Hugging Face's logo

mlfoundations-dev
/
OH_original_wo_null_sources

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
53d5b30
•
1 Parent(s): 444d77b

Training in progress, epoch 2

Browse files
Files changed (15) hide show
  1. config.json.sagemaker-uploaded +0 -0
  2. model-00001-of-00004.safetensors +1 -1
  3. model-00001-of-00004.safetensors.sagemaker-uploaded +0 -0
  4. model-00002-of-00004.safetensors +1 -1
  5. model-00002-of-00004.safetensors.sagemaker-uploaded +0 -0
  6. model-00003-of-00004.safetensors +1 -1
  7. model-00003-of-00004.safetensors.sagemaker-uploaded +0 -0
  8. model-00004-of-00004.safetensors +1 -1
  9. model-00004-of-00004.safetensors.sagemaker-uploaded +0 -0
  10. model.safetensors.index.json.sagemaker-uploaded +0 -0
  11. special_tokens_map.json.sagemaker-uploaded +0 -0
  12. tokenizer.json.sagemaker-uploaded +0 -0
  13. tokenizer_config.json.sagemaker-uploaded +0 -0
  14. trainer_log.jsonl +32 -0
  15. training_args.bin.sagemaker-uploaded +0 -0
config.json.sagemaker-uploaded ADDED
File without changes
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:832c283a746be7a741a01be4fcd9598a4fd48ac7326dab83d667fdaf6ce317e8
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a803e0a81b47991e397e723397c7aa71743c981da3e932249fa45c6ceab88417
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 sha256:7b397349adbe124f9a416ce66a91a8fe769c7e5ddbd067f809021334c747b145
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b193c1dfe8510f84742c52cc0d51daed500cf53e73f6ad7a36b8fc798809812
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 sha256:8b7781f1eb491706237912570907efb6bfa84c234ef64f6e143fb743a030dec1
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a14a205bc7483cc4f8c314a3892b210744cd3506b8c53774fa3cac0d842f588
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:e33e2ed8a2749618c5d4c14f4439aa6621e2721b8253f0a1c357bc2bb51a00df
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7979e7d82c3a5f32261a8c65d55d02fa9b8ed711ea5da334a5cf48f490fc00fa
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
@@ -30,3 +30,35 @@
30
  {"current_steps": 300, "total_steps": 909, "loss": 0.6023, "learning_rate": 5e-06, "epoch": 0.9900990099009901, "percentage": 33.0, "elapsed_time": "0:43:53", "remaining_time": "1:29:06"}
31
  {"current_steps": 303, "total_steps": 909, "eval_loss": 0.6056193113327026, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:45:13", "remaining_time": "1:30:27"}
32
  {"current_steps": 310, "total_steps": 909, "loss": 0.5633, "learning_rate": 5e-06, "epoch": 1.023102310231023, "percentage": 34.1, "elapsed_time": "0:47:07", "remaining_time": "1:31:03"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
30
  {"current_steps": 300, "total_steps": 909, "loss": 0.6023, "learning_rate": 5e-06, "epoch": 0.9900990099009901, "percentage": 33.0, "elapsed_time": "0:43:53", "remaining_time": "1:29:06"}
31
  {"current_steps": 303, "total_steps": 909, "eval_loss": 0.6056193113327026, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:45:13", "remaining_time": "1:30:27"}
32
  {"current_steps": 310, "total_steps": 909, "loss": 0.5633, "learning_rate": 5e-06, "epoch": 1.023102310231023, "percentage": 34.1, "elapsed_time": "0:47:07", "remaining_time": "1:31:03"}
