Hugging Face's logo

mlfoundations-dev
/
OH_DCFT_V3_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
0da9101
•
1 Parent(s): b92e2c1

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-uploading +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-uploading +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 +86 -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 sha256:305e40ab81d849f557c2a7c3cecf3a478f2bd1cb54682c20232fba18c6f50671
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87e7e281158cf4a30804a7571bc5e7179fcc72ec0fb5cf6970afe9a580c51a33
3
  size 4976698672
model-00001-of-00004.safetensors.sagemaker-uploading 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 sha256:07ace567a980b27950f50a5f99099c2919e9ece10b4e328521f8a5d388cdb772
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99e8c784b085e763f99a98a7b38775c4ccf81f665dc9194cfdc744f78c59635d
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 sha256:3ba20d46b4eb6688cac92852f674305abe4bc33ac9e4e387b04b5470464bf5f3
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f722d30850060f7ba0d02e79c7272c2dde6e89f6f6388f4b3149d3b3a64cbcd7
3
  size 4915916176
model-00003-of-00004.safetensors.sagemaker-uploading 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:c3577a15c4913113fca4cbca1658994d854a43b4134485ed6706a855cbad6e11
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84749fa42c2b966edb4f1c380f1e15637883f3b96b3115fd2ad734c1ae9aa64e
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
@@ -41,3 +41,89 @@
41
  {"current_steps": 410, "total_steps": 1254, "loss": 0.6443, "learning_rate": 5e-06, "epoch": 0.9791044776119403, "percentage": 32.7, "elapsed_time": "1:51:17", "remaining_time": "3:49:04"}
42
  {"current_steps": 418, "total_steps": 1254, "eval_loss": 0.6459853649139404, "epoch": 0.9982089552238806, "percentage": 33.33, "elapsed_time": "1:56:03", "remaining_time": "3:52:07"}
43
  {"current_steps": 420, "total_steps": 1254, "loss": 0.6464, "learning_rate": 5e-06, "epoch": 1.0029850746268656, "percentage": 33.49, "elapsed_time": "1:57:22", "remaining_time": "3:53:05"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
41
  {"current_steps": 410, "total_steps": 1254, "loss": 0.6443, "learning_rate": 5e-06, "epoch": 0.9791044776119403, "percentage": 32.7, "elapsed_time": "1:51:17", "remaining_time": "3:49:04"}
42
  {"current_steps": 418, "total_steps": 1254, "eval_loss": 0.6459853649139404, "epoch": 0.9982089552238806, "percentage": 33.33, "elapsed_time": "1:56:03", "remaining_time": "3:52:07"}
43
  {"current_steps": 420, "total_steps": 1254, "loss": 0.6464, "learning_rate": 5e-06, "epoch": 1.0029850746268656, "percentage": 33.49, "elapsed_time": "1:57:22", "remaining_time": "3:53:05"}
44
+ {"current_steps": 430, "total_steps": 1254, "loss": 0.6064, "learning_rate": 5e-06, "epoch": 1.026865671641791, "percentage": 34.29, "elapsed_time": "2:00:04", "remaining_time": "3:50:06"}
45
+ {"current_steps": 440, "total_steps": 1254, "loss": 0.6082, "learning_rate": 5e-06, "epoch": 1.0507462686567164, "percentage": 35.09, "elapsed_time": "2:02:47", "remaining_time": "3:47:09"}
46
+ {"current_steps": 450, "total_steps": 1254, "loss": 0.6113, "learning_rate": 5e-06, "epoch": 1.0746268656716418, "percentage": 35.89, "elapsed_time": "2:05:30", "remaining_time": "3:44:14"}
