Hugging Face's logo

mlfoundations-dev
/
hp_ablations_qwen_adambeta2_0.9995

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
b0dff9d
•
1 Parent(s): f40fa5b

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 sha256:27ad665f470504e9db848d6dcb809104f181cfc6cf49d32bd33f4f263095a84d
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:607c8c1360fcdac376bd19eebf1ab04ff9f17b555226ed88c1a3a853d9ea437a
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88828ac4a2b80c860ab7cac4c7948ec32aca7f5b7b57e575ce7d7b1b7d15e4eb
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67484f53657314a2e1a9becb76978a84462c0679a354c272e97befd4888ed10b
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a963fd3be8396e15f6a84011744db43c4935d72154621fae1b156ed0a2df811
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:157193333511a347ebe39869b44af8aeb0be870359306f8d7d1bfe57e6d4c1bb
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:731ce75386a65aa48026737f16b75c06aacdfc403ff17a3178d9585b304fab81
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db0c725a92308aa62bf8b67140f961a193d03e260197b21cc6ac14246e4aed3d
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -87,3 +87,47 @@
87
  {"current_steps": 860, "total_steps": 1314, "loss": 0.5987, "learning_rate": 5e-06, "epoch": 1.9606837606837608, "percentage": 65.45, "elapsed_time": "12:42:19", "remaining_time": "6:42:26"}
88
  {"current_steps": 870, "total_steps": 1314, "loss": 0.5961, "learning_rate": 5e-06, "epoch": 1.9834757834757835, "percentage": 66.21, "elapsed_time": "12:51:05", "remaining_time": "6:33:31"}
89
  {"current_steps": 877, "total_steps": 1314, "eval_loss": 0.6187062859535217, "epoch": 1.9994301994301993, "percentage": 66.74, "elapsed_time": "13:04:31", "remaining_time": "6:30:55"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
87
  {"current_steps": 860, "total_steps": 1314, "loss": 0.5987, "learning_rate": 5e-06, "epoch": 1.9606837606837608, "percentage": 65.45, "elapsed_time": "12:42:19", "remaining_time": "6:42:26"}
88
  {"current_steps": 870, "total_steps": 1314, "loss": 0.5961, "learning_rate": 5e-06, "epoch": 1.9834757834757835, "percentage": 66.21, "elapsed_time": "12:51:05", "remaining_time": "6:33:31"}
89
  {"current_steps": 877, "total_steps": 1314, "eval_loss": 0.6187062859535217, "epoch": 1.9994301994301993, "percentage": 66.74, "elapsed_time": "13:04:31", "remaining_time": "6:30:55"}
90
+ {"current_steps": 880, "total_steps": 1314, "loss": 0.6155, "learning_rate": 5e-06, "epoch": 2.006837606837607, "percentage": 66.97, "elapsed_time": "13:08:15", "remaining_time": "6:28:45"}
91
+ {"current_steps": 890, "total_steps": 1314, "loss": 0.5547, "learning_rate": 5e-06, "epoch": 2.0296296296296297, "percentage": 67.73, "elapsed_time": "13:17:02", "remaining_time": "6:19:42"}
92
+ {"current_steps": 900, "total_steps": 1314, "loss": 0.5698, "learning_rate": 5e-06, "epoch": 2.0524216524216525, "percentage": 68.49, "elapsed_time": "13:25:48", "remaining_time": "6:10:40"}
93
+ {"current_steps": 910, "total_steps": 1314, "loss": 0.5679, "learning_rate": 5e-06, "epoch": 2.0752136752136754, "percentage": 69.25, "elapsed_time": "13:34:33", "remaining_time": "6:01:37"}
94
+ {"current_steps": 920, "total_steps": 1314, "loss": 0.571, "learning_rate": 5e-06, "epoch": 2.098005698005698, "percentage": 70.02, "elapsed_time": "13:43:18", "remaining_time": "5:52:35"}
95
+ {"current_steps": 930, "total_steps": 1314, "loss": 0.569, "learning_rate": 5e-06, "epoch": 2.1207977207977207, "percentage": 70.78, "elapsed_time": "13:52:04", "remaining_time": "5:43:33"}
96
+ {"current_steps": 940, "total_steps": 1314, "loss": 0.5637, "learning_rate": 5e-06, "epoch": 2.1435897435897435, "percentage": 71.54, "elapsed_time": "14:00:49", "remaining_time": "5:34:32"}
97
+ {"current_steps": 950, "total_steps": 1314, "loss": 0.5646, "learning_rate": 5e-06, "epoch": 2.1663817663817664, "percentage": 72.3, "elapsed_time": "14:09:37", "remaining_time": "5:25:32"}
98
+ {"current_steps": 960, "total_steps": 1314, "loss": 0.5697, "learning_rate": 5e-06, "epoch": 2.1891737891737892, "percentage": 73.06, "elapsed_time": "14:18:23", "remaining_time": "5:16:32"}
99
+ {"current_steps": 970, "total_steps": 1314, "loss": 0.5691, "learning_rate": 5e-06, "epoch": 2.211965811965812, "percentage": 73.82, "elapsed_time": "14:27:10", "remaining_time": "5:07:32"}
100
+ {"current_steps": 980, "total_steps": 1314, "loss": 0.5588, "learning_rate": 5e-06, "epoch": 2.234757834757835, "percentage": 74.58, "elapsed_time": "14:35:56", "remaining_time": "4:58:32"}
101
+ {"current_steps": 990, "total_steps": 1314, "loss": 0.5678, "learning_rate": 5e-06, "epoch": 2.2575498575498574, "percentage": 75.34, "elapsed_time": "14:44:42", "remaining_time": "4:49:32"}
102
+ {"current_steps": 1000, "total_steps": 1314, "loss": 0.5682, "learning_rate": 5e-06, "epoch": 2.2803418803418802, "percentage": 76.1, "elapsed_time": "14:53:30", "remaining_time": "4:40:33"}
103
+ {"current_steps": 1010, "total_steps": 1314, "loss": 0.5656, "learning_rate": 5e-06, "epoch": 2.303133903133903, "percentage": 76.86, "elapsed_time": "15:02:16", "remaining_time": "4:31:34"}
104
+ {"current_steps": 1020, "total_steps": 1314, "loss": 0.5687, "learning_rate": 5e-06, "epoch": 2.325925925925926, "percentage": 77.63, "elapsed_time": "15:11:02", "remaining_time": "4:22:35"}
105
+ {"current_steps": 1030, "total_steps": 1314, "loss": 0.5699, "learning_rate": 5e-06, "epoch": 2.348717948717949, "percentage": 78.39, "elapsed_time": "15:19:48", "remaining_time": "4:13:37"}
106
+ {"current_steps": 1040, "total_steps": 1314, "loss": 0.568, "learning_rate": 5e-06, "epoch": 2.3715099715099717, "percentage": 79.15, "elapsed_time": "15:28:35", "remaining_time": "4:04:38"}
107
+ {"current_steps": 1050, "total_steps": 1314, "loss": 0.5673, "learning_rate": 5e-06, "epoch": 2.394301994301994, "percentage": 79.91, "elapsed_time": "15:37:21", "remaining_time": "3:55:40"}
108
+ {"current_steps": 1060, "total_steps": 1314, "loss": 0.5756, "learning_rate": 5e-06, "epoch": 2.417094017094017, "percentage": 80.67, "elapsed_time": "15:46:06", "remaining_time": "3:46:42"}
109
+ {"current_steps": 1070, "total_steps": 1314, "loss": 0.5785, "learning_rate": 5e-06, "epoch": 2.43988603988604, "percentage": 81.43, "elapsed_time": "15:54:51", "remaining_time": "3:37:44"}
110
+ {"current_steps": 1080, "total_steps": 1314, "loss": 0.5738, "learning_rate": 5e-06, "epoch": 2.4626780626780627, "percentage": 82.19, "elapsed_time": "16:03:37", "remaining_time": "3:28:47"}
111
+ {"current_steps": 1090, "total_steps": 1314, "loss": 0.5714, "learning_rate": 5e-06, "epoch": 2.4854700854700855, "percentage": 82.95, "elapsed_time": "16:12:23", "remaining_time": "3:19:49"}
112
+ {"current_steps": 1100, "total_steps": 1314, "loss": 0.5778, "learning_rate": 5e-06, "epoch": 2.5082621082621084, "percentage": 83.71, "elapsed_time": "16:21:09", "remaining_time": "3:10:52"}
113
+ {"current_steps": 1110, "total_steps": 1314, "loss": 0.5714, "learning_rate": 5e-06, "epoch": 2.5310541310541312, "percentage": 84.47, "elapsed_time": "16:29:54", "remaining_time": "3:01:55"}
114
+ {"current_steps": 1120, "total_steps": 1314, "loss": 0.5695, "learning_rate": 5e-06, "epoch": 2.5538461538461537, "percentage": 85.24, "elapsed_time": "16:38:41", "remaining_time": "2:52:59"}
115
