Hugging Face's logo

mlfoundations-dev
/
top_10_ranking_stackexchange

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
bf97457
·
verified ·
1 Parent(s): 4a9c919

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 +37 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e64f889c919712fe83536853590c7f046f84ddfdcf5233deebf9f8245d1336d
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d9f7a97c1f447ac301f5086ae1d9ad820a7587268756b3540215fd47492c3d7
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:631122b613c021e963599fe69b4c66b4ba9110b81d5d3c960f9bf7ef2998121d
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:204f04587d53b33c0fca9b70afb005ad7b25c777afafce0fa0b3b4913116fd65
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:d7ab7477ee75c799d1f0504d6a190399feccb676aac24ad6ef8724d95bff9346
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7860c32edae460ae771afa963ec87a687472b8ccc20ff5c79ee25b8b1cbbea3d
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:b7d099da71419d3f38eb560e072b379c0ee97c0b62740124c2e4d00c83cff7e4
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddbeb1726a80c6afacb0116595845a1acaa42745ba0ac6828e796adbe1ad356a
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -74,3 +74,40 @@
74
  {"current_steps": 730, "total_steps": 1119, "loss": 0.7489, "lr": 5e-06, "epoch": 1.9564489112227805, "percentage": 65.24, "elapsed_time": "11:48:13", "remaining_time": "6:17:23"}
75
  {"current_steps": 740, "total_steps": 1119, "loss": 0.7568, "lr": 5e-06, "epoch": 1.983249581239531, "percentage": 66.13, "elapsed_time": "11:57:50", "remaining_time": "6:07:38"}
76
  {"current_steps": 746, "total_steps": 1119, "eval_loss": 0.7848142385482788, "epoch": 1.9993299832495812, "percentage": 66.67, "elapsed_time": "12:10:27", "remaining_time": "6:05:13"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
74
  {"current_steps": 730, "total_steps": 1119, "loss": 0.7489, "lr": 5e-06, "epoch": 1.9564489112227805, "percentage": 65.24, "elapsed_time": "11:48:13", "remaining_time": "6:17:23"}
75
  {"current_steps": 740, "total_steps": 1119, "loss": 0.7568, "lr": 5e-06, "epoch": 1.983249581239531, "percentage": 66.13, "elapsed_time": "11:57:50", "remaining_time": "6:07:38"}
76
  {"current_steps": 746, "total_steps": 1119, "eval_loss": 0.7848142385482788, "epoch": 1.9993299832495812, "percentage": 66.67, "elapsed_time": "12:10:27", "remaining_time": "6:05:13"}
77
+ {"current_steps": 750, "total_steps": 1119, "loss": 0.806, "lr": 5e-06, "epoch": 2.0100502512562812, "percentage": 67.02, "elapsed_time": "12:15:21", "remaining_time": "6:01:47"}
78
+ {"current_steps": 760, "total_steps": 1119, "loss": 0.7051, "lr": 5e-06, "epoch": 2.036850921273032, "percentage": 67.92, "elapsed_time": "12:24:57", "remaining_time": "5:51:53"}
79
+ {"current_steps": 770, "total_steps": 1119, "loss": 0.7054, "lr": 5e-06, "epoch": 2.063651591289782, "percentage": 68.81, "elapsed_time": "12:34:32", "remaining_time": "5:41:59"}
80
+ {"current_steps": 780, "total_steps": 1119, "loss": 0.7057, "lr": 5e-06, "epoch": 2.090452261306533, "percentage": 69.71, "elapsed_time": "12:44:07", "remaining_time": "5:32:05"}
