Hugging Face's logo

mlfoundations-dev
/
hp_ablations_gemma_lr8e-6

Text Generation
Transformers
Safetensors
gemma2
llama-factory
full
Generated from Trainer
text-generation-inference
Model card Files
xet
 Community
sedrickkeh commited on
Commit
f6a0d9d
·
verified ·
1 Parent(s): 8e6ee66

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 sha256:58918f16c1dae66902e0454e4d31ba43ff681634f0288007f1d9ad14dc1cc43b
3
  size 4903351912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43d0b5d0bebf72d66fb1fe221ee2675fdfb3673a2b9aea14bd384a071d02e256
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:e49e6cf1ff8d84685d21a268a683914cad3d385374a0b0fbdd0d91f806d3236d
3
  size 4947570872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb5bff4eaa1b83d4a2cea9e03490bfe2a7dacf4b37aff0521ecbb2c916fcef1d
3
  size 4947570872
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e94e340d769f0c84b6c048f26a80dbbd87e84e7ae216ea69f96f85596fbc667
3
  size 4962221464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44a5f987dfc86c2bdbbc583d891aeb36241a0cb63dc01ebce86371b50211adff
3
  size 4962221464
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c593056b7cfc22117aaca00f32c52717bbd7cacc1fed3445bc5f7671749365b
3
  size 3670322200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:099be6d32fccd643c12054ca9d7aca72452b8b88d8c18dbe5146bb30838beb36
3
  size 3670322200
trainer_log.jsonl CHANGED
@@ -88,3 +88,47 @@
88
  {"current_steps": 870, "total_steps": 1329, "loss": 0.5337, "learning_rate": 8e-06, "epoch": 1.9633286318758816, "percentage": 65.46, "elapsed_time": "21:31:59", "remaining_time": "11:21:38"}
89
  {"current_steps": 880, "total_steps": 1329, "loss": 0.5319, "learning_rate": 8e-06, "epoch": 1.9858956276445698, "percentage": 66.22, "elapsed_time": "21:46:41", "remaining_time": "11:06:42"}
90
  {"current_steps": 886, "total_steps": 1329, "eval_loss": 0.5926612615585327, "epoch": 1.9994358251057829, "percentage": 66.67, "elapsed_time": "22:07:15", "remaining_time": "11:03:37"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
88
  {"current_steps": 870, "total_steps": 1329, "loss": 0.5337, "learning_rate": 8e-06, "epoch": 1.9633286318758816, "percentage": 65.46, "elapsed_time": "21:31:59", "remaining_time": "11:21:38"}
89
  {"current_steps": 880, "total_steps": 1329, "loss": 0.5319, "learning_rate": 8e-06, "epoch": 1.9858956276445698, "percentage": 66.22, "elapsed_time": "21:46:41", "remaining_time": "11:06:42"}
90
  {"current_steps": 886, "total_steps": 1329, "eval_loss": 0.5926612615585327, "epoch": 1.9994358251057829, "percentage": 66.67, "elapsed_time": "22:07:15", "remaining_time": "11:03:37"}
91
+ {"current_steps": 890, "total_steps": 1329, "loss": 0.5456, "learning_rate": 8e-06, "epoch": 2.008462623413258, "percentage": 66.97, "elapsed_time": "22:14:10", "remaining_time": "10:58:05"}
92
+ {"current_steps": 900, "total_steps": 1329, "loss": 0.4427, "learning_rate": 8e-06, "epoch": 2.0310296191819464, "percentage": 67.72, "elapsed_time": "22:28:54", "remaining_time": "10:42:58"}
93
+ {"current_steps": 910, "total_steps": 1329, "loss": 0.4433, "learning_rate": 8e-06, "epoch": 2.0535966149506346, "percentage": 68.47, "elapsed_time": "22:43:37", "remaining_time": "10:27:52"}
94
+ {"current_steps": 920, "total_steps": 1329, "loss": 0.436, "learning_rate": 8e-06, "epoch": 2.076163610719323, "percentage": 69.22, "elapsed_time": "22:58:21", "remaining_time": "10:12:46"}
95
+ {"current_steps": 930, "total_steps": 1329, "loss": 0.4431, "learning_rate": 8e-06, "epoch": 2.098730606488011, "percentage": 69.98, "elapsed_time": "23:13:06", "remaining_time": "9:57:41"}
96