33
+ {"current_steps": 320, "total_steps": 909, "loss": 0.5606, "learning_rate": 5e-06, "epoch": 1.056105610561056, "percentage": 35.2, "elapsed_time": "0:48:34", "remaining_time": "1:29:24"}
34
+ {"current_steps": 330, "total_steps": 909, "loss": 0.5508, "learning_rate": 5e-06, "epoch": 1.0891089108910892, "percentage": 36.3, "elapsed_time": "0:50:01", "remaining_time": "1:27:46"}
35
+ {"current_steps": 340, "total_steps": 909, "loss": 0.5572, "learning_rate": 5e-06, "epoch": 1.1221122112211221, "percentage": 37.4, "elapsed_time": "0:51:28", "remaining_time": "1:26:08"}
36
+ {"current_steps": 350, "total_steps": 909, "loss": 0.555, "learning_rate": 5e-06, "epoch": 1.155115511551155, "percentage": 38.5, "elapsed_time": "0:52:55", "remaining_time": "1:24:31"}
37
+ {"current_steps": 360, "total_steps": 909, "loss": 0.5528, "learning_rate": 5e-06, "epoch": 1.188118811881188, "percentage": 39.6, "elapsed_time": "0:54:22", "remaining_time": "1:22:55"}
38
+ {"current_steps": 370, "total_steps": 909, "loss": 0.5591, "learning_rate": 5e-06, "epoch": 1.221122112211221, "percentage": 40.7, "elapsed_time": "0:55:49", "remaining_time": "1:21:19"}
39
+ {"current_steps": 380, "total_steps": 909, "loss": 0.5478, "learning_rate": 5e-06, "epoch": 1.2541254125412542, "percentage": 41.8, "elapsed_time": "0:57:17", "remaining_time": "1:19:45"}
40
+ {"current_steps": 390, "total_steps": 909, "loss": 0.553, "learning_rate": 5e-06, "epoch": 1.2871287128712872, "percentage": 42.9, "elapsed_time": "0:58:44", "remaining_time": "1:18:10"}
41
+ {"current_steps": 400, "total_steps": 909, "loss": 0.5498, "learning_rate": 5e-06, "epoch": 1.3201320132013201, "percentage": 44.0, "elapsed_time": "1:00:11", "remaining_time": "1:16:35"}
42
+ {"current_steps": 410, "total_steps": 909, "loss": 0.5502, "learning_rate": 5e-06, "epoch": 1.353135313531353, "percentage": 45.1, "elapsed_time": "1:01:38", "remaining_time": "1:15:01"}
43
+ {"current_steps": 420, "total_steps": 909, "loss": 0.5539, "learning_rate": 5e-06, "epoch": 1.386138613861386, "percentage": 46.2, "elapsed_time": "1:03:05", "remaining_time": "1:13:27"}
44
+ {"current_steps": 430, "total_steps": 909, "loss": 0.5489, "learning_rate": 5e-06, "epoch": 1.4191419141914192, "percentage": 47.3, "elapsed_time": "1:04:32", "remaining_time": "1:11:54"}
45
+ {"current_steps": 440, "total_steps": 909, "loss": 0.555, "learning_rate": 5e-06, "epoch": 1.4521452145214522, "percentage": 48.4, "elapsed_time": "1:05:59", "remaining_time": "1:10:20"}
46
+ {"current_steps": 450, "total_steps": 909, "loss": 0.5491, "learning_rate": 5e-06, "epoch": 1.4851485148514851, "percentage": 49.5, "elapsed_time": "1:07:27", "remaining_time": "1:08:48"}
47
+ {"current_steps": 460, "total_steps": 909, "loss": 0.5522, "learning_rate": 5e-06, "epoch": 1.5181518151815183, "percentage": 50.61, "elapsed_time": "1:08:54", "remaining_time": "1:07:15"}
48
+ {"current_steps": 470, "total_steps": 909, "loss": 0.5442, "learning_rate": 5e-06, "epoch": 1.551155115511551, "percentage": 51.71, "elapsed_time": "1:10:22", "remaining_time": "1:05:43"}
