Hugging Face's logo

mlfoundations-dev
/
hp_ablations_qwen_adambeta2_0.99

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
25a3e02
•
1 Parent(s): 557d104

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:ab605ab6c73fad891e68f19e6f227d53aa7909386c9861363b08b606831d4c5d
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:178dfba1eed306134fde295021a7a80f77b40e922d92ee64164205c334650a5d
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b71bdae2f575cdf517363dd9db8bbd9a5991a21587febad63cc60afc8d2b4cf
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2c37c461422899bb84f33257913e2bc59526cb72d6124be41a6cc3980884ab8
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:c3fcf1eb4155ce9844bb5bcd6bd40aecfc4e3e3f0b0277a211bef37faf71bfef
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d986a97f15bf3ea019adb9d4303570374bcbd0694bdaeb842fd18e8ebfe918e
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:bb25dcff97957e838f032553f68605723f2fcce7a6370936d14800c75e453ab3
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f49bac7df1fc70dd989d10937b57759695e082a22286d5ca3593b86344a9e912
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -87,3 +87,47 @@
87
  {"current_steps": 860, "total_steps": 1314, "loss": 0.5988, "learning_rate": 5e-06, "epoch": 1.9606837606837608, "percentage": 65.45, "elapsed_time": "12:37:43", "remaining_time": "6:40:00"}
88
  {"current_steps": 870, "total_steps": 1314, "loss": 0.5962, "learning_rate": 5e-06, "epoch": 1.9834757834757835, "percentage": 66.21, "elapsed_time": "12:46:27", "remaining_time": "6:31:09"}
89
  {"current_steps": 877, "total_steps": 1314, "eval_loss": 0.6187435388565063, "epoch": 1.9994301994301993, "percentage": 66.74, "elapsed_time": "12:59:52", "remaining_time": "6:28:36"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
87
  {"current_steps": 860, "total_steps": 1314, "loss": 0.5988, "learning_rate": 5e-06, "epoch": 1.9606837606837608, "percentage": 65.45, "elapsed_time": "12:37:43", "remaining_time": "6:40:00"}
88
  {"current_steps": 870, "total_steps": 1314, "loss": 0.5962, "learning_rate": 5e-06, "epoch": 1.9834757834757835, "percentage": 66.21, "elapsed_time": "12:46:27", "remaining_time": "6:31:09"}
89
  {"current_steps": 877, "total_steps": 1314, "eval_loss": 0.6187435388565063, "epoch": 1.9994301994301993, "percentage": 66.74, "elapsed_time": "12:59:52", "remaining_time": "6:28:36"}
90
+ {"current_steps": 880, "total_steps": 1314, "loss": 0.6157, "learning_rate": 5e-06, "epoch": 2.006837606837607, "percentage": 66.97, "elapsed_time": "13:03:37", "remaining_time": "6:26:28"}
91
+ {"current_steps": 890, "total_steps": 1314, "loss": 0.5552, "learning_rate": 5e-06, "epoch": 2.0296296296296297, "percentage": 67.73, "elapsed_time": "13:12:20", "remaining_time": "6:17:28"}
92
+ {"current_steps": 900, "total_steps": 1314, "loss": 0.5703, "learning_rate": 5e-06, "epoch": 2.0524216524216525, "percentage": 68.49, "elapsed_time": "13:21:04", "remaining_time": "6:08:29"}
93
+ {"current_steps": 910, "total_steps": 1314, "loss": 0.5684, "learning_rate": 5e-06, "epoch": 2.0752136752136754, "percentage": 69.25, "elapsed_time": "13:29:48", "remaining_time": "5:59:31"}
94
+ {"current_steps": 920, "total_steps": 1314, "loss": 0.5715, "learning_rate": 5e-06, "epoch": 2.098005698005698, "percentage": 70.02, "elapsed_time": "13:38:31", "remaining_time": "5:50:32"}
95
+ {"current_steps": 930, "total_steps": 1314, "loss": 0.5695, "learning_rate": 5e-06, "epoch": 2.1207977207977207, "percentage": 70.78, "elapsed_time": "13:47:13", "remaining_time": "5:41:34"}
96
+ {"current_steps": 940, "total_steps": 1314, "loss": 0.5642, "learning_rate": 5e-06, "epoch": 2.1435897435897435, "percentage": 71.54, "elapsed_time": "13:55:57", "remaining_time": "5:32:36"}
