Hugging Face's logo

mlfoundations-dev
/
hp_ablations_gemma_adambeta2_0.995

Text Generation
Transformers
Safetensors
gemma2
llama-factory
full
Generated from Trainer
text-generation-inference
Model card Files
xet
 Community
sedrickkeh commited on
Commit
aaf5de6
·
verified ·
1 Parent(s): 069e13c

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:fced6ab155ac9b433b67924c2356a678e507ba7a79e59d857870181733f70c7c
3
  size 4903351912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a281654632aa6d23c84ef042764dcbb4067dab8d78647606fea781f347a0997
3
  size 4903351912
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:119befb7a9e8e6dff813979bc81f0eceae65f53e1c930a3306107707fabd1767
3
  size 4947570872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46f9aa80a4e93fe79008df218637571ea0df75b52743984255837be8319b11c1
3
  size 4947570872
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:816c6ba27386786d6f7ebe4b2cbef3465c09f00199dd183990144deab0d82f4d
3
  size 4962221464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a757baac9438b064a951a8eb0fa42a2519f68ee397a193d7776746ca5e84ee8b
3
  size 4962221464
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12992aee83eb6a07d0edb3579ff389daaf1d9a28a7c8f0aac0f2d827682f412d
3
  size 3670322200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0e7139c24a774b5111d38c7084c97dc630d3a99190fa280b610bf52737eca58
3
  size 3670322200
trainer_log.jsonl CHANGED
@@ -88,3 +88,47 @@
88
  {"current_steps": 870, "total_steps": 1329, "loss": 0.5455, "learning_rate": 5e-06, "epoch": 1.9633286318758816, "percentage": 65.46, "elapsed_time": "21:47:21", "remaining_time": "11:29:44"}
89
  {"current_steps": 880, "total_steps": 1329, "loss": 0.5438, "learning_rate": 5e-06, "epoch": 1.9858956276445698, "percentage": 66.22, "elapsed_time": "22:02:14", "remaining_time": "11:14:38"}
90
  {"current_steps": 886, "total_steps": 1329, "eval_loss": 0.5871796011924744, "epoch": 1.9994358251057829, "percentage": 66.67, "elapsed_time": "22:23:03", "remaining_time": "11:11:31"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
88
  {"current_steps": 870, "total_steps": 1329, "loss": 0.5455, "learning_rate": 5e-06, "epoch": 1.9633286318758816, "percentage": 65.46, "elapsed_time": "21:47:21", "remaining_time": "11:29:44"}
89
  {"current_steps": 880, "total_steps": 1329, "loss": 0.5438, "learning_rate": 5e-06, "epoch": 1.9858956276445698, "percentage": 66.22, "elapsed_time": "22:02:14", "remaining_time": "11:14:38"}
90
  {"current_steps": 886, "total_steps": 1329, "eval_loss": 0.5871796011924744, "epoch": 1.9994358251057829, "percentage": 66.67, "elapsed_time": "22:23:03", "remaining_time": "11:11:31"}
91
+ {"current_steps": 890, "total_steps": 1329, "loss": 0.5674, "learning_rate": 5e-06, "epoch": 2.008462623413258, "percentage": 66.97, "elapsed_time": "22:30:02", "remaining_time": "11:05:55"}
92
+ {"current_steps": 900, "total_steps": 1329, "loss": 0.4789, "learning_rate": 5e-06, "epoch": 2.0310296191819464, "percentage": 67.72, "elapsed_time": "22:44:56", "remaining_time": "10:50:37"}
93
+ {"current_steps": 910, "total_steps": 1329, "loss": 0.4806, "learning_rate": 5e-06, "epoch": 2.0535966149506346, "percentage": 68.47, "elapsed_time": "22:59:48", "remaining_time": "10:35:19"}
94
+ {"current_steps": 920, "total_steps": 1329, "loss": 0.4731, "learning_rate": 5e-06, "epoch": 2.076163610719323, "percentage": 69.22, "elapsed_time": "23:14:41", "remaining_time": "10:20:01"}
95
+ {"current_steps": 930, "total_steps": 1329, "loss": 0.4804, "learning_rate": 5e-06, "epoch": 2.098730606488011, "percentage": 69.98, "elapsed_time": "23:29:36", "remaining_time": "10:04:45"}
96
+ {"current_steps": 940, "total_steps": 1329, "loss": 0.4845, "learning_rate": 5e-06, "epoch": 2.1212976022566994, "percentage": 70.73, "elapsed_time": "23:44:28", "remaining_time": "9:49:29"}
97
