Hugging Face's logo

mlfoundations-dev
/
hp_ablations_gemma_adambeta2_0.9995

Text Generation
Transformers
Safetensors
gemma2
llama-factory
full
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
9e39ea1
·
verified ·
1 Parent(s): 8270d2b

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:ce614322d4c7502d6ea514dab94c32beaad72289947c0e127ded3b6201c5fe4d
3
  size 4903351912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7ff8a096fcfd809ae9bf09132138b8e918e1e6744e759c1bd5a4abbfa238561
3
  size 4903351912
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12298323e3a73554d6d031b5a69ef7069fa6fe4fdec714c57f48144d41f518c5
3
  size 4947570872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63b06af6e920faa30223cf5ff177b9e42603d1b026a03df92395fc86eea2c4ed
3
  size 4947570872
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7bb3f84bad64081c9b226a5988cdd3f503179ae025023afb5f3c72fb80d18b51
3
  size 4962221464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5109eb203922e834ed9df2bb384e93d591c2a678e0bc235f653c2c7481147b02
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:aa302bcf3785ed7d6ac4638bdb04d8249034e56a1d27dbfc3317e1554bff0a59
3
  size 3670322200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5071208e548f06d4abe04e4aa932c261bbdc40800f35917d2e98121d1ac912b0
3
  size 3670322200
trainer_log.jsonl CHANGED
@@ -88,3 +88,47 @@
88
  {"current_steps": 870, "total_steps": 1329, "loss": 0.5457, "learning_rate": 5e-06, "epoch": 1.9633286318758816, "percentage": 65.46, "elapsed_time": "21:56:28", "remaining_time": "11:34:33"}
89
  {"current_steps": 880, "total_steps": 1329, "loss": 0.5441, "learning_rate": 5e-06, "epoch": 1.9858956276445698, "percentage": 66.22, "elapsed_time": "22:11:27", "remaining_time": "11:19:20"}
90
  {"current_steps": 886, "total_steps": 1329, "eval_loss": 0.587400496006012, "epoch": 1.9994358251057829, "percentage": 66.67, "elapsed_time": "22:32:23", "remaining_time": "11:16:11"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
88
  {"current_steps": 870, "total_steps": 1329, "loss": 0.5457, "learning_rate": 5e-06, "epoch": 1.9633286318758816, "percentage": 65.46, "elapsed_time": "21:56:28", "remaining_time": "11:34:33"}
89
  {"current_steps": 880, "total_steps": 1329, "loss": 0.5441, "learning_rate": 5e-06, "epoch": 1.9858956276445698, "percentage": 66.22, "elapsed_time": "22:11:27", "remaining_time": "11:19:20"}
90
  {"current_steps": 886, "total_steps": 1329, "eval_loss": 0.587400496006012, "epoch": 1.9994358251057829, "percentage": 66.67, "elapsed_time": "22:32:23", "remaining_time": "11:16:11"}
91
+ {"current_steps": 890, "total_steps": 1329, "loss": 0.568, "learning_rate": 5e-06, "epoch": 2.008462623413258, "percentage": 66.97, "elapsed_time": "22:39:23", "remaining_time": "11:10:31"}
92
+ {"current_steps": 900, "total_steps": 1329, "loss": 0.4787, "learning_rate": 5e-06, "epoch": 2.0310296191819464, "percentage": 67.72, "elapsed_time": "22:54:23", "remaining_time": "10:55:07"}
93
+ {"current_steps": 910, "total_steps": 1329, "loss": 0.4804, "learning_rate": 5e-06, "epoch": 2.0535966149506346, "percentage": 68.47, "elapsed_time": "23:09:24", "remaining_time": "10:39:44"}
94
+ {"current_steps": 920, "total_steps": 1329, "loss": 0.4728, "learning_rate": 5e-06, "epoch": 2.076163610719323, "percentage": 69.22, "elapsed_time": "23:24:24", "remaining_time": "10:24:21"}
95
+ {"current_steps": 930, "total_steps": 1329, "loss": 0.4803, "learning_rate": 5e-06, "epoch": 2.098730606488011, "percentage": 69.98, "elapsed_time": "23:39:25", "remaining_time": "10:08:58"}
96
+ {"current_steps": 940, "total_steps": 1329, "loss": 0.4843, "learning_rate": 5e-06, "epoch": 2.1212976022566994, "percentage": 70.73, "elapsed_time": "23:54:26", "remaining_time": "9:53:36"}
97