97
+ {"current_steps": 950, "total_steps": 1314, "loss": 0.5651, "learning_rate": 5e-06, "epoch": 2.1663817663817664, "percentage": 72.3, "elapsed_time": "14:04:40", "remaining_time": "5:23:38"}
98
+ {"current_steps": 960, "total_steps": 1314, "loss": 0.5702, "learning_rate": 5e-06, "epoch": 2.1891737891737892, "percentage": 73.06, "elapsed_time": "14:13:22", "remaining_time": "5:14:40"}
99
+ {"current_steps": 970, "total_steps": 1314, "loss": 0.5696, "learning_rate": 5e-06, "epoch": 2.211965811965812, "percentage": 73.82, "elapsed_time": "14:22:05", "remaining_time": "5:05:44"}
100
+ {"current_steps": 980, "total_steps": 1314, "loss": 0.5592, "learning_rate": 5e-06, "epoch": 2.234757834757835, "percentage": 74.58, "elapsed_time": "14:30:48", "remaining_time": "4:56:47"}
101
+ {"current_steps": 990, "total_steps": 1314, "loss": 0.5683, "learning_rate": 5e-06, "epoch": 2.2575498575498574, "percentage": 75.34, "elapsed_time": "14:39:31", "remaining_time": "4:47:50"}
102
+ {"current_steps": 1000, "total_steps": 1314, "loss": 0.5686, "learning_rate": 5e-06, "epoch": 2.2803418803418802, "percentage": 76.1, "elapsed_time": "14:48:13", "remaining_time": "4:38:54"}
103
+ {"current_steps": 1010, "total_steps": 1314, "loss": 0.5661, "learning_rate": 5e-06, "epoch": 2.303133903133903, "percentage": 76.86, "elapsed_time": "14:56:55", "remaining_time": "4:29:57"}
104
+ {"current_steps": 1020, "total_steps": 1314, "loss": 0.5691, "learning_rate": 5e-06, "epoch": 2.325925925925926, "percentage": 77.63, "elapsed_time": "15:05:39", "remaining_time": "4:21:02"}
105
+ {"current_steps": 1030, "total_steps": 1314, "loss": 0.5704, "learning_rate": 5e-06, "epoch": 2.348717948717949, "percentage": 78.39, "elapsed_time": "15:14:21", "remaining_time": "4:12:06"}
106
+ {"current_steps": 1040, "total_steps": 1314, "loss": 0.5683, "learning_rate": 5e-06, "epoch": 2.3715099715099717, "percentage": 79.15, "elapsed_time": "15:23:04", "remaining_time": "4:03:11"}
107
+ {"current_steps": 1050, "total_steps": 1314, "loss": 0.5677, "learning_rate": 5e-06, "epoch": 2.394301994301994, "percentage": 79.91, "elapsed_time": "15:31:47", "remaining_time": "3:54:16"}
108
+ {"current_steps": 1060, "total_steps": 1314, "loss": 0.576, "learning_rate": 5e-06, "epoch": 2.417094017094017, "percentage": 80.67, "elapsed_time": "15:40:30", "remaining_time": "3:45:21"}
109
+ {"current_steps": 1070, "total_steps": 1314, "loss": 0.5788, "learning_rate": 5e-06, "epoch": 2.43988603988604, "percentage": 81.43, "elapsed_time": "15:49:12", "remaining_time": "3:36:27"}
110
+ {"current_steps": 1080, "total_steps": 1314, "loss": 0.5741, "learning_rate": 5e-06, "epoch": 2.4626780626780627, "percentage": 82.19, "elapsed_time": "15:57:55", "remaining_time": "3:27:32"}
111
+ {"current_steps": 1090, "total_steps": 1314, "loss": 0.5718, "learning_rate": 5e-06, "epoch": 2.4854700854700855, "percentage": 82.95, "elapsed_time": "16:06:37", "remaining_time": "3:18:38"}
112
+ {"current_steps": 1100, "total_steps": 1314, "loss": 0.5782, "learning_rate": 5e-06, "epoch": 2.5082621082621084, "percentage": 83.71, "elapsed_time": "16:15:20", "remaining_time": "3:09:44"}
113
+ {"current_steps": 1110, "total_steps": 1314, "loss": 0.5717, "learning_rate": 5e-06, "epoch": 2.5310541310541312, "percentage": 84.47, "elapsed_time": "16:24:03", "remaining_time": "3:00:51"}
114
+ {"current_steps": 1120, "total_steps": 1314, "loss": 0.5698, "learning_rate": 5e-06, "epoch": 2.5538461538461537, "percentage": 85.24, "elapsed_time": "16:32:47", "remaining_time": "2:51:57"}
115