+ {"current_steps": 950, "total_steps": 1329, "loss": 0.4861, "learning_rate": 5e-06, "epoch": 2.143864598025388, "percentage": 71.48, "elapsed_time": "23:59:23", "remaining_time": "9:34:14"}
98
+ {"current_steps": 960, "total_steps": 1329, "loss": 0.4824, "learning_rate": 5e-06, "epoch": 2.1664315937940763, "percentage": 72.23, "elapsed_time": "1 day, 0:14:14", "remaining_time": "9:18:58"}
99
+ {"current_steps": 970, "total_steps": 1329, "loss": 0.4804, "learning_rate": 5e-06, "epoch": 2.1889985895627646, "percentage": 72.99, "elapsed_time": "1 day, 0:29:05", "remaining_time": "9:03:43"}
100
+ {"current_steps": 980, "total_steps": 1329, "loss": 0.4754, "learning_rate": 5e-06, "epoch": 2.211565585331453, "percentage": 73.74, "elapsed_time": "1 day, 0:43:58", "remaining_time": "8:48:28"}
101
+ {"current_steps": 990, "total_steps": 1329, "loss": 0.4753, "learning_rate": 5e-06, "epoch": 2.234132581100141, "percentage": 74.49, "elapsed_time": "1 day, 0:58:51", "remaining_time": "8:33:14"}
102
+ {"current_steps": 1000, "total_steps": 1329, "loss": 0.4843, "learning_rate": 5e-06, "epoch": 2.2566995768688294, "percentage": 75.24, "elapsed_time": "1 day, 1:13:44", "remaining_time": "8:18:01"}
103
+ {"current_steps": 1010, "total_steps": 1329, "loss": 0.4905, "learning_rate": 5e-06, "epoch": 2.2792665726375176, "percentage": 76.0, "elapsed_time": "1 day, 1:28:38", "remaining_time": "8:02:48"}
104
+ {"current_steps": 1020, "total_steps": 1329, "loss": 0.4849, "learning_rate": 5e-06, "epoch": 2.301833568406206, "percentage": 76.75, "elapsed_time": "1 day, 1:43:30", "remaining_time": "7:47:35"}
105
+ {"current_steps": 1030, "total_steps": 1329, "loss": 0.4892, "learning_rate": 5e-06, "epoch": 2.324400564174894, "percentage": 77.5, "elapsed_time": "1 day, 1:58:23", "remaining_time": "7:32:23"}
106
+ {"current_steps": 1040, "total_steps": 1329, "loss": 0.4871, "learning_rate": 5e-06, "epoch": 2.3469675599435824, "percentage": 78.25, "elapsed_time": "1 day, 2:13:16", "remaining_time": "7:17:11"}
107
+ {"current_steps": 1050, "total_steps": 1329, "loss": 0.4848, "learning_rate": 5e-06, "epoch": 2.3695345557122707, "percentage": 79.01, "elapsed_time": "1 day, 2:28:11", "remaining_time": "7:02:00"}
108
+ {"current_steps": 1060, "total_steps": 1329, "loss": 0.4841, "learning_rate": 5e-06, "epoch": 2.392101551480959, "percentage": 79.76, "elapsed_time": "1 day, 2:43:03", "remaining_time": "6:46:48"}
109
+ {"current_steps": 1070, "total_steps": 1329, "loss": 0.4851, "learning_rate": 5e-06, "epoch": 2.414668547249647, "percentage": 80.51, "elapsed_time": "1 day, 2:57:56", "remaining_time": "6:31:37"}
110
+ {"current_steps": 1080, "total_steps": 1329, "loss": 0.4884, "learning_rate": 5e-06, "epoch": 2.4372355430183354, "percentage": 81.26, "elapsed_time": "1 day, 3:12:46", "remaining_time": "6:16:26"}
111
+ {"current_steps": 1090, "total_steps": 1329, "loss": 0.4866, "learning_rate": 5e-06, "epoch": 2.459802538787024, "percentage": 82.02, "elapsed_time": "1 day, 3:27:37", "remaining_time": "6:01:16"}
112
+ {"current_steps": 1100, "total_steps": 1329, "loss": 0.4898, "learning_rate": 5e-06, "epoch": 2.4823695345557124, "percentage": 82.77, "elapsed_time": "1 day, 3:42:28", "remaining_time": "5:46:05"}
113
+ {"current_steps": 1110, "total_steps": 1329, "loss": 0.4929, "learning_rate": 5e-06, "epoch": 2.5049365303244007, "percentage": 83.52, "elapsed_time": "1 day, 3:57:20", "remaining_time": "5:30:56"}
114
+ {"current_steps": 1120, "total_steps": 1329, "loss": 0.4838, "learning_rate": 5e-06, "epoch": 2.527503526093089, "percentage": 84.27, "elapsed_time": "1 day, 4:12:12", "remaining_time": "5:15:46"}
115
+ {"current_steps": 1130, "total_steps": 1329, "loss": 0.4887, "learning_rate": 5e-06, "epoch": 2.550070521861777, "percentage": 85.03, "elapsed_time": "1 day, 4:27:03", "remaining_time": "5:00:37"}
116