47
+ {"current_steps": 460, "total_steps": 1254, "loss": 0.6025, "learning_rate": 5e-06, "epoch": 1.0985074626865672, "percentage": 36.68, "elapsed_time": "2:08:13", "remaining_time": "3:41:19"}
48
+ {"current_steps": 470, "total_steps": 1254, "loss": 0.6096, "learning_rate": 5e-06, "epoch": 1.1223880597014926, "percentage": 37.48, "elapsed_time": "2:10:55", "remaining_time": "3:38:23"}
49
+ {"current_steps": 480, "total_steps": 1254, "loss": 0.6127, "learning_rate": 5e-06, "epoch": 1.146268656716418, "percentage": 38.28, "elapsed_time": "2:13:37", "remaining_time": "3:35:27"}
50
+ {"current_steps": 490, "total_steps": 1254, "loss": 0.6016, "learning_rate": 5e-06, "epoch": 1.1701492537313434, "percentage": 39.07, "elapsed_time": "2:16:18", "remaining_time": "3:32:31"}
51
+ {"current_steps": 500, "total_steps": 1254, "loss": 0.6078, "learning_rate": 5e-06, "epoch": 1.1940298507462686, "percentage": 39.87, "elapsed_time": "2:18:59", "remaining_time": "3:29:36"}
52
+ {"current_steps": 510, "total_steps": 1254, "loss": 0.6028, "learning_rate": 5e-06, "epoch": 1.217910447761194, "percentage": 40.67, "elapsed_time": "2:21:40", "remaining_time": "3:26:40"}
53
+ {"current_steps": 520, "total_steps": 1254, "loss": 0.6057, "learning_rate": 5e-06, "epoch": 1.2417910447761193, "percentage": 41.47, "elapsed_time": "2:24:21", "remaining_time": "3:23:45"}
54
+ {"current_steps": 530, "total_steps": 1254, "loss": 0.6128, "learning_rate": 5e-06, "epoch": 1.2656716417910447, "percentage": 42.26, "elapsed_time": "2:27:02", "remaining_time": "3:20:52"}
55
+ {"current_steps": 540, "total_steps": 1254, "loss": 0.6133, "learning_rate": 5e-06, "epoch": 1.2895522388059701, "percentage": 43.06, "elapsed_time": "2:29:44", "remaining_time": "3:17:59"}
56
+ {"current_steps": 550, "total_steps": 1254, "loss": 0.6089, "learning_rate": 5e-06, "epoch": 1.3134328358208955, "percentage": 43.86, "elapsed_time": "2:32:25", "remaining_time": "3:15:06"}
57
+ {"current_steps": 560, "total_steps": 1254, "loss": 0.6079, "learning_rate": 5e-06, "epoch": 1.337313432835821, "percentage": 44.66, "elapsed_time": "2:35:07", "remaining_time": "3:12:14"}
58
+ {"current_steps": 570, "total_steps": 1254, "loss": 0.6069, "learning_rate": 5e-06, "epoch": 1.3611940298507463, "percentage": 45.45, "elapsed_time": "2:37:49", "remaining_time": "3:09:23"}
59
+ {"current_steps": 580, "total_steps": 1254, "loss": 0.6069, "learning_rate": 5e-06, "epoch": 1.3850746268656717, "percentage": 46.25, "elapsed_time": "2:40:31", "remaining_time": "3:06:32"}
60
+ {"current_steps": 590, "total_steps": 1254, "loss": 0.6111, "learning_rate": 5e-06, "epoch": 1.408955223880597, "percentage": 47.05, "elapsed_time": "2:43:13", "remaining_time": "3:03:41"}
61
+ {"current_steps": 600, "total_steps": 1254, "loss": 0.613, "learning_rate": 5e-06, "epoch": 1.4328358208955223, "percentage": 47.85, "elapsed_time": "2:45:54", "remaining_time": "3:00:50"}
62
+ {"current_steps": 610, "total_steps": 1254, "loss": 0.6031, "learning_rate": 5e-06, "epoch": 1.4567164179104477, "percentage": 48.64, "elapsed_time": "2:48:37", "remaining_time": "2:58:01"}
63