+ {"current_steps": 1130, "total_steps": 1314, "loss": 0.5693, "learning_rate": 5e-06, "epoch": 2.5766381766381765, "percentage": 86.0, "elapsed_time": "16:41:30", "remaining_time": "2:43:04"}
116
+ {"current_steps": 1140, "total_steps": 1314, "loss": 0.5689, "learning_rate": 5e-06, "epoch": 2.5994301994301994, "percentage": 86.76, "elapsed_time": "16:50:12", "remaining_time": "2:34:11"}
117
+ {"current_steps": 1150, "total_steps": 1314, "loss": 0.5692, "learning_rate": 5e-06, "epoch": 2.6222222222222222, "percentage": 87.52, "elapsed_time": "16:58:55", "remaining_time": "2:25:18"}
118
+ {"current_steps": 1160, "total_steps": 1314, "loss": 0.5703, "learning_rate": 5e-06, "epoch": 2.645014245014245, "percentage": 88.28, "elapsed_time": "17:07:37", "remaining_time": "2:16:25"}
119
+ {"current_steps": 1170, "total_steps": 1314, "loss": 0.5731, "learning_rate": 5e-06, "epoch": 2.667806267806268, "percentage": 89.04, "elapsed_time": "17:16:20", "remaining_time": "2:07:32"}
120
+ {"current_steps": 1180, "total_steps": 1314, "loss": 0.5682, "learning_rate": 5e-06, "epoch": 2.690598290598291, "percentage": 89.8, "elapsed_time": "17:25:03", "remaining_time": "1:58:40"}
121
+ {"current_steps": 1190, "total_steps": 1314, "loss": 0.5694, "learning_rate": 5e-06, "epoch": 2.7133903133903132, "percentage": 90.56, "elapsed_time": "17:33:45", "remaining_time": "1:49:48"}
122
+ {"current_steps": 1200, "total_steps": 1314, "loss": 0.5725, "learning_rate": 5e-06, "epoch": 2.736182336182336, "percentage": 91.32, "elapsed_time": "17:42:28", "remaining_time": "1:40:56"}
123
+ {"current_steps": 1210, "total_steps": 1314, "loss": 0.5759, "learning_rate": 5e-06, "epoch": 2.758974358974359, "percentage": 92.09, "elapsed_time": "17:51:12", "remaining_time": "1:32:04"}
124
+ {"current_steps": 1220, "total_steps": 1314, "loss": 0.5658, "learning_rate": 5e-06, "epoch": 2.781766381766382, "percentage": 92.85, "elapsed_time": "17:59:55", "remaining_time": "1:23:12"}
125
+ {"current_steps": 1230, "total_steps": 1314, "loss": 0.5643, "learning_rate": 5e-06, "epoch": 2.8045584045584047, "percentage": 93.61, "elapsed_time": "18:08:39", "remaining_time": "1:14:20"}
126
+ {"current_steps": 1240, "total_steps": 1314, "loss": 0.5791, "learning_rate": 5e-06, "epoch": 2.827350427350427, "percentage": 94.37, "elapsed_time": "18:17:23", "remaining_time": "1:05:29"}
127
+ {"current_steps": 1250, "total_steps": 1314, "loss": 0.5757, "learning_rate": 5e-06, "epoch": 2.8501424501424504, "percentage": 95.13, "elapsed_time": "18:26:06", "remaining_time": "0:56:37"}
128
+ {"current_steps": 1260, "total_steps": 1314, "loss": 0.5729, "learning_rate": 5e-06, "epoch": 2.872934472934473, "percentage": 95.89, "elapsed_time": "18:34:49", "remaining_time": "0:47:46"}
129
+ {"current_steps": 1270, "total_steps": 1314, "loss": 0.5739, "learning_rate": 5e-06, "epoch": 2.8957264957264957, "percentage": 96.65, "elapsed_time": "18:43:33", "remaining_time": "0:38:55"}
130
+ {"current_steps": 1280, "total_steps": 1314, "loss": 0.5641, "learning_rate": 5e-06, "epoch": 2.9185185185185185, "percentage": 97.41, "elapsed_time": "18:52:16", "remaining_time": "0:30:04"}
131
+ {"current_steps": 1290, "total_steps": 1314, "loss": 0.5643, "learning_rate": 5e-06, "epoch": 2.9413105413105414, "percentage": 98.17, "elapsed_time": "19:00:59", "remaining_time": "0:21:13"}
132
+ {"current_steps": 1300, "total_steps": 1314, "loss": 0.5654, "learning_rate": 5e-06, "epoch": 2.9641025641025642, "percentage": 98.93, "elapsed_time": "19:09:42", "remaining_time": "0:12:22"}
133
+ {"current_steps": 1310, "total_steps": 1314, "loss": 0.5752, "learning_rate": 5e-06, "epoch": 2.9868945868945866, "percentage": 99.7, "elapsed_time": "19:18:24", "remaining_time": "0:03:32"}