Hugging Face's logo

mlfoundations-dev
/
hp_ablations_qwen_adambeta1_0.92

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
b6bebf1
·
verified ·
1 Parent(s): c1d7876

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:ae5ced109ab97c008e02f54ac1e9efc78b8d7b040f1dfbb5d93e808f6628b124
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:736b47150c73e76021d342446e76f13d54809b649fe02511949f44a2136f8d1d
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c8668dab4ddb1006a496044e4f84b8c0d0f34117619a291813c24d9710b02de
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9ec313fe22250a4d8575fbc43c5bc0025d6bdb600c6acc7b943c23bd4023d24
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00357ba79a1d9d7664c649bef84700bfd6ca387ad6693f5ebdafd183fcd720f6
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ce2ee6875687e5cff8f9ac96f2dee1c9c69252c445145942f17624d97feda2f
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:a5cbc9cb7c4155926a24c0a08183ebb25efbb08036516368385768ba4d7f207f
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7999ed667dfac151512cadedce0137d089fcd3c58d0cd7f94247c6a70d29f8d4
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -87,3 +87,47 @@
87
  {"current_steps": 860, "total_steps": 1314, "loss": 0.5986, "learning_rate": 5e-06, "epoch": 1.9606837606837608, "percentage": 65.45, "elapsed_time": "12:46:10", "remaining_time": "6:44:28"}
88
  {"current_steps": 870, "total_steps": 1314, "loss": 0.5961, "learning_rate": 5e-06, "epoch": 1.9834757834757835, "percentage": 66.21, "elapsed_time": "12:54:58", "remaining_time": "6:35:30"}
89
  {"current_steps": 877, "total_steps": 1314, "eval_loss": 0.6187193393707275, "epoch": 1.9994301994301993, "percentage": 66.74, "elapsed_time": "13:08:28", "remaining_time": "6:32:53"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
87
  {"current_steps": 860, "total_steps": 1314, "loss": 0.5986, "learning_rate": 5e-06, "epoch": 1.9606837606837608, "percentage": 65.45, "elapsed_time": "12:46:10", "remaining_time": "6:44:28"}
88
  {"current_steps": 870, "total_steps": 1314, "loss": 0.5961, "learning_rate": 5e-06, "epoch": 1.9834757834757835, "percentage": 66.21, "elapsed_time": "12:54:58", "remaining_time": "6:35:30"}
89
  {"current_steps": 877, "total_steps": 1314, "eval_loss": 0.6187193393707275, "epoch": 1.9994301994301993, "percentage": 66.74, "elapsed_time": "13:08:28", "remaining_time": "6:32:53"}
90
+ {"current_steps": 880, "total_steps": 1314, "loss": 0.6154, "learning_rate": 5e-06, "epoch": 2.006837606837607, "percentage": 66.97, "elapsed_time": "13:12:15", "remaining_time": "6:30:43"}
91
+ {"current_steps": 890, "total_steps": 1314, "loss": 0.5547, "learning_rate": 5e-06, "epoch": 2.0296296296296297, "percentage": 67.73, "elapsed_time": "13:21:05", "remaining_time": "6:21:38"}
92
+ {"current_steps": 900, "total_steps": 1314, "loss": 0.5697, "learning_rate": 5e-06, "epoch": 2.0524216524216525, "percentage": 68.49, "elapsed_time": "13:29:53", "remaining_time": "6:12:33"}
93
+ {"current_steps": 910, "total_steps": 1314, "loss": 0.5678, "learning_rate": 5e-06, "epoch": 2.0752136752136754, "percentage": 69.25, "elapsed_time": "13:38:41", "remaining_time": "6:03:27"}
94
+ {"current_steps": 920, "total_steps": 1314, "loss": 0.5709, "learning_rate": 5e-06, "epoch": 2.098005698005698, "percentage": 70.02, "elapsed_time": "13:47:29", "remaining_time": "5:54:23"}
95
+ {"current_steps": 930, "total_steps": 1314, "loss": 0.569, "learning_rate": 5e-06, "epoch": 2.1207977207977207, "percentage": 70.78, "elapsed_time": "13:56:17", "remaining_time": "5:45:18"}
96
+ {"current_steps": 940, "total_steps": 1314, "loss": 0.5636, "learning_rate": 5e-06, "epoch": 2.1435897435897435, "percentage": 71.54, "elapsed_time": "14:05:06", "remaining_time": "5:36:14"}
