Hugging Face's logo

mlfoundations-dev
/
hp_ablations_qwen_lr1e-5

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
1
sedrickkeh commited on
Commit
210f50d
·
verified ·
1 Parent(s): a47e56f

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 +44 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8b52957f4757d42e55734af0277b31e1c674dd655e07cebdac0d3d0dbc043eb
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5748b6f8474b2d432052244a98b97e44340f8e5438175ea76403e390f898822c
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:94ca1a56dc7a5db50ce830cd4ca8d09348539c37517e5a8217664bf8451bb913
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8288574fe99af193f2ce0f01283bdc4b7cebec4d67ae014bcf296692ae7fb2df
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:188deb79d163b692e48a24af1b5d7723d57d7e51eac146a306add78ea9db0d20
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d479e80d70f6bf3f2fa56ecfe8ad0a595919dca190d3dcc9da7ddf0aaa1c7ef8
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:576138b3446d165b17eaabbcc5e051dafa314a663292dfd367f9e4389634d08d
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:168a75a7572e3ee1edf2094254c3c1c1cc5c8e6f369235b1bdd7a3c0758a0832
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -87,3 +87,47 @@
87
  {"current_steps": 860, "total_steps": 1314, "loss": 0.5798, "learning_rate": 1e-05, "epoch": 1.9606837606837608, "percentage": 65.45, "elapsed_time": "12:39:03", "remaining_time": "6:40:42"}
88
  {"current_steps": 870, "total_steps": 1314, "loss": 0.5774, "learning_rate": 1e-05, "epoch": 1.9834757834757835, "percentage": 66.21, "elapsed_time": "12:47:47", "remaining_time": "6:31:50"}
89
  {"current_steps": 877, "total_steps": 1314, "eval_loss": 0.6186357736587524, "epoch": 1.9994301994301993, "percentage": 66.74, "elapsed_time": "13:01:13", "remaining_time": "6:29:16"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
87
  {"current_steps": 860, "total_steps": 1314, "loss": 0.5798, "learning_rate": 1e-05, "epoch": 1.9606837606837608, "percentage": 65.45, "elapsed_time": "12:39:03", "remaining_time": "6:40:42"}
88
  {"current_steps": 870, "total_steps": 1314, "loss": 0.5774, "learning_rate": 1e-05, "epoch": 1.9834757834757835, "percentage": 66.21, "elapsed_time": "12:47:47", "remaining_time": "6:31:50"}
89
  {"current_steps": 877, "total_steps": 1314, "eval_loss": 0.6186357736587524, "epoch": 1.9994301994301993, "percentage": 66.74, "elapsed_time": "13:01:13", "remaining_time": "6:29:16"}
90
+ {"current_steps": 880, "total_steps": 1314, "loss": 0.5896, "learning_rate": 1e-05, "epoch": 2.006837606837607, "percentage": 66.97, "elapsed_time": "13:04:59", "remaining_time": "6:27:08"}
91
+ {"current_steps": 890, "total_steps": 1314, "loss": 0.5143, "learning_rate": 1e-05, "epoch": 2.0296296296296297, "percentage": 67.73, "elapsed_time": "13:13:44", "remaining_time": "6:18:08"}
92
+ {"current_steps": 900, "total_steps": 1314, "loss": 0.5277, "learning_rate": 1e-05, "epoch": 2.0524216524216525, "percentage": 68.49, "elapsed_time": "13:22:28", "remaining_time": "6:09:08"}
93
+ {"current_steps": 910, "total_steps": 1314, "loss": 0.5262, "learning_rate": 1e-05, "epoch": 2.0752136752136754, "percentage": 69.25, "elapsed_time": "13:31:12", "remaining_time": "6:00:08"}
94
+ {"current_steps": 920, "total_steps": 1314, "loss": 0.529, "learning_rate": 1e-05, "epoch": 2.098005698005698, "percentage": 70.02, "elapsed_time": "13:39:56", "remaining_time": "5:51:09"}
95
+ {"current_steps": 930, "total_steps": 1314, "loss": 0.5279, "learning_rate": 1e-05, "epoch": 2.1207977207977207, "percentage": 70.78, "elapsed_time": "13:48:41", "remaining_time": "5:42:10"}
96