+ {"current_steps": 950, "total_steps": 1329, "loss": 0.4861, "learning_rate": 5e-06, "epoch": 2.143864598025388, "percentage": 71.48, "elapsed_time": "1 day, 0:09:25", "remaining_time": "9:38:14"}
98
+ {"current_steps": 960, "total_steps": 1329, "loss": 0.4824, "learning_rate": 5e-06, "epoch": 2.1664315937940763, "percentage": 72.23, "elapsed_time": "1 day, 0:24:26", "remaining_time": "9:22:53"}
99
+ {"current_steps": 970, "total_steps": 1329, "loss": 0.4807, "learning_rate": 5e-06, "epoch": 2.1889985895627646, "percentage": 72.99, "elapsed_time": "1 day, 0:39:28", "remaining_time": "9:07:33"}
100
+ {"current_steps": 980, "total_steps": 1329, "loss": 0.476, "learning_rate": 5e-06, "epoch": 2.211565585331453, "percentage": 73.74, "elapsed_time": "1 day, 0:54:29", "remaining_time": "8:52:13"}
101
+ {"current_steps": 990, "total_steps": 1329, "loss": 0.4757, "learning_rate": 5e-06, "epoch": 2.234132581100141, "percentage": 74.49, "elapsed_time": "1 day, 1:09:31", "remaining_time": "8:36:53"}
102
+ {"current_steps": 1000, "total_steps": 1329, "loss": 0.4848, "learning_rate": 5e-06, "epoch": 2.2566995768688294, "percentage": 75.24, "elapsed_time": "1 day, 1:24:31", "remaining_time": "8:21:34"}
103
+ {"current_steps": 1010, "total_steps": 1329, "loss": 0.491, "learning_rate": 5e-06, "epoch": 2.2792665726375176, "percentage": 76.0, "elapsed_time": "1 day, 1:39:32", "remaining_time": "8:06:15"}
104
+ {"current_steps": 1020, "total_steps": 1329, "loss": 0.4853, "learning_rate": 5e-06, "epoch": 2.301833568406206, "percentage": 76.75, "elapsed_time": "1 day, 1:54:33", "remaining_time": "7:50:56"}
105
+ {"current_steps": 1030, "total_steps": 1329, "loss": 0.4897, "learning_rate": 5e-06, "epoch": 2.324400564174894, "percentage": 77.5, "elapsed_time": "1 day, 2:09:33", "remaining_time": "7:35:37"}
106
+ {"current_steps": 1040, "total_steps": 1329, "loss": 0.4875, "learning_rate": 5e-06, "epoch": 2.3469675599435824, "percentage": 78.25, "elapsed_time": "1 day, 2:24:34", "remaining_time": "7:20:19"}
107
+ {"current_steps": 1050, "total_steps": 1329, "loss": 0.4853, "learning_rate": 5e-06, "epoch": 2.3695345557122707, "percentage": 79.01, "elapsed_time": "1 day, 2:39:34", "remaining_time": "7:05:01"}
108
+ {"current_steps": 1060, "total_steps": 1329, "loss": 0.4848, "learning_rate": 5e-06, "epoch": 2.392101551480959, "percentage": 79.76, "elapsed_time": "1 day, 2:54:34", "remaining_time": "6:49:44"}
109
+ {"current_steps": 1070, "total_steps": 1329, "loss": 0.4857, "learning_rate": 5e-06, "epoch": 2.414668547249647, "percentage": 80.51, "elapsed_time": "1 day, 3:09:35", "remaining_time": "6:34:27"}
110
+ {"current_steps": 1080, "total_steps": 1329, "loss": 0.4891, "learning_rate": 5e-06, "epoch": 2.4372355430183354, "percentage": 81.26, "elapsed_time": "1 day, 3:24:35", "remaining_time": "6:19:10"}
111
+ {"current_steps": 1090, "total_steps": 1329, "loss": 0.4871, "learning_rate": 5e-06, "epoch": 2.459802538787024, "percentage": 82.02, "elapsed_time": "1 day, 3:39:36", "remaining_time": "6:03:53"}
112
+ {"current_steps": 1100, "total_steps": 1329, "loss": 0.4902, "learning_rate": 5e-06, "epoch": 2.4823695345557124, "percentage": 82.77, "elapsed_time": "1 day, 3:54:36", "remaining_time": "5:48:37"}
113
+ {"current_steps": 1110, "total_steps": 1329, "loss": 0.4934, "learning_rate": 5e-06, "epoch": 2.5049365303244007, "percentage": 83.52, "elapsed_time": "1 day, 4:09:36", "remaining_time": "5:33:21"}
114
+ {"current_steps": 1120, "total_steps": 1329, "loss": 0.4841, "learning_rate": 5e-06, "epoch": 2.527503526093089, "percentage": 84.27, "elapsed_time": "1 day, 4:24:37", "remaining_time": "5:18:05"}
115
+ {"current_steps": 1130, "total_steps": 1329, "loss": 0.4891, "learning_rate": 5e-06, "epoch": 2.550070521861777, "percentage": 85.03, "elapsed_time": "1 day, 4:39:37", "remaining_time": "5:02:50"}
116
