Hugging Face's logo

mlfoundations-dev
/
hp_ablations_gemma_adambeta2_0.95

Text Generation
Transformers
Safetensors
gemma2
llama-factory
full
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
4dd7818
·
verified ·
1 Parent(s): 4fea40b

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 sha256:2858bdf0313445d0c64c98fa6cfa71dd1c9724dcd6f072b94ea247654a077279
3
  size 4903351912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06033aace4b61267e9df01b42e30f1ef340d2a3ec96db77846048f4f5a98ef52
3
  size 4903351912
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be4acbd177d4252e5f3a492fb61f0387090bbe332fe8bc8ac5cf2eb11eeaa984
3
  size 4947570872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ec4a6f0957cea11eb331f50fd2df341cb94d75ca37edee13ec7ff3ccd66602d
3
  size 4947570872
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2524cc26e222252c24c43b8cbd30731135b17905e0c4d448ee74ecb3fa45231a
3
  size 4962221464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0a5d55431ac3108afb4dc91f30dd02383f7ecf23d54d5b8490dd1450c27b93e
3
  size 4962221464
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bbeed37582edf11b0ee5eea36ebacaa3540dbc33d4bb807c4a42f99dcf3159d
3
  size 3670322200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a46a8f5f9868f5ffaff6818322487a05fdd3742c3cf36ec25e38dc06debe6566
3
  size 3670322200
trainer_log.jsonl CHANGED
@@ -88,3 +88,47 @@
88
  {"current_steps": 870, "total_steps": 1329, "loss": 0.5449, "learning_rate": 5e-06, "epoch": 1.9633286318758816, "percentage": 65.46, "elapsed_time": "21:55:55", "remaining_time": "11:34:15"}
89
  {"current_steps": 880, "total_steps": 1329, "loss": 0.5431, "learning_rate": 5e-06, "epoch": 1.9858956276445698, "percentage": 66.22, "elapsed_time": "22:10:54", "remaining_time": "11:19:03"}
90
  {"current_steps": 886, "total_steps": 1329, "eval_loss": 0.587314784526825, "epoch": 1.9994358251057829, "percentage": 66.67, "elapsed_time": "22:31:50", "remaining_time": "11:15:55"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
88
  {"current_steps": 870, "total_steps": 1329, "loss": 0.5449, "learning_rate": 5e-06, "epoch": 1.9633286318758816, "percentage": 65.46, "elapsed_time": "21:55:55", "remaining_time": "11:34:15"}
89
  {"current_steps": 880, "total_steps": 1329, "loss": 0.5431, "learning_rate": 5e-06, "epoch": 1.9858956276445698, "percentage": 66.22, "elapsed_time": "22:10:54", "remaining_time": "11:19:03"}
90
  {"current_steps": 886, "total_steps": 1329, "eval_loss": 0.587314784526825, "epoch": 1.9994358251057829, "percentage": 66.67, "elapsed_time": "22:31:50", "remaining_time": "11:15:55"}
91
+ {"current_steps": 890, "total_steps": 1329, "loss": 0.567, "learning_rate": 5e-06, "epoch": 2.008462623413258, "percentage": 66.97, "elapsed_time": "22:38:50", "remaining_time": "11:10:15"}
92
+ {"current_steps": 900, "total_steps": 1329, "loss": 0.4782, "learning_rate": 5e-06, "epoch": 2.0310296191819464, "percentage": 67.72, "elapsed_time": "22:53:50", "remaining_time": "10:54:52"}
93
+ {"current_steps": 910, "total_steps": 1329, "loss": 0.4798, "learning_rate": 5e-06, "epoch": 2.0535966149506346, "percentage": 68.47, "elapsed_time": "23:08:51", "remaining_time": "10:39:29"}
94
+ {"current_steps": 920, "total_steps": 1329, "loss": 0.4721, "learning_rate": 5e-06, "epoch": 2.076163610719323, "percentage": 69.22, "elapsed_time": "23:23:52", "remaining_time": "10:24:06"}
95
+ {"current_steps": 930, "total_steps": 1329, "loss": 0.4792, "learning_rate": 5e-06, "epoch": 2.098730606488011, "percentage": 69.98, "elapsed_time": "23:38:53", "remaining_time": "10:08:44"}
96
+ {"current_steps": 940, "total_steps": 1329, "loss": 0.4833, "learning_rate": 5e-06, "epoch": 2.1212976022566994, "percentage": 70.73, "elapsed_time": "23:53:53", "remaining_time": "9:53:23"}
97