+ {"current_steps": 620, "total_steps": 1254, "loss": 0.6126, "learning_rate": 5e-06, "epoch": 1.480597014925373, "percentage": 49.44, "elapsed_time": "2:51:20", "remaining_time": "2:55:12"}
64
+ {"current_steps": 630, "total_steps": 1254, "loss": 0.608, "learning_rate": 5e-06, "epoch": 1.5044776119402985, "percentage": 50.24, "elapsed_time": "2:54:02", "remaining_time": "2:52:23"}
65
+ {"current_steps": 640, "total_steps": 1254, "loss": 0.6031, "learning_rate": 5e-06, "epoch": 1.528358208955224, "percentage": 51.04, "elapsed_time": "2:56:46", "remaining_time": "2:49:35"}
66
+ {"current_steps": 650, "total_steps": 1254, "loss": 0.605, "learning_rate": 5e-06, "epoch": 1.5522388059701493, "percentage": 51.83, "elapsed_time": "2:59:28", "remaining_time": "2:46:46"}
67
+ {"current_steps": 660, "total_steps": 1254, "loss": 0.6109, "learning_rate": 5e-06, "epoch": 1.5761194029850745, "percentage": 52.63, "elapsed_time": "3:02:11", "remaining_time": "2:43:58"}
68
+ {"current_steps": 670, "total_steps": 1254, "loss": 0.6058, "learning_rate": 5e-06, "epoch": 1.6, "percentage": 53.43, "elapsed_time": "3:04:53", "remaining_time": "2:41:09"}
69
+ {"current_steps": 680, "total_steps": 1254, "loss": 0.6123, "learning_rate": 5e-06, "epoch": 1.6238805970149253, "percentage": 54.23, "elapsed_time": "3:07:36", "remaining_time": "2:38:21"}
70
+ {"current_steps": 690, "total_steps": 1254, "loss": 0.5942, "learning_rate": 5e-06, "epoch": 1.6477611940298509, "percentage": 55.02, "elapsed_time": "3:10:18", "remaining_time": "2:35:33"}
71
+ {"current_steps": 700, "total_steps": 1254, "loss": 0.6106, "learning_rate": 5e-06, "epoch": 1.671641791044776, "percentage": 55.82, "elapsed_time": "3:13:00", "remaining_time": "2:32:44"}
72
+ {"current_steps": 710, "total_steps": 1254, "loss": 0.6091, "learning_rate": 5e-06, "epoch": 1.6955223880597015, "percentage": 56.62, "elapsed_time": "3:15:41", "remaining_time": "2:29:56"}
73
+ {"current_steps": 720, "total_steps": 1254, "loss": 0.6123, "learning_rate": 5e-06, "epoch": 1.7194029850746269, "percentage": 57.42, "elapsed_time": "3:18:24", "remaining_time": "2:27:08"}
74
+ {"current_steps": 730, "total_steps": 1254, "loss": 0.6019, "learning_rate": 5e-06, "epoch": 1.7432835820895523, "percentage": 58.21, "elapsed_time": "3:21:06", "remaining_time": "2:24:21"}
75
+ {"current_steps": 740, "total_steps": 1254, "loss": 0.6012, "learning_rate": 5e-06, "epoch": 1.7671641791044777, "percentage": 59.01, "elapsed_time": "3:23:48", "remaining_time": "2:21:33"}
76
+ {"current_steps": 750, "total_steps": 1254, "loss": 0.6088, "learning_rate": 5e-06, "epoch": 1.7910447761194028, "percentage": 59.81, "elapsed_time": "3:26:30", "remaining_time": "2:18:46"}
77
+ {"current_steps": 760, "total_steps": 1254, "loss": 0.602, "learning_rate": 5e-06, "epoch": 1.8149253731343284, "percentage": 60.61, "elapsed_time": "3:29:12", "remaining_time": "2:15:59"}
78
+ {"current_steps": 770, "total_steps": 1254, "loss": 0.609, "learning_rate": 5e-06, "epoch": 1.8388059701492536, "percentage": 61.4, "elapsed_time": "3:31:53", "remaining_time": "2:13:11"}
79
+ {"current_steps": 780, "total_steps": 1254, "loss": 0.6108, "learning_rate": 5e-06, "epoch": 1.8626865671641792, "percentage": 62.2, "elapsed_time": "3:34:33", "remaining_time": "2:10:23"}
80