81
+ {"current_steps": 790, "total_steps": 1119, "loss": 0.7074, "lr": 5e-06, "epoch": 2.117252931323283, "percentage": 70.6, "elapsed_time": "12:53:43", "remaining_time": "5:22:13"}
82
+ {"current_steps": 800, "total_steps": 1119, "loss": 0.7035, "lr": 5e-06, "epoch": 2.1440536013400333, "percentage": 71.49, "elapsed_time": "13:03:20", "remaining_time": "5:12:21"}
83
+ {"current_steps": 810, "total_steps": 1119, "loss": 0.7045, "lr": 5e-06, "epoch": 2.170854271356784, "percentage": 72.39, "elapsed_time": "13:12:56", "remaining_time": "5:02:29"}
84
+ {"current_steps": 820, "total_steps": 1119, "loss": 0.7085, "lr": 5e-06, "epoch": 2.1976549413735342, "percentage": 73.28, "elapsed_time": "13:22:32", "remaining_time": "4:52:38"}
85
+ {"current_steps": 830, "total_steps": 1119, "loss": 0.7067, "lr": 5e-06, "epoch": 2.224455611390285, "percentage": 74.17, "elapsed_time": "13:32:09", "remaining_time": "4:42:47"}
86
+ {"current_steps": 840, "total_steps": 1119, "loss": 0.712, "lr": 5e-06, "epoch": 2.251256281407035, "percentage": 75.07, "elapsed_time": "13:41:44", "remaining_time": "4:32:56"}
87
+ {"current_steps": 850, "total_steps": 1119, "loss": 0.7132, "lr": 5e-06, "epoch": 2.2780569514237854, "percentage": 75.96, "elapsed_time": "13:51:20", "remaining_time": "4:23:05"}
88
+ {"current_steps": 860, "total_steps": 1119, "loss": 0.7126, "lr": 5e-06, "epoch": 2.304857621440536, "percentage": 76.85, "elapsed_time": "14:00:57", "remaining_time": "4:13:15"}
89
+ {"current_steps": 870, "total_steps": 1119, "loss": 0.71, "lr": 5e-06, "epoch": 2.3316582914572863, "percentage": 77.75, "elapsed_time": "14:10:33", "remaining_time": "4:03:26"}
90
+ {"current_steps": 880, "total_steps": 1119, "loss": 0.7095, "lr": 5e-06, "epoch": 2.358458961474037, "percentage": 78.64, "elapsed_time": "14:20:11", "remaining_time": "3:53:37"}
91
+ {"current_steps": 890, "total_steps": 1119, "loss": 0.7091, "lr": 5e-06, "epoch": 2.3852596314907872, "percentage": 79.54, "elapsed_time": "14:29:46", "remaining_time": "3:43:47"}
92
+ {"current_steps": 900, "total_steps": 1119, "loss": 0.7061, "lr": 5e-06, "epoch": 2.4120603015075375, "percentage": 80.43, "elapsed_time": "14:39:23", "remaining_time": "3:33:59"}
93
+ {"current_steps": 910, "total_steps": 1119, "loss": 0.709, "lr": 5e-06, "epoch": 2.438860971524288, "percentage": 81.32, "elapsed_time": "14:48:59", "remaining_time": "3:24:10"}
94
+ {"current_steps": 920, "total_steps": 1119, "loss": 0.7092, "lr": 5e-06, "epoch": 2.4656616415410384, "percentage": 82.22, "elapsed_time": "14:58:34", "remaining_time": "3:14:21"}
95
+ {"current_steps": 930, "total_steps": 1119, "loss": 0.7074, "lr": 5e-06, "epoch": 2.492462311557789, "percentage": 83.11, "elapsed_time": "15:08:10", "remaining_time": "3:04:33"}
96
+ {"current_steps": 940, "total_steps": 1119, "loss": 0.7123, "lr": 5e-06, "epoch": 2.5192629815745393, "percentage": 84.0, "elapsed_time": "15:17:45", "remaining_time": "2:54:45"}
97
+ {"current_steps": 950, "total_steps": 1119, "loss": 0.7117, "lr": 5e-06, "epoch": 2.5460636515912896, "percentage": 84.9, "elapsed_time": "15:27:20", "remaining_time": "2:44:58"}
98
+ {"current_steps": 960, "total_steps": 1119, "loss": 0.7123, "lr": 5e-06, "epoch": 2.5728643216080402, "percentage": 85.79, "elapsed_time": "15:36:56", "remaining_time": "2:35:10"}
99
+ {"current_steps": 970, "total_steps": 1119, "loss": 0.7124, "lr": 5e-06, "epoch": 2.5996649916247905, "percentage": 86.68, "elapsed_time": "15:46:32", "remaining_time": "2:25:23"}
100
+ {"current_steps": 980, "total_steps": 1119, "loss": 0.7095, "lr": 5e-06, "epoch": 2.626465661641541, "percentage": 87.58, "elapsed_time": "15:56:07", "remaining_time": "2:15:36"}
101
+ {"current_steps": 990, "total_steps": 1119, "loss": 0.7098, "lr": 5e-06, "epoch": 2.6532663316582914, "percentage": 88.47, "elapsed_time": "16:05:43", "remaining_time": "2:05:50"}
102
+ {"current_steps": 1000, "total_steps": 1119, "loss": 0.7114, "lr": 5e-06, "epoch": 2.6800670016750416, "percentage": 89.37, "elapsed_time": "16:15:19", "remaining_time": "1:56:03"}
103
+ {"current_steps": 1010, "total_steps": 1119, "loss": 0.7126, "lr": 5e-06, "epoch": 2.7068676716917923, "percentage": 90.26, "elapsed_time": "16:24:55", "remaining_time": "1:46:17"}
104
+ {"current_steps": 1020, "total_steps": 1119, "loss": 0.7107, "lr": 5e-06, "epoch": 2.7336683417085426, "percentage": 91.15, "elapsed_time": "16:34:31", "remaining_time": "1:36:31"}
105
+ {"current_steps": 1030, "total_steps": 1119, "loss": 0.708, "lr": 5e-06, "epoch": 2.7604690117252932, "percentage": 92.05, "elapsed_time": "16:44:07", "remaining_time": "1:26:45"}
106
+ {"current_steps": 1040, "total_steps": 1119, "loss": 0.7166, "lr": 5e-06, "epoch": 2.7872696817420435, "percentage": 92.94, "elapsed_time": "16:53:42", "remaining_time": "1:17:00"}
107
+ {"current_steps": 1050, "total_steps": 1119, "loss": 0.7112, "lr": 5e-06, "epoch": 2.8140703517587937, "percentage": 93.83, "elapsed_time": "17:03:19", "remaining_time": "1:07:14"}
108
+ {"current_steps": 1060, "total_steps": 1119, "loss": 0.7083, "lr": 5e-06, "epoch": 2.8408710217755444, "percentage": 94.73, "elapsed_time": "17:12:55", "remaining_time": "0:57:29"}
109
+ {"current_steps": 1070, "total_steps": 1119, "loss": 0.7165, "lr": 5e-06, "epoch": 2.8676716917922946, "percentage": 95.62, "elapsed_time": "17:22:29", "remaining_time": "0:47:44"}
110
+ {"current_steps": 1080, "total_steps": 1119, "loss": 0.7126, "lr": 5e-06, "epoch": 2.8944723618090453, "percentage": 96.51, "elapsed_time": "17:32:06", "remaining_time": "0:37:59"}
111
+ {"current_steps": 1090, "total_steps": 1119, "loss": 0.709, "lr": 5e-06, "epoch": 2.9212730318257956, "percentage": 97.41, "elapsed_time": "17:41:43", "remaining_time": "0:28:14"}
112
+ {"current_steps": 1100, "total_steps": 1119, "loss": 0.7131, "lr": 5e-06, "epoch": 2.948073701842546, "percentage": 98.3, "elapsed_time": "17:51:19", "remaining_time": "0:18:30"}
113
+ {"current_steps": 1110, "total_steps": 1119, "loss": 0.7167, "lr": 5e-06, "epoch": 2.9748743718592965, "percentage": 99.2, "elapsed_time": "18:00:56", "remaining_time": "0:08:45"}