+ {"current_steps": 950, "total_steps": 1329, "loss": 0.485, "learning_rate": 5e-06, "epoch": 2.143864598025388, "percentage": 71.48, "elapsed_time": "1 day, 0:08:53", "remaining_time": "9:38:01"}
98
+ {"current_steps": 960, "total_steps": 1329, "loss": 0.4811, "learning_rate": 5e-06, "epoch": 2.1664315937940763, "percentage": 72.23, "elapsed_time": "1 day, 0:23:53", "remaining_time": "9:22:41"}
99
+ {"current_steps": 970, "total_steps": 1329, "loss": 0.4792, "learning_rate": 5e-06, "epoch": 2.1889985895627646, "percentage": 72.99, "elapsed_time": "1 day, 0:38:55", "remaining_time": "9:07:21"}
100
+ {"current_steps": 980, "total_steps": 1329, "loss": 0.4741, "learning_rate": 5e-06, "epoch": 2.211565585331453, "percentage": 73.74, "elapsed_time": "1 day, 0:53:56", "remaining_time": "8:52:01"}
101
+ {"current_steps": 990, "total_steps": 1329, "loss": 0.4741, "learning_rate": 5e-06, "epoch": 2.234132581100141, "percentage": 74.49, "elapsed_time": "1 day, 1:08:55", "remaining_time": "8:36:41"}
102
+ {"current_steps": 1000, "total_steps": 1329, "loss": 0.4829, "learning_rate": 5e-06, "epoch": 2.2566995768688294, "percentage": 75.24, "elapsed_time": "1 day, 1:23:55", "remaining_time": "8:21:22"}
103
+ {"current_steps": 1010, "total_steps": 1329, "loss": 0.4892, "learning_rate": 5e-06, "epoch": 2.2792665726375176, "percentage": 76.0, "elapsed_time": "1 day, 1:38:55", "remaining_time": "8:06:03"}
104
+ {"current_steps": 1020, "total_steps": 1329, "loss": 0.4835, "learning_rate": 5e-06, "epoch": 2.301833568406206, "percentage": 76.75, "elapsed_time": "1 day, 1:53:55", "remaining_time": "7:50:44"}
105
+ {"current_steps": 1030, "total_steps": 1329, "loss": 0.4877, "learning_rate": 5e-06, "epoch": 2.324400564174894, "percentage": 77.5, "elapsed_time": "1 day, 2:08:56", "remaining_time": "7:35:27"}
106
+ {"current_steps": 1040, "total_steps": 1329, "loss": 0.4857, "learning_rate": 5e-06, "epoch": 2.3469675599435824, "percentage": 78.25, "elapsed_time": "1 day, 2:23:55", "remaining_time": "7:20:08"}
107
+ {"current_steps": 1050, "total_steps": 1329, "loss": 0.4836, "learning_rate": 5e-06, "epoch": 2.3695345557122707, "percentage": 79.01, "elapsed_time": "1 day, 2:38:55", "remaining_time": "7:04:51"}
108
+ {"current_steps": 1060, "total_steps": 1329, "loss": 0.4827, "learning_rate": 5e-06, "epoch": 2.392101551480959, "percentage": 79.76, "elapsed_time": "1 day, 2:53:55", "remaining_time": "6:49:34"}
109
+ {"current_steps": 1070, "total_steps": 1329, "loss": 0.4839, "learning_rate": 5e-06, "epoch": 2.414668547249647, "percentage": 80.51, "elapsed_time": "1 day, 3:08:54", "remaining_time": "6:34:17"}
110
+ {"current_steps": 1080, "total_steps": 1329, "loss": 0.4872, "learning_rate": 5e-06, "epoch": 2.4372355430183354, "percentage": 81.26, "elapsed_time": "1 day, 3:23:54", "remaining_time": "6:19:00"}
111
+ {"current_steps": 1090, "total_steps": 1329, "loss": 0.4853, "learning_rate": 5e-06, "epoch": 2.459802538787024, "percentage": 82.02, "elapsed_time": "1 day, 3:38:55", "remaining_time": "6:03:44"}
112
+ {"current_steps": 1100, "total_steps": 1329, "loss": 0.4884, "learning_rate": 5e-06, "epoch": 2.4823695345557124, "percentage": 82.77, "elapsed_time": "1 day, 3:53:54", "remaining_time": "5:48:28"}
113
+ {"current_steps": 1110, "total_steps": 1329, "loss": 0.4918, "learning_rate": 5e-06, "epoch": 2.5049365303244007, "percentage": 83.52, "elapsed_time": "1 day, 4:08:55", "remaining_time": "5:33:13"}
114
+ {"current_steps": 1120, "total_steps": 1329, "loss": 0.4825, "learning_rate": 5e-06, "epoch": 2.527503526093089, "percentage": 84.27, "elapsed_time": "1 day, 4:23:55", "remaining_time": "5:17:57"}
115
+ {"current_steps": 1130, "total_steps": 1329, "loss": 0.4875, "learning_rate": 5e-06, "epoch": 2.550070521861777, "percentage": 85.03, "elapsed_time": "1 day, 4:38:55", "remaining_time": "5:02:42"}
116