+ {"current_steps": 940, "total_steps": 1314, "loss": 0.523, "learning_rate": 1e-05, "epoch": 2.1435897435897435, "percentage": 71.54, "elapsed_time": "13:57:24", "remaining_time": "5:33:10"}
97
+ {"current_steps": 950, "total_steps": 1314, "loss": 0.5239, "learning_rate": 1e-05, "epoch": 2.1663817663817664, "percentage": 72.3, "elapsed_time": "14:06:08", "remaining_time": "5:24:12"}
98
+ {"current_steps": 960, "total_steps": 1314, "loss": 0.5291, "learning_rate": 1e-05, "epoch": 2.1891737891737892, "percentage": 73.06, "elapsed_time": "14:14:52", "remaining_time": "5:15:14"}
99
+ {"current_steps": 970, "total_steps": 1314, "loss": 0.529, "learning_rate": 1e-05, "epoch": 2.211965811965812, "percentage": 73.82, "elapsed_time": "14:23:36", "remaining_time": "5:06:16"}
100
+ {"current_steps": 980, "total_steps": 1314, "loss": 0.5197, "learning_rate": 1e-05, "epoch": 2.234757834757835, "percentage": 74.58, "elapsed_time": "14:32:20", "remaining_time": "4:57:18"}
101
+ {"current_steps": 990, "total_steps": 1314, "loss": 0.5287, "learning_rate": 1e-05, "epoch": 2.2575498575498574, "percentage": 75.34, "elapsed_time": "14:41:04", "remaining_time": "4:48:21"}
102
+ {"current_steps": 1000, "total_steps": 1314, "loss": 0.5293, "learning_rate": 1e-05, "epoch": 2.2803418803418802, "percentage": 76.1, "elapsed_time": "14:49:48", "remaining_time": "4:39:23"}
103
+ {"current_steps": 1010, "total_steps": 1314, "loss": 0.5269, "learning_rate": 1e-05, "epoch": 2.303133903133903, "percentage": 76.86, "elapsed_time": "14:58:32", "remaining_time": "4:30:27"}
104
+ {"current_steps": 1020, "total_steps": 1314, "loss": 0.5298, "learning_rate": 1e-05, "epoch": 2.325925925925926, "percentage": 77.63, "elapsed_time": "15:07:16", "remaining_time": "4:21:30"}
105
+ {"current_steps": 1030, "total_steps": 1314, "loss": 0.5311, "learning_rate": 1e-05, "epoch": 2.348717948717949, "percentage": 78.39, "elapsed_time": "15:16:00", "remaining_time": "4:12:34"}
106
+ {"current_steps": 1040, "total_steps": 1314, "loss": 0.5299, "learning_rate": 1e-05, "epoch": 2.3715099715099717, "percentage": 79.15, "elapsed_time": "15:24:44", "remaining_time": "4:03:37"}
107
+ {"current_steps": 1050, "total_steps": 1314, "loss": 0.5292, "learning_rate": 1e-05, "epoch": 2.394301994301994, "percentage": 79.91, "elapsed_time": "15:33:28", "remaining_time": "3:54:42"}
108
+ {"current_steps": 1060, "total_steps": 1314, "loss": 0.537, "learning_rate": 1e-05, "epoch": 2.417094017094017, "percentage": 80.67, "elapsed_time": "15:42:11", "remaining_time": "3:45:46"}
109
+ {"current_steps": 1070, "total_steps": 1314, "loss": 0.5397, "learning_rate": 1e-05, "epoch": 2.43988603988604, "percentage": 81.43, "elapsed_time": "15:50:55", "remaining_time": "3:36:50"}
110
+ {"current_steps": 1080, "total_steps": 1314, "loss": 0.5354, "learning_rate": 1e-05, "epoch": 2.4626780626780627, "percentage": 82.19, "elapsed_time": "15:59:39", "remaining_time": "3:27:55"}
111
+ {"current_steps": 1090, "total_steps": 1314, "loss": 0.5339, "learning_rate": 1e-05, "epoch": 2.4854700854700855, "percentage": 82.95, "elapsed_time": "16:08:24", "remaining_time": "3:19:00"}
112
+ {"current_steps": 1100, "total_steps": 1314, "loss": 0.5394, "learning_rate": 1e-05, "epoch": 2.5082621082621084, "percentage": 83.71, "elapsed_time": "16:17:08", "remaining_time": "3:10:05"}
113
+ {"current_steps": 1110, "total_steps": 1314, "loss": 0.5341, "learning_rate": 1e-05, "epoch": 2.5310541310541312, "percentage": 84.47, "elapsed_time": "16:25:52", "remaining_time": "3:01:11"}
114
+ {"current_steps": 1120, "total_steps": 1314, "loss": 0.5322, "learning_rate": 1e-05, "epoch": 2.5538461538461537, "percentage": 85.24, "elapsed_time": "16:34:36", "remaining_time": "2:52:16"}
115