+ {"current_steps": 790, "total_steps": 1254, "loss": 0.6059, "learning_rate": 5e-06, "epoch": 1.8865671641791044, "percentage": 63.0, "elapsed_time": "3:37:15", "remaining_time": "2:07:36"}
81
+ {"current_steps": 800, "total_steps": 1254, "loss": 0.6071, "learning_rate": 5e-06, "epoch": 1.9104477611940298, "percentage": 63.8, "elapsed_time": "3:39:56", "remaining_time": "2:04:48"}
82
+ {"current_steps": 810, "total_steps": 1254, "loss": 0.6006, "learning_rate": 5e-06, "epoch": 1.9343283582089552, "percentage": 64.59, "elapsed_time": "3:42:37", "remaining_time": "2:02:02"}
83
+ {"current_steps": 820, "total_steps": 1254, "loss": 0.606, "learning_rate": 5e-06, "epoch": 1.9582089552238806, "percentage": 65.39, "elapsed_time": "3:45:20", "remaining_time": "1:59:15"}
84
+ {"current_steps": 830, "total_steps": 1254, "loss": 0.6046, "learning_rate": 5e-06, "epoch": 1.982089552238806, "percentage": 66.19, "elapsed_time": "3:48:02", "remaining_time": "1:56:29"}
85
+ {"current_steps": 837, "total_steps": 1254, "eval_loss": 0.6354221701622009, "epoch": 1.9988059701492538, "percentage": 66.75, "elapsed_time": "3:52:28", "remaining_time": "1:55:49"}
86
+ {"current_steps": 840, "total_steps": 1254, "loss": 0.6034, "learning_rate": 5e-06, "epoch": 2.005970149253731, "percentage": 66.99, "elapsed_time": "3:54:14", "remaining_time": "1:55:26"}
87
+ {"current_steps": 850, "total_steps": 1254, "loss": 0.5647, "learning_rate": 5e-06, "epoch": 2.029850746268657, "percentage": 67.78, "elapsed_time": "3:56:55", "remaining_time": "1:52:36"}
88
+ {"current_steps": 860, "total_steps": 1254, "loss": 0.5566, "learning_rate": 5e-06, "epoch": 2.053731343283582, "percentage": 68.58, "elapsed_time": "3:59:37", "remaining_time": "1:49:46"}
89
+ {"current_steps": 870, "total_steps": 1254, "loss": 0.5679, "learning_rate": 5e-06, "epoch": 2.0776119402985076, "percentage": 69.38, "elapsed_time": "4:02:18", "remaining_time": "1:46:56"}
90
+ {"current_steps": 880, "total_steps": 1254, "loss": 0.5611, "learning_rate": 5e-06, "epoch": 2.1014925373134328, "percentage": 70.18, "elapsed_time": "4:05:00", "remaining_time": "1:44:07"}
91
+ {"current_steps": 890, "total_steps": 1254, "loss": 0.565, "learning_rate": 5e-06, "epoch": 2.1253731343283584, "percentage": 70.97, "elapsed_time": "4:07:41", "remaining_time": "1:41:18"}
92
+ {"current_steps": 900, "total_steps": 1254, "loss": 0.5611, "learning_rate": 5e-06, "epoch": 2.1492537313432836, "percentage": 71.77, "elapsed_time": "4:10:23", "remaining_time": "1:38:29"}
93
+ {"current_steps": 910, "total_steps": 1254, "loss": 0.5618, "learning_rate": 5e-06, "epoch": 2.173134328358209, "percentage": 72.57, "elapsed_time": "4:13:06", "remaining_time": "1:35:40"}
94
+ {"current_steps": 920, "total_steps": 1254, "loss": 0.568, "learning_rate": 5e-06, "epoch": 2.1970149253731344, "percentage": 73.37, "elapsed_time": "4:15:48", "remaining_time": "1:32:52"}
95
+ {"current_steps": 930, "total_steps": 1254, "loss": 0.5698, "learning_rate": 5e-06, "epoch": 2.2208955223880595, "percentage": 74.16, "elapsed_time": "4:18:30", "remaining_time": "1:30:03"}
96
+ {"current_steps": 940, "total_steps": 1254, "loss": 0.5607, "learning_rate": 5e-06, "epoch": 2.244776119402985, "percentage": 74.96, "elapsed_time": "4:21:12", "remaining_time": "1:27:15"}