97
+ {"current_steps": 950, "total_steps": 1314, "loss": 0.5646, "learning_rate": 5e-06, "epoch": 2.1663817663817664, "percentage": 72.3, "elapsed_time": "14:13:55", "remaining_time": "5:27:11"}
98
+ {"current_steps": 960, "total_steps": 1314, "loss": 0.5696, "learning_rate": 5e-06, "epoch": 2.1891737891737892, "percentage": 73.06, "elapsed_time": "14:22:40", "remaining_time": "5:18:06"}
99
+ {"current_steps": 970, "total_steps": 1314, "loss": 0.569, "learning_rate": 5e-06, "epoch": 2.211965811965812, "percentage": 73.82, "elapsed_time": "14:31:28", "remaining_time": "5:09:03"}
100
+ {"current_steps": 980, "total_steps": 1314, "loss": 0.5587, "learning_rate": 5e-06, "epoch": 2.234757834757835, "percentage": 74.58, "elapsed_time": "14:40:15", "remaining_time": "5:00:00"}
101
+ {"current_steps": 990, "total_steps": 1314, "loss": 0.5678, "learning_rate": 5e-06, "epoch": 2.2575498575498574, "percentage": 75.34, "elapsed_time": "14:49:02", "remaining_time": "4:50:57"}
102
+ {"current_steps": 1000, "total_steps": 1314, "loss": 0.568, "learning_rate": 5e-06, "epoch": 2.2803418803418802, "percentage": 76.1, "elapsed_time": "14:57:51", "remaining_time": "4:41:55"}
103
+ {"current_steps": 1010, "total_steps": 1314, "loss": 0.5655, "learning_rate": 5e-06, "epoch": 2.303133903133903, "percentage": 76.86, "elapsed_time": "15:06:39", "remaining_time": "4:32:53"}
104
+ {"current_steps": 1020, "total_steps": 1314, "loss": 0.5686, "learning_rate": 5e-06, "epoch": 2.325925925925926, "percentage": 77.63, "elapsed_time": "15:15:27", "remaining_time": "4:23:52"}
105
+ {"current_steps": 1030, "total_steps": 1314, "loss": 0.5699, "learning_rate": 5e-06, "epoch": 2.348717948717949, "percentage": 78.39, "elapsed_time": "15:24:16", "remaining_time": "4:14:50"}
106
+ {"current_steps": 1040, "total_steps": 1314, "loss": 0.5679, "learning_rate": 5e-06, "epoch": 2.3715099715099717, "percentage": 79.15, "elapsed_time": "15:33:05", "remaining_time": "4:05:49"}
107
+ {"current_steps": 1050, "total_steps": 1314, "loss": 0.5672, "learning_rate": 5e-06, "epoch": 2.394301994301994, "percentage": 79.91, "elapsed_time": "15:41:50", "remaining_time": "3:56:48"}
108
+ {"current_steps": 1060, "total_steps": 1314, "loss": 0.5755, "learning_rate": 5e-06, "epoch": 2.417094017094017, "percentage": 80.67, "elapsed_time": "15:50:38", "remaining_time": "3:47:47"}
109
+ {"current_steps": 1070, "total_steps": 1314, "loss": 0.5784, "learning_rate": 5e-06, "epoch": 2.43988603988604, "percentage": 81.43, "elapsed_time": "15:59:27", "remaining_time": "3:38:47"}
110
+ {"current_steps": 1080, "total_steps": 1314, "loss": 0.5737, "learning_rate": 5e-06, "epoch": 2.4626780626780627, "percentage": 82.19, "elapsed_time": "16:08:14", "remaining_time": "3:29:47"}
111
+ {"current_steps": 1090, "total_steps": 1314, "loss": 0.5713, "learning_rate": 5e-06, "epoch": 2.4854700854700855, "percentage": 82.95, "elapsed_time": "16:17:02", "remaining_time": "3:20:47"}
112
+ {"current_steps": 1100, "total_steps": 1314, "loss": 0.5777, "learning_rate": 5e-06, "epoch": 2.5082621082621084, "percentage": 83.71, "elapsed_time": "16:25:49", "remaining_time": "3:11:47"}
113
+ {"current_steps": 1110, "total_steps": 1314, "loss": 0.5713, "learning_rate": 5e-06, "epoch": 2.5310541310541312, "percentage": 84.47, "elapsed_time": "16:34:36", "remaining_time": "3:02:47"}
114
+ {"current_steps": 1120, "total_steps": 1314, "loss": 0.5694, "learning_rate": 5e-06, "epoch": 2.5538461538461537, "percentage": 85.24, "elapsed_time": "16:43:23", "remaining_time": "2:53:48"}
115