49
+ {"current_steps": 480, "total_steps": 909, "loss": 0.556, "learning_rate": 5e-06, "epoch": 1.5841584158415842, "percentage": 52.81, "elapsed_time": "1:11:49", "remaining_time": "1:04:11"}
50
+ {"current_steps": 490, "total_steps": 909, "loss": 0.5543, "learning_rate": 5e-06, "epoch": 1.6171617161716172, "percentage": 53.91, "elapsed_time": "1:13:17", "remaining_time": "1:02:40"}
51
+ {"current_steps": 500, "total_steps": 909, "loss": 0.5447, "learning_rate": 5e-06, "epoch": 1.6501650165016502, "percentage": 55.01, "elapsed_time": "1:14:45", "remaining_time": "1:01:09"}
52
+ {"current_steps": 510, "total_steps": 909, "loss": 0.5503, "learning_rate": 5e-06, "epoch": 1.6831683168316833, "percentage": 56.11, "elapsed_time": "1:16:13", "remaining_time": "0:59:37"}
53
+ {"current_steps": 520, "total_steps": 909, "loss": 0.5486, "learning_rate": 5e-06, "epoch": 1.716171617161716, "percentage": 57.21, "elapsed_time": "1:17:40", "remaining_time": "0:58:06"}
54
+ {"current_steps": 530, "total_steps": 909, "loss": 0.5526, "learning_rate": 5e-06, "epoch": 1.7491749174917492, "percentage": 58.31, "elapsed_time": "1:19:07", "remaining_time": "0:56:34"}
55
+ {"current_steps": 540, "total_steps": 909, "loss": 0.5501, "learning_rate": 5e-06, "epoch": 1.7821782178217822, "percentage": 59.41, "elapsed_time": "1:20:34", "remaining_time": "0:55:03"}
56
+ {"current_steps": 550, "total_steps": 909, "loss": 0.5466, "learning_rate": 5e-06, "epoch": 1.8151815181518152, "percentage": 60.51, "elapsed_time": "1:22:02", "remaining_time": "0:53:33"}
57
+ {"current_steps": 560, "total_steps": 909, "loss": 0.5513, "learning_rate": 5e-06, "epoch": 1.8481848184818483, "percentage": 61.61, "elapsed_time": "1:23:30", "remaining_time": "0:52:02"}
58
+ {"current_steps": 570, "total_steps": 909, "loss": 0.5391, "learning_rate": 5e-06, "epoch": 1.881188118811881, "percentage": 62.71, "elapsed_time": "1:24:58", "remaining_time": "0:50:32"}
59
+ {"current_steps": 580, "total_steps": 909, "loss": 0.5448, "learning_rate": 5e-06, "epoch": 1.9141914191419143, "percentage": 63.81, "elapsed_time": "1:26:26", "remaining_time": "0:49:01"}
60
+ {"current_steps": 590, "total_steps": 909, "loss": 0.549, "learning_rate": 5e-06, "epoch": 1.9471947194719472, "percentage": 64.91, "elapsed_time": "1:27:54", "remaining_time": "0:47:31"}
61
+ {"current_steps": 600, "total_steps": 909, "loss": 0.5515, "learning_rate": 5e-06, "epoch": 1.9801980198019802, "percentage": 66.01, "elapsed_time": "1:29:22", "remaining_time": "0:46:01"}
62
+ {"current_steps": 606, "total_steps": 909, "eval_loss": 0.5981757640838623, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:31:08", "remaining_time": "0:45:34"}
63
+ {"current_steps": 610, "total_steps": 909, "loss": 0.5238, "learning_rate": 5e-06, "epoch": 2.0132013201320134, "percentage": 67.11, "elapsed_time": "1:32:42", "remaining_time": "0:45:26"}
64
+ {"current_steps": 620, "total_steps": 909, "loss": 0.4914, "learning_rate": 5e-06, "epoch": 2.046204620462046, "percentage": 68.21, "elapsed_time": "1:34:09", "remaining_time": "0:43:53"}
training_args.bin.sagemaker-uploaded ADDED
File without changes