97
+ {"current_steps": 950, "total_steps": 1254, "loss": 0.5657, "learning_rate": 5e-06, "epoch": 2.2686567164179103, "percentage": 75.76, "elapsed_time": "4:23:54", "remaining_time": "1:24:26"}
98
+ {"current_steps": 960, "total_steps": 1254, "loss": 0.5582, "learning_rate": 5e-06, "epoch": 2.292537313432836, "percentage": 76.56, "elapsed_time": "4:26:35", "remaining_time": "1:21:38"}
99
+ {"current_steps": 970, "total_steps": 1254, "loss": 0.5673, "learning_rate": 5e-06, "epoch": 2.316417910447761, "percentage": 77.35, "elapsed_time": "4:29:19", "remaining_time": "1:18:51"}
100
+ {"current_steps": 980, "total_steps": 1254, "loss": 0.5627, "learning_rate": 5e-06, "epoch": 2.3402985074626868, "percentage": 78.15, "elapsed_time": "4:32:02", "remaining_time": "1:16:03"}
101
+ {"current_steps": 990, "total_steps": 1254, "loss": 0.5632, "learning_rate": 5e-06, "epoch": 2.364179104477612, "percentage": 78.95, "elapsed_time": "4:34:44", "remaining_time": "1:13:15"}
102
+ {"current_steps": 1000, "total_steps": 1254, "loss": 0.5683, "learning_rate": 5e-06, "epoch": 2.388059701492537, "percentage": 79.74, "elapsed_time": "4:37:25", "remaining_time": "1:10:28"}
103
+ {"current_steps": 1010, "total_steps": 1254, "loss": 0.5616, "learning_rate": 5e-06, "epoch": 2.4119402985074627, "percentage": 80.54, "elapsed_time": "4:40:07", "remaining_time": "1:07:40"}
104
+ {"current_steps": 1020, "total_steps": 1254, "loss": 0.5607, "learning_rate": 5e-06, "epoch": 2.435820895522388, "percentage": 81.34, "elapsed_time": "4:42:50", "remaining_time": "1:04:53"}
105
+ {"current_steps": 1030, "total_steps": 1254, "loss": 0.564, "learning_rate": 5e-06, "epoch": 2.4597014925373135, "percentage": 82.14, "elapsed_time": "4:45:33", "remaining_time": "1:02:06"}
106
+ {"current_steps": 1040, "total_steps": 1254, "loss": 0.572, "learning_rate": 5e-06, "epoch": 2.4835820895522387, "percentage": 82.93, "elapsed_time": "4:48:16", "remaining_time": "0:59:19"}
107
+ {"current_steps": 1050, "total_steps": 1254, "loss": 0.561, "learning_rate": 5e-06, "epoch": 2.5074626865671643, "percentage": 83.73, "elapsed_time": "4:50:57", "remaining_time": "0:56:31"}
108
+ {"current_steps": 1060, "total_steps": 1254, "loss": 0.5702, "learning_rate": 5e-06, "epoch": 2.5313432835820895, "percentage": 84.53, "elapsed_time": "4:53:38", "remaining_time": "0:53:44"}
109
+ {"current_steps": 1070, "total_steps": 1254, "loss": 0.5648, "learning_rate": 5e-06, "epoch": 2.5552238805970147, "percentage": 85.33, "elapsed_time": "4:56:19", "remaining_time": "0:50:57"}
110
+ {"current_steps": 1080, "total_steps": 1254, "loss": 0.5699, "learning_rate": 5e-06, "epoch": 2.5791044776119403, "percentage": 86.12, "elapsed_time": "4:59:01", "remaining_time": "0:48:10"}
111
+ {"current_steps": 1090, "total_steps": 1254, "loss": 0.5687, "learning_rate": 5e-06, "epoch": 2.602985074626866, "percentage": 86.92, "elapsed_time": "5:01:41", "remaining_time": "0:45:23"}
112
+ {"current_steps": 1100, "total_steps": 1254, "loss": 0.5647, "learning_rate": 5e-06, "epoch": 2.626865671641791, "percentage": 87.72, "elapsed_time": "5:04:23", "remaining_time": "0:42:36"}
113
+ {"current_steps": 1110, "total_steps": 1254, "loss": 0.5628, "learning_rate": 5e-06, "epoch": 2.6507462686567163, "percentage": 88.52, "elapsed_time": "5:07:05", "remaining_time": "0:39:50"}