+ {"current_steps": 1140, "total_steps": 1329, "loss": 0.4874, "learning_rate": 5e-06, "epoch": 2.5726375176304654, "percentage": 85.78, "elapsed_time": "1 day, 4:54:37", "remaining_time": "4:47:35"}
117
+ {"current_steps": 1150, "total_steps": 1329, "loss": 0.4884, "learning_rate": 5e-06, "epoch": 2.5952045133991537, "percentage": 86.53, "elapsed_time": "1 day, 5:09:37", "remaining_time": "4:32:20"}
118
+ {"current_steps": 1160, "total_steps": 1329, "loss": 0.4921, "learning_rate": 5e-06, "epoch": 2.617771509167842, "percentage": 87.28, "elapsed_time": "1 day, 5:24:38", "remaining_time": "4:17:05"}
119
+ {"current_steps": 1170, "total_steps": 1329, "loss": 0.481, "learning_rate": 5e-06, "epoch": 2.64033850493653, "percentage": 88.04, "elapsed_time": "1 day, 5:39:38", "remaining_time": "4:01:50"}
120
+ {"current_steps": 1180, "total_steps": 1329, "loss": 0.4918, "learning_rate": 5e-06, "epoch": 2.6629055007052185, "percentage": 88.79, "elapsed_time": "1 day, 5:54:38", "remaining_time": "3:46:36"}
121
+ {"current_steps": 1190, "total_steps": 1329, "loss": 0.4925, "learning_rate": 5e-06, "epoch": 2.685472496473907, "percentage": 89.54, "elapsed_time": "1 day, 6:09:38", "remaining_time": "3:31:22"}
122
+ {"current_steps": 1200, "total_steps": 1329, "loss": 0.4911, "learning_rate": 5e-06, "epoch": 2.7080394922425954, "percentage": 90.29, "elapsed_time": "1 day, 6:24:38", "remaining_time": "3:16:08"}
123
+ {"current_steps": 1210, "total_steps": 1329, "loss": 0.4924, "learning_rate": 5e-06, "epoch": 2.7306064880112837, "percentage": 91.05, "elapsed_time": "1 day, 6:39:38", "remaining_time": "3:00:55"}
124
+ {"current_steps": 1220, "total_steps": 1329, "loss": 0.489, "learning_rate": 5e-06, "epoch": 2.753173483779972, "percentage": 91.8, "elapsed_time": "1 day, 6:54:39", "remaining_time": "2:45:42"}
125
+ {"current_steps": 1230, "total_steps": 1329, "loss": 0.4955, "learning_rate": 5e-06, "epoch": 2.77574047954866, "percentage": 92.55, "elapsed_time": "1 day, 7:09:40", "remaining_time": "2:30:29"}
126
+ {"current_steps": 1240, "total_steps": 1329, "loss": 0.4938, "learning_rate": 5e-06, "epoch": 2.7983074753173485, "percentage": 93.3, "elapsed_time": "1 day, 7:24:40", "remaining_time": "2:15:16"}
127
+ {"current_steps": 1250, "total_steps": 1329, "loss": 0.4941, "learning_rate": 5e-06, "epoch": 2.8208744710860367, "percentage": 94.06, "elapsed_time": "1 day, 7:39:41", "remaining_time": "2:00:03"}
128
+ {"current_steps": 1260, "total_steps": 1329, "loss": 0.4958, "learning_rate": 5e-06, "epoch": 2.843441466854725, "percentage": 94.81, "elapsed_time": "1 day, 7:54:41", "remaining_time": "1:44:51"}
129
+ {"current_steps": 1270, "total_steps": 1329, "loss": 0.4928, "learning_rate": 5e-06, "epoch": 2.8660084626234132, "percentage": 95.56, "elapsed_time": "1 day, 8:09:42", "remaining_time": "1:29:38"}
130
+ {"current_steps": 1280, "total_steps": 1329, "loss": 0.4909, "learning_rate": 5e-06, "epoch": 2.8885754583921015, "percentage": 96.31, "elapsed_time": "1 day, 8:24:42", "remaining_time": "1:14:26"}
131
+ {"current_steps": 1290, "total_steps": 1329, "loss": 0.4946, "learning_rate": 5e-06, "epoch": 2.9111424541607898, "percentage": 97.07, "elapsed_time": "1 day, 8:39:43", "remaining_time": "0:59:14"}
132
+ {"current_steps": 1300, "total_steps": 1329, "loss": 0.4902, "learning_rate": 5e-06, "epoch": 2.933709449929478, "percentage": 97.82, "elapsed_time": "1 day, 8:54:44", "remaining_time": "0:44:03"}
133
+ {"current_steps": 1310, "total_steps": 1329, "loss": 0.4939, "learning_rate": 5e-06, "epoch": 2.9562764456981663, "percentage": 98.57, "elapsed_time": "1 day, 9:09:44", "remaining_time": "0:28:51"}
134
+ {"current_steps": 1320, "total_steps": 1329, "loss": 0.4904, "learning_rate": 5e-06, "epoch": 2.9788434414668545, "percentage": 99.32, "elapsed_time": "1 day, 9:24:43", "remaining_time": "0:13:40"}