {"current_steps": 450, "total_steps": 996, "loss": 0.5571, "learning_rate": 5e-06, "epoch": 1.3533834586466165, "percentage": 45.18, "elapsed_time": "2:10:05", "remaining_time": "2:37:50"}
47
+ {"current_steps": 460, "total_steps": 996, "loss": 0.5487, "learning_rate": 5e-06, "epoch": 1.3834586466165413, "percentage": 46.18, "elapsed_time": "2:12:52", "remaining_time": "2:34:49"}
48
+ {"current_steps": 470, "total_steps": 996, "loss": 0.5586, "learning_rate": 5e-06, "epoch": 1.413533834586466, "percentage": 47.19, "elapsed_time": "2:15:40", "remaining_time": "2:31:50"}
49
+ {"current_steps": 480, "total_steps": 996, "loss": 0.5528, "learning_rate": 5e-06, "epoch": 1.443609022556391, "percentage": 48.19, "elapsed_time": "2:18:28", "remaining_time": "2:28:51"}
50
+ {"current_steps": 490, "total_steps": 996, "loss": 0.5624, "learning_rate": 5e-06, "epoch": 1.4736842105263157, "percentage": 49.2, "elapsed_time": "2:21:15", "remaining_time": "2:25:52"}
51
+ {"current_steps": 500, "total_steps": 996, "loss": 0.5565, "learning_rate": 5e-06, "epoch": 1.5037593984962405, "percentage": 50.2, "elapsed_time": "2:24:03", "remaining_time": "2:22:54"}
52
+ {"current_steps": 510, "total_steps": 996, "loss": 0.5587, "learning_rate": 5e-06, "epoch": 1.5338345864661656, "percentage": 51.2, "elapsed_time": "2:26:50", "remaining_time": "2:19:55"}
53
+ {"current_steps": 520, "total_steps": 996, "loss": 0.5493, "learning_rate": 5e-06, "epoch": 1.5639097744360901, "percentage": 52.21, "elapsed_time": "2:29:38", "remaining_time": "2:16:59"}
54
+ {"current_steps": 530, "total_steps": 996, "loss": 0.5603, "learning_rate": 5e-06, "epoch": 1.5939849624060152, "percentage": 53.21, "elapsed_time": "2:32:27", "remaining_time": "2:14:02"}
55
+ {"current_steps": 540, "total_steps": 996, "loss": 0.5564, "learning_rate": 5e-06, "epoch": 1.6240601503759398, "percentage": 54.22, "elapsed_time": "2:35:15", "remaining_time": "2:11:06"}
56
+ {"current_steps": 550, "total_steps": 996, "loss": 0.5605, "learning_rate": 5e-06, "epoch": 1.6541353383458648, "percentage": 55.22, "elapsed_time": "2:38:04", "remaining_time": "2:08:10"}
57
+ {"current_steps": 560, "total_steps": 996, "loss": 0.5601, "learning_rate": 5e-06, "epoch": 1.6842105263157894, "percentage": 56.22, "elapsed_time": "2:40:52", "remaining_time": "2:05:15"}
58
+ {"current_steps": 570, "total_steps": 996, "loss": 0.5554, "learning_rate": 5e-06, "epoch": 1.7142857142857144, "percentage": 57.23, "elapsed_time": "2:43:41", "remaining_time": "2:02:20"}
59
+ {"current_steps": 580, "total_steps": 996, "loss": 0.5645, "learning_rate": 5e-06, "epoch": 1.744360902255639, "percentage": 58.23, "elapsed_time": "2:46:28", "remaining_time": "1:59:24"}
60
+ {"current_steps": 590, "total_steps": 996, "loss": 0.5536, "learning_rate": 5e-06, "epoch": 1.774436090225564, "percentage": 59.24, "elapsed_time": "2:49:16", "remaining_time": "1:56:29"}
61
+ {"current_steps": 600, "total_steps": 996, "loss": 0.5625, "learning_rate": 5e-06, "epoch": 1.8045112781954886, "percentage": 60.24, "elapsed_time": "2:52:04", "remaining_time": "1:53:34"}
62
+ {"current_steps": 610, "total_steps": 996, "loss": 0.554, "learning_rate": 5e-06, "epoch": 1.8345864661654137, "percentage": 61.24, "elapsed_time": "2:54:53", "remaining_time": "1:50:40"}
63
+ {"current_steps": 620, "total_steps": 996, "loss": 0.5529, "learning_rate": 5e-06, "epoch": 1.8646616541353382, "percentage": 62.25, "elapsed_time": "2:57:42", "remaining_time": "1:47:46"}
64
+ {"current_steps": 630, "total_steps": 996, "loss": 0.547, "learning_rate": 5e-06, "epoch": 1.8947368421052633, "percentage": 63.25, "elapsed_time": "3:00:31", "remaining_time": "1:44:52"}
65
+ {"current_steps": 640, "total_steps": 996, "loss": 0.5508, "learning_rate": 5e-06, "epoch": 1.9248120300751879, "percentage": 64.26, "elapsed_time": "3:03:18", "remaining_time": "1:41:58"}
66
+ {"current_steps": 650, "total_steps": 996, "loss": 0.5626, "learning_rate": 5e-06, "epoch": 1.954887218045113, "percentage": 65.26, "elapsed_time": "3:06:05", "remaining_time": "1:39:03"}
67
+ {"current_steps": 660, "total_steps": 996, "loss": 0.5579, "learning_rate": 5e-06, "epoch": 1.9849624060150375, "percentage": 66.27, "elapsed_time": "3:08:52", "remaining_time": "1:36:09"}
68
+ {"current_steps": 665, "total_steps": 996, "eval_loss": 0.6012639403343201, "epoch": 2.0, "percentage": 66.77, "elapsed_time": "3:12:11", "remaining_time": "1:35:39"}
69
+ {"current_steps": 670, "total_steps": 996, "loss": 0.5349, "learning_rate": 5e-06, "epoch": 2.0150375939849625, "percentage": 67.27, "elapsed_time": "3:14:41", "remaining_time": "1:34:43"}
training_args.bin.sagemaker-uploaded ADDED
File without changes