114
+ {"current_steps": 1120, "total_steps": 1254, "loss": 0.5672, "learning_rate": 5e-06, "epoch": 2.674626865671642, "percentage": 89.31, "elapsed_time": "5:09:47", "remaining_time": "0:37:03"}
115
+ {"current_steps": 1130, "total_steps": 1254, "loss": 0.5715, "learning_rate": 5e-06, "epoch": 2.698507462686567, "percentage": 90.11, "elapsed_time": "5:12:28", "remaining_time": "0:34:17"}
116
+ {"current_steps": 1140, "total_steps": 1254, "loss": 0.5664, "learning_rate": 5e-06, "epoch": 2.7223880597014927, "percentage": 90.91, "elapsed_time": "5:15:09", "remaining_time": "0:31:30"}
117
+ {"current_steps": 1150, "total_steps": 1254, "loss": 0.5703, "learning_rate": 5e-06, "epoch": 2.746268656716418, "percentage": 91.71, "elapsed_time": "5:17:50", "remaining_time": "0:28:44"}
118
+ {"current_steps": 1160, "total_steps": 1254, "loss": 0.568, "learning_rate": 5e-06, "epoch": 2.7701492537313435, "percentage": 92.5, "elapsed_time": "5:20:32", "remaining_time": "0:25:58"}
119
+ {"current_steps": 1170, "total_steps": 1254, "loss": 0.5617, "learning_rate": 5e-06, "epoch": 2.7940298507462686, "percentage": 93.3, "elapsed_time": "5:23:15", "remaining_time": "0:23:12"}
120
+ {"current_steps": 1180, "total_steps": 1254, "loss": 0.5632, "learning_rate": 5e-06, "epoch": 2.817910447761194, "percentage": 94.1, "elapsed_time": "5:25:57", "remaining_time": "0:20:26"}
121
+ {"current_steps": 1190, "total_steps": 1254, "loss": 0.5659, "learning_rate": 5e-06, "epoch": 2.8417910447761194, "percentage": 94.9, "elapsed_time": "5:28:39", "remaining_time": "0:17:40"}
122
+ {"current_steps": 1200, "total_steps": 1254, "loss": 0.5677, "learning_rate": 5e-06, "epoch": 2.8656716417910446, "percentage": 95.69, "elapsed_time": "5:31:22", "remaining_time": "0:14:54"}
123
+ {"current_steps": 1210, "total_steps": 1254, "loss": 0.5756, "learning_rate": 5e-06, "epoch": 2.8895522388059702, "percentage": 96.49, "elapsed_time": "5:34:04", "remaining_time": "0:12:08"}
124
+ {"current_steps": 1220, "total_steps": 1254, "loss": 0.5686, "learning_rate": 5e-06, "epoch": 2.9134328358208954, "percentage": 97.29, "elapsed_time": "5:36:46", "remaining_time": "0:09:23"}
125
+ {"current_steps": 1230, "total_steps": 1254, "loss": 0.5734, "learning_rate": 5e-06, "epoch": 2.937313432835821, "percentage": 98.09, "elapsed_time": "5:39:28", "remaining_time": "0:06:37"}
126
+ {"current_steps": 1240, "total_steps": 1254, "loss": 0.5699, "learning_rate": 5e-06, "epoch": 2.961194029850746, "percentage": 98.88, "elapsed_time": "5:42:10", "remaining_time": "0:03:51"}
127
+ {"current_steps": 1250, "total_steps": 1254, "loss": 0.5716, "learning_rate": 5e-06, "epoch": 2.9850746268656714, "percentage": 99.68, "elapsed_time": "5:44:53", "remaining_time": "0:01:06"}
128
+ {"current_steps": 1254, "total_steps": 1254, "eval_loss": 0.636893630027771, "epoch": 2.9946268656716417, "percentage": 100.0, "elapsed_time": "5:49:27", "remaining_time": "0:00:00"}
129
+ {"current_steps": 1254, "total_steps": 1254, "epoch": 2.9946268656716417, "percentage": 100.0, "elapsed_time": "5:50:45", "remaining_time": "0:00:00"}
training_args.bin.sagemaker-uploaded ADDED
File without changes