+ {"current_steps": 1130, "total_steps": 1314, "loss": 0.5688, "learning_rate": 5e-06, "epoch": 2.5766381766381765, "percentage": 86.0, "elapsed_time": "16:52:12", "remaining_time": "2:44:49"}
116
+ {"current_steps": 1140, "total_steps": 1314, "loss": 0.5685, "learning_rate": 5e-06, "epoch": 2.5994301994301994, "percentage": 86.76, "elapsed_time": "17:01:01", "remaining_time": "2:35:50"}
117
+ {"current_steps": 1150, "total_steps": 1314, "loss": 0.5688, "learning_rate": 5e-06, "epoch": 2.6222222222222222, "percentage": 87.52, "elapsed_time": "17:09:50", "remaining_time": "2:26:51"}
118
+ {"current_steps": 1160, "total_steps": 1314, "loss": 0.5699, "learning_rate": 5e-06, "epoch": 2.645014245014245, "percentage": 88.28, "elapsed_time": "17:18:39", "remaining_time": "2:17:53"}
119
+ {"current_steps": 1170, "total_steps": 1314, "loss": 0.5727, "learning_rate": 5e-06, "epoch": 2.667806267806268, "percentage": 89.04, "elapsed_time": "17:27:28", "remaining_time": "2:08:55"}
120
+ {"current_steps": 1180, "total_steps": 1314, "loss": 0.5678, "learning_rate": 5e-06, "epoch": 2.690598290598291, "percentage": 89.8, "elapsed_time": "17:36:15", "remaining_time": "1:59:56"}
121
+ {"current_steps": 1190, "total_steps": 1314, "loss": 0.5689, "learning_rate": 5e-06, "epoch": 2.7133903133903132, "percentage": 90.56, "elapsed_time": "17:45:05", "remaining_time": "1:50:59"}
122
+ {"current_steps": 1200, "total_steps": 1314, "loss": 0.5721, "learning_rate": 5e-06, "epoch": 2.736182336182336, "percentage": 91.32, "elapsed_time": "17:53:54", "remaining_time": "1:42:01"}
123
+ {"current_steps": 1210, "total_steps": 1314, "loss": 0.5755, "learning_rate": 5e-06, "epoch": 2.758974358974359, "percentage": 92.09, "elapsed_time": "18:02:43", "remaining_time": "1:33:03"}
124
+ {"current_steps": 1220, "total_steps": 1314, "loss": 0.5654, "learning_rate": 5e-06, "epoch": 2.781766381766382, "percentage": 92.85, "elapsed_time": "18:11:31", "remaining_time": "1:24:06"}
125
+ {"current_steps": 1230, "total_steps": 1314, "loss": 0.5639, "learning_rate": 5e-06, "epoch": 2.8045584045584047, "percentage": 93.61, "elapsed_time": "18:20:19", "remaining_time": "1:15:08"}
126
+ {"current_steps": 1240, "total_steps": 1314, "loss": 0.5787, "learning_rate": 5e-06, "epoch": 2.827350427350427, "percentage": 94.37, "elapsed_time": "18:29:08", "remaining_time": "1:06:11"}
127
+ {"current_steps": 1250, "total_steps": 1314, "loss": 0.5753, "learning_rate": 5e-06, "epoch": 2.8501424501424504, "percentage": 95.13, "elapsed_time": "18:37:56", "remaining_time": "0:57:14"}
128
+ {"current_steps": 1260, "total_steps": 1314, "loss": 0.5725, "learning_rate": 5e-06, "epoch": 2.872934472934473, "percentage": 95.89, "elapsed_time": "18:46:44", "remaining_time": "0:48:17"}
129
+ {"current_steps": 1270, "total_steps": 1314, "loss": 0.5735, "learning_rate": 5e-06, "epoch": 2.8957264957264957, "percentage": 96.65, "elapsed_time": "18:55:32", "remaining_time": "0:39:20"}
130
+ {"current_steps": 1280, "total_steps": 1314, "loss": 0.5637, "learning_rate": 5e-06, "epoch": 2.9185185185185185, "percentage": 97.41, "elapsed_time": "19:04:20", "remaining_time": "0:30:23"}
131
+ {"current_steps": 1290, "total_steps": 1314, "loss": 0.5639, "learning_rate": 5e-06, "epoch": 2.9413105413105414, "percentage": 98.17, "elapsed_time": "19:13:06", "remaining_time": "0:21:27"}
132
+ {"current_steps": 1300, "total_steps": 1314, "loss": 0.565, "learning_rate": 5e-06, "epoch": 2.9641025641025642, "percentage": 98.93, "elapsed_time": "19:21:54", "remaining_time": "0:12:30"}
133
+ {"current_steps": 1310, "total_steps": 1314, "loss": 0.5748, "learning_rate": 5e-06, "epoch": 2.9868945868945866, "percentage": 99.7, "elapsed_time": "19:30:43", "remaining_time": "0:03:34"}