+ {"current_steps": 1130, "total_steps": 1314, "loss": 0.5689, "learning_rate": 5e-06, "epoch": 2.5766381766381765, "percentage": 86.0, "elapsed_time": "16:47:27", "remaining_time": "2:44:02"}
116
+ {"current_steps": 1140, "total_steps": 1314, "loss": 0.5685, "learning_rate": 5e-06, "epoch": 2.5994301994301994, "percentage": 86.76, "elapsed_time": "16:56:13", "remaining_time": "2:35:06"}
117
+ {"current_steps": 1150, "total_steps": 1314, "loss": 0.5688, "learning_rate": 5e-06, "epoch": 2.6222222222222222, "percentage": 87.52, "elapsed_time": "17:04:59", "remaining_time": "2:26:10"}
118
+ {"current_steps": 1160, "total_steps": 1314, "loss": 0.57, "learning_rate": 5e-06, "epoch": 2.645014245014245, "percentage": 88.28, "elapsed_time": "17:13:45", "remaining_time": "2:17:14"}
119
+ {"current_steps": 1170, "total_steps": 1314, "loss": 0.5728, "learning_rate": 5e-06, "epoch": 2.667806267806268, "percentage": 89.04, "elapsed_time": "17:22:30", "remaining_time": "2:08:18"}
120
+ {"current_steps": 1180, "total_steps": 1314, "loss": 0.5679, "learning_rate": 5e-06, "epoch": 2.690598290598291, "percentage": 89.8, "elapsed_time": "17:31:16", "remaining_time": "1:59:22"}
121
+ {"current_steps": 1190, "total_steps": 1314, "loss": 0.569, "learning_rate": 5e-06, "epoch": 2.7133903133903132, "percentage": 90.56, "elapsed_time": "17:40:01", "remaining_time": "1:50:27"}
122
+ {"current_steps": 1200, "total_steps": 1314, "loss": 0.5722, "learning_rate": 5e-06, "epoch": 2.736182336182336, "percentage": 91.32, "elapsed_time": "17:48:46", "remaining_time": "1:41:32"}
123
+ {"current_steps": 1210, "total_steps": 1314, "loss": 0.5756, "learning_rate": 5e-06, "epoch": 2.758974358974359, "percentage": 92.09, "elapsed_time": "17:57:32", "remaining_time": "1:32:36"}
124
+ {"current_steps": 1220, "total_steps": 1314, "loss": 0.5654, "learning_rate": 5e-06, "epoch": 2.781766381766382, "percentage": 92.85, "elapsed_time": "18:06:18", "remaining_time": "1:23:41"}
125
+ {"current_steps": 1230, "total_steps": 1314, "loss": 0.5639, "learning_rate": 5e-06, "epoch": 2.8045584045584047, "percentage": 93.61, "elapsed_time": "18:15:03", "remaining_time": "1:14:47"}
126
+ {"current_steps": 1240, "total_steps": 1314, "loss": 0.5787, "learning_rate": 5e-06, "epoch": 2.827350427350427, "percentage": 94.37, "elapsed_time": "18:23:49", "remaining_time": "1:05:52"}
127
+ {"current_steps": 1250, "total_steps": 1314, "loss": 0.5754, "learning_rate": 5e-06, "epoch": 2.8501424501424504, "percentage": 95.13, "elapsed_time": "18:32:34", "remaining_time": "0:56:57"}
128
+ {"current_steps": 1260, "total_steps": 1314, "loss": 0.5725, "learning_rate": 5e-06, "epoch": 2.872934472934473, "percentage": 95.89, "elapsed_time": "18:41:20", "remaining_time": "0:48:03"}
129
+ {"current_steps": 1270, "total_steps": 1314, "loss": 0.5735, "learning_rate": 5e-06, "epoch": 2.8957264957264957, "percentage": 96.65, "elapsed_time": "18:50:06", "remaining_time": "0:39:09"}
130
+ {"current_steps": 1280, "total_steps": 1314, "loss": 0.5637, "learning_rate": 5e-06, "epoch": 2.9185185185185185, "percentage": 97.41, "elapsed_time": "18:58:52", "remaining_time": "0:30:15"}
131
+ {"current_steps": 1290, "total_steps": 1314, "loss": 0.5639, "learning_rate": 5e-06, "epoch": 2.9413105413105414, "percentage": 98.17, "elapsed_time": "19:07:37", "remaining_time": "0:21:21"}
132
+ {"current_steps": 1300, "total_steps": 1314, "loss": 0.5651, "learning_rate": 5e-06, "epoch": 2.9641025641025642, "percentage": 98.93, "elapsed_time": "19:16:23", "remaining_time": "0:12:27"}
133
+ {"current_steps": 1310, "total_steps": 1314, "loss": 0.5749, "learning_rate": 5e-06, "epoch": 2.9868945868945866, "percentage": 99.7, "elapsed_time": "19:25:09", "remaining_time": "0:03:33"}