+ {"current_steps": 1140, "total_steps": 1329, "loss": 0.4867, "learning_rate": 5e-06, "epoch": 2.5726375176304654, "percentage": 85.78, "elapsed_time": "1 day, 4:41:55", "remaining_time": "4:45:28"}
117
+ {"current_steps": 1150, "total_steps": 1329, "loss": 0.4877, "learning_rate": 5e-06, "epoch": 2.5952045133991537, "percentage": 86.53, "elapsed_time": "1 day, 4:56:48", "remaining_time": "4:30:20"}
118
+ {"current_steps": 1160, "total_steps": 1329, "loss": 0.4912, "learning_rate": 5e-06, "epoch": 2.617771509167842, "percentage": 87.28, "elapsed_time": "1 day, 5:11:41", "remaining_time": "4:15:12"}
119
+ {"current_steps": 1170, "total_steps": 1329, "loss": 0.4804, "learning_rate": 5e-06, "epoch": 2.64033850493653, "percentage": 88.04, "elapsed_time": "1 day, 5:26:34", "remaining_time": "4:00:04"}
120
+ {"current_steps": 1180, "total_steps": 1329, "loss": 0.491, "learning_rate": 5e-06, "epoch": 2.6629055007052185, "percentage": 88.79, "elapsed_time": "1 day, 5:41:29", "remaining_time": "3:44:57"}
121
+ {"current_steps": 1190, "total_steps": 1329, "loss": 0.4918, "learning_rate": 5e-06, "epoch": 2.685472496473907, "percentage": 89.54, "elapsed_time": "1 day, 5:56:22", "remaining_time": "3:29:49"}
122
+ {"current_steps": 1200, "total_steps": 1329, "loss": 0.4903, "learning_rate": 5e-06, "epoch": 2.7080394922425954, "percentage": 90.29, "elapsed_time": "1 day, 6:11:15", "remaining_time": "3:14:42"}
123
+ {"current_steps": 1210, "total_steps": 1329, "loss": 0.4915, "learning_rate": 5e-06, "epoch": 2.7306064880112837, "percentage": 91.05, "elapsed_time": "1 day, 6:26:10", "remaining_time": "2:59:35"}
124
+ {"current_steps": 1220, "total_steps": 1329, "loss": 0.4882, "learning_rate": 5e-06, "epoch": 2.753173483779972, "percentage": 91.8, "elapsed_time": "1 day, 6:41:03", "remaining_time": "2:44:29"}
125
+ {"current_steps": 1230, "total_steps": 1329, "loss": 0.4947, "learning_rate": 5e-06, "epoch": 2.77574047954866, "percentage": 92.55, "elapsed_time": "1 day, 6:55:59", "remaining_time": "2:29:23"}
126
+ {"current_steps": 1240, "total_steps": 1329, "loss": 0.4932, "learning_rate": 5e-06, "epoch": 2.7983074753173485, "percentage": 93.3, "elapsed_time": "1 day, 7:10:52", "remaining_time": "2:14:16"}
127
+ {"current_steps": 1250, "total_steps": 1329, "loss": 0.4933, "learning_rate": 5e-06, "epoch": 2.8208744710860367, "percentage": 94.06, "elapsed_time": "1 day, 7:25:45", "remaining_time": "1:59:10"}
128
+ {"current_steps": 1260, "total_steps": 1329, "loss": 0.4951, "learning_rate": 5e-06, "epoch": 2.843441466854725, "percentage": 94.81, "elapsed_time": "1 day, 7:40:36", "remaining_time": "1:44:04"}
129
+ {"current_steps": 1270, "total_steps": 1329, "loss": 0.492, "learning_rate": 5e-06, "epoch": 2.8660084626234132, "percentage": 95.56, "elapsed_time": "1 day, 7:55:27", "remaining_time": "1:28:59"}
130
+ {"current_steps": 1280, "total_steps": 1329, "loss": 0.4903, "learning_rate": 5e-06, "epoch": 2.8885754583921015, "percentage": 96.31, "elapsed_time": "1 day, 8:10:19", "remaining_time": "1:13:53"}
131
+ {"current_steps": 1290, "total_steps": 1329, "loss": 0.494, "learning_rate": 5e-06, "epoch": 2.9111424541607898, "percentage": 97.07, "elapsed_time": "1 day, 8:25:08", "remaining_time": "0:58:48"}
132
+ {"current_steps": 1300, "total_steps": 1329, "loss": 0.4896, "learning_rate": 5e-06, "epoch": 2.933709449929478, "percentage": 97.82, "elapsed_time": "1 day, 8:40:04", "remaining_time": "0:43:43"}
133
+ {"current_steps": 1310, "total_steps": 1329, "loss": 0.4933, "learning_rate": 5e-06, "epoch": 2.9562764456981663, "percentage": 98.57, "elapsed_time": "1 day, 8:54:58", "remaining_time": "0:28:38"}
134
+ {"current_steps": 1320, "total_steps": 1329, "loss": 0.4898, "learning_rate": 5e-06, "epoch": 2.9788434414668545, "percentage": 99.32, "elapsed_time": "1 day, 9:09:53", "remaining_time": "0:13:34"}