+ {"current_steps": 1130, "total_steps": 1314, "loss": 0.5319, "learning_rate": 1e-05, "epoch": 2.5766381766381765, "percentage": 86.0, "elapsed_time": "16:43:21", "remaining_time": "2:43:22"}
116
+ {"current_steps": 1140, "total_steps": 1314, "loss": 0.5318, "learning_rate": 1e-05, "epoch": 2.5994301994301994, "percentage": 86.76, "elapsed_time": "16:52:06", "remaining_time": "2:34:28"}
117
+ {"current_steps": 1150, "total_steps": 1314, "loss": 0.5324, "learning_rate": 1e-05, "epoch": 2.6222222222222222, "percentage": 87.52, "elapsed_time": "17:00:50", "remaining_time": "2:25:34"}
118
+ {"current_steps": 1160, "total_steps": 1314, "loss": 0.5338, "learning_rate": 1e-05, "epoch": 2.645014245014245, "percentage": 88.28, "elapsed_time": "17:09:34", "remaining_time": "2:16:41"}
119
+ {"current_steps": 1170, "total_steps": 1314, "loss": 0.5361, "learning_rate": 1e-05, "epoch": 2.667806267806268, "percentage": 89.04, "elapsed_time": "17:18:18", "remaining_time": "2:07:47"}
120
+ {"current_steps": 1180, "total_steps": 1314, "loss": 0.5316, "learning_rate": 1e-05, "epoch": 2.690598290598291, "percentage": 89.8, "elapsed_time": "17:27:03", "remaining_time": "1:58:54"}
121
+ {"current_steps": 1190, "total_steps": 1314, "loss": 0.5331, "learning_rate": 1e-05, "epoch": 2.7133903133903132, "percentage": 90.56, "elapsed_time": "17:35:48", "remaining_time": "1:50:00"}
122
+ {"current_steps": 1200, "total_steps": 1314, "loss": 0.5362, "learning_rate": 1e-05, "epoch": 2.736182336182336, "percentage": 91.32, "elapsed_time": "17:44:32", "remaining_time": "1:41:07"}
123
+ {"current_steps": 1210, "total_steps": 1314, "loss": 0.5394, "learning_rate": 1e-05, "epoch": 2.758974358974359, "percentage": 92.09, "elapsed_time": "17:53:16", "remaining_time": "1:32:14"}
124
+ {"current_steps": 1220, "total_steps": 1314, "loss": 0.5301, "learning_rate": 1e-05, "epoch": 2.781766381766382, "percentage": 92.85, "elapsed_time": "18:02:00", "remaining_time": "1:23:22"}
125
+ {"current_steps": 1230, "total_steps": 1314, "loss": 0.5286, "learning_rate": 1e-05, "epoch": 2.8045584045584047, "percentage": 93.61, "elapsed_time": "18:10:45", "remaining_time": "1:14:29"}
126
+ {"current_steps": 1240, "total_steps": 1314, "loss": 0.5428, "learning_rate": 1e-05, "epoch": 2.827350427350427, "percentage": 94.37, "elapsed_time": "18:19:29", "remaining_time": "1:05:36"}
127
+ {"current_steps": 1250, "total_steps": 1314, "loss": 0.5393, "learning_rate": 1e-05, "epoch": 2.8501424501424504, "percentage": 95.13, "elapsed_time": "18:28:14", "remaining_time": "0:56:44"}
128
+ {"current_steps": 1260, "total_steps": 1314, "loss": 0.5369, "learning_rate": 1e-05, "epoch": 2.872934472934473, "percentage": 95.89, "elapsed_time": "18:36:58", "remaining_time": "0:47:52"}
129
+ {"current_steps": 1270, "total_steps": 1314, "loss": 0.5381, "learning_rate": 1e-05, "epoch": 2.8957264957264957, "percentage": 96.65, "elapsed_time": "18:45:42", "remaining_time": "0:39:00"}
130
+ {"current_steps": 1280, "total_steps": 1314, "loss": 0.5288, "learning_rate": 1e-05, "epoch": 2.9185185185185185, "percentage": 97.41, "elapsed_time": "18:54:27", "remaining_time": "0:30:08"}
131
+ {"current_steps": 1290, "total_steps": 1314, "loss": 0.5293, "learning_rate": 1e-05, "epoch": 2.9413105413105414, "percentage": 98.17, "elapsed_time": "19:03:10", "remaining_time": "0:21:16"}
132
+ {"current_steps": 1300, "total_steps": 1314, "loss": 0.5303, "learning_rate": 1e-05, "epoch": 2.9641025641025642, "percentage": 98.93, "elapsed_time": "19:11:54", "remaining_time": "0:12:24"}
133
+ {"current_steps": 1310, "total_steps": 1314, "loss": 0.5394, "learning_rate": 1e-05, "epoch": 2.9868945868945866, "percentage": 99.7, "elapsed_time": "19:20:38", "remaining_time": "0:03:32"}