+ {"current_steps": 1140, "total_steps": 1329, "loss": 0.4857, "learning_rate": 5e-06, "epoch": 2.5726375176304654, "percentage": 85.78, "elapsed_time": "1 day, 4:53:56", "remaining_time": "4:47:28"}
117
+ {"current_steps": 1150, "total_steps": 1329, "loss": 0.4866, "learning_rate": 5e-06, "epoch": 2.5952045133991537, "percentage": 86.53, "elapsed_time": "1 day, 5:08:56", "remaining_time": "4:32:13"}
118
+ {"current_steps": 1160, "total_steps": 1329, "loss": 0.4902, "learning_rate": 5e-06, "epoch": 2.617771509167842, "percentage": 87.28, "elapsed_time": "1 day, 5:23:57", "remaining_time": "4:16:59"}
119
+ {"current_steps": 1170, "total_steps": 1329, "loss": 0.4792, "learning_rate": 5e-06, "epoch": 2.64033850493653, "percentage": 88.04, "elapsed_time": "1 day, 5:38:57", "remaining_time": "4:01:45"}
120
+ {"current_steps": 1180, "total_steps": 1329, "loss": 0.4902, "learning_rate": 5e-06, "epoch": 2.6629055007052185, "percentage": 88.79, "elapsed_time": "1 day, 5:53:57", "remaining_time": "3:46:31"}
121
+ {"current_steps": 1190, "total_steps": 1329, "loss": 0.4908, "learning_rate": 5e-06, "epoch": 2.685472496473907, "percentage": 89.54, "elapsed_time": "1 day, 6:08:58", "remaining_time": "3:31:18"}
122
+ {"current_steps": 1200, "total_steps": 1329, "loss": 0.4894, "learning_rate": 5e-06, "epoch": 2.7080394922425954, "percentage": 90.29, "elapsed_time": "1 day, 6:23:58", "remaining_time": "3:16:04"}
123
+ {"current_steps": 1210, "total_steps": 1329, "loss": 0.4907, "learning_rate": 5e-06, "epoch": 2.7306064880112837, "percentage": 91.05, "elapsed_time": "1 day, 6:38:58", "remaining_time": "3:00:51"}
124
+ {"current_steps": 1220, "total_steps": 1329, "loss": 0.4874, "learning_rate": 5e-06, "epoch": 2.753173483779972, "percentage": 91.8, "elapsed_time": "1 day, 6:53:58", "remaining_time": "2:45:38"}
125
+ {"current_steps": 1230, "total_steps": 1329, "loss": 0.4939, "learning_rate": 5e-06, "epoch": 2.77574047954866, "percentage": 92.55, "elapsed_time": "1 day, 7:08:59", "remaining_time": "2:30:25"}
126
+ {"current_steps": 1240, "total_steps": 1329, "loss": 0.4921, "learning_rate": 5e-06, "epoch": 2.7983074753173485, "percentage": 93.3, "elapsed_time": "1 day, 7:23:58", "remaining_time": "2:15:13"}
127
+ {"current_steps": 1250, "total_steps": 1329, "loss": 0.4923, "learning_rate": 5e-06, "epoch": 2.8208744710860367, "percentage": 94.06, "elapsed_time": "1 day, 7:38:58", "remaining_time": "2:00:00"}
128
+ {"current_steps": 1260, "total_steps": 1329, "loss": 0.4942, "learning_rate": 5e-06, "epoch": 2.843441466854725, "percentage": 94.81, "elapsed_time": "1 day, 7:53:57", "remaining_time": "1:44:48"}
129
+ {"current_steps": 1270, "total_steps": 1329, "loss": 0.4912, "learning_rate": 5e-06, "epoch": 2.8660084626234132, "percentage": 95.56, "elapsed_time": "1 day, 8:08:56", "remaining_time": "1:29:36"}
130
+ {"current_steps": 1280, "total_steps": 1329, "loss": 0.4891, "learning_rate": 5e-06, "epoch": 2.8885754583921015, "percentage": 96.31, "elapsed_time": "1 day, 8:23:55", "remaining_time": "1:14:24"}
131
+ {"current_steps": 1290, "total_steps": 1329, "loss": 0.493, "learning_rate": 5e-06, "epoch": 2.9111424541607898, "percentage": 97.07, "elapsed_time": "1 day, 8:38:55", "remaining_time": "0:59:13"}
132
+ {"current_steps": 1300, "total_steps": 1329, "loss": 0.4886, "learning_rate": 5e-06, "epoch": 2.933709449929478, "percentage": 97.82, "elapsed_time": "1 day, 8:53:55", "remaining_time": "0:44:02"}
133
+ {"current_steps": 1310, "total_steps": 1329, "loss": 0.4925, "learning_rate": 5e-06, "epoch": 2.9562764456981663, "percentage": 98.57, "elapsed_time": "1 day, 9:08:53", "remaining_time": "0:28:50"}
134
+ {"current_steps": 1320, "total_steps": 1329, "loss": 0.489, "learning_rate": 5e-06, "epoch": 2.9788434414668545, "percentage": 99.32, "elapsed_time": "1 day, 9:23:54", "remaining_time": "0:13:39"}