+ {"current_steps": 940, "total_steps": 1329, "loss": 0.4477, "learning_rate": 8e-06, "epoch": 2.1212976022566994, "percentage": 70.73, "elapsed_time": "23:27:50", "remaining_time": "9:42:36"}
97
+ {"current_steps": 950, "total_steps": 1329, "loss": 0.4495, "learning_rate": 8e-06, "epoch": 2.143864598025388, "percentage": 71.48, "elapsed_time": "23:42:33", "remaining_time": "9:27:31"}
98
+ {"current_steps": 960, "total_steps": 1329, "loss": 0.446, "learning_rate": 8e-06, "epoch": 2.1664315937940763, "percentage": 72.23, "elapsed_time": "23:57:17", "remaining_time": "9:12:27"}
99
+ {"current_steps": 970, "total_steps": 1329, "loss": 0.4452, "learning_rate": 8e-06, "epoch": 2.1889985895627646, "percentage": 72.99, "elapsed_time": "1 day, 0:12:01", "remaining_time": "8:57:23"}
100
+ {"current_steps": 980, "total_steps": 1329, "loss": 0.4411, "learning_rate": 8e-06, "epoch": 2.211565585331453, "percentage": 73.74, "elapsed_time": "1 day, 0:26:45", "remaining_time": "8:42:20"}
101
+ {"current_steps": 990, "total_steps": 1329, "loss": 0.4412, "learning_rate": 8e-06, "epoch": 2.234132581100141, "percentage": 74.49, "elapsed_time": "1 day, 0:41:29", "remaining_time": "8:27:17"}
102
+ {"current_steps": 1000, "total_steps": 1329, "loss": 0.4491, "learning_rate": 8e-06, "epoch": 2.2566995768688294, "percentage": 75.24, "elapsed_time": "1 day, 0:56:13", "remaining_time": "8:12:15"}
103
+ {"current_steps": 1010, "total_steps": 1329, "loss": 0.4552, "learning_rate": 8e-06, "epoch": 2.2792665726375176, "percentage": 76.0, "elapsed_time": "1 day, 1:10:57", "remaining_time": "7:57:13"}
104
+ {"current_steps": 1020, "total_steps": 1329, "loss": 0.451, "learning_rate": 8e-06, "epoch": 2.301833568406206, "percentage": 76.75, "elapsed_time": "1 day, 1:25:42", "remaining_time": "7:42:11"}
105
+ {"current_steps": 1030, "total_steps": 1329, "loss": 0.455, "learning_rate": 8e-06, "epoch": 2.324400564174894, "percentage": 77.5, "elapsed_time": "1 day, 1:40:25", "remaining_time": "7:27:10"}
106
+ {"current_steps": 1040, "total_steps": 1329, "loss": 0.4537, "learning_rate": 8e-06, "epoch": 2.3469675599435824, "percentage": 78.25, "elapsed_time": "1 day, 1:55:07", "remaining_time": "7:12:08"}
107
+ {"current_steps": 1050, "total_steps": 1329, "loss": 0.4518, "learning_rate": 8e-06, "epoch": 2.3695345557122707, "percentage": 79.01, "elapsed_time": "1 day, 2:09:51", "remaining_time": "6:57:07"}
108
+ {"current_steps": 1060, "total_steps": 1329, "loss": 0.4513, "learning_rate": 8e-06, "epoch": 2.392101551480959, "percentage": 79.76, "elapsed_time": "1 day, 2:24:34", "remaining_time": "6:42:07"}
109
+ {"current_steps": 1070, "total_steps": 1329, "loss": 0.4528, "learning_rate": 8e-06, "epoch": 2.414668547249647, "percentage": 80.51, "elapsed_time": "1 day, 2:39:17", "remaining_time": "6:27:07"}
110
+ {"current_steps": 1080, "total_steps": 1329, "loss": 0.4555, "learning_rate": 8e-06, "epoch": 2.4372355430183354, "percentage": 81.26, "elapsed_time": "1 day, 2:54:00", "remaining_time": "6:12:07"}
111
+ {"current_steps": 1090, "total_steps": 1329, "loss": 0.4543, "learning_rate": 8e-06, "epoch": 2.459802538787024, "percentage": 82.02, "elapsed_time": "1 day, 3:08:43", "remaining_time": "5:57:07"}
112
+ {"current_steps": 1100, "total_steps": 1329, "loss": 0.458, "learning_rate": 8e-06, "epoch": 2.4823695345557124, "percentage": 82.77, "elapsed_time": "1 day, 3:23:26", "remaining_time": "5:42:08"}
113
+ {"current_steps": 1110, "total_steps": 1329, "loss": 0.4607, "learning_rate": 8e-06, "epoch": 2.5049365303244007, "percentage": 83.52, "elapsed_time": "1 day, 3:38:09", "remaining_time": "5:27:09"}
114
+ {"current_steps": 1120, "total_steps": 1329, "loss": 0.4526, "learning_rate": 8e-06, "epoch": 2.527503526093089, "percentage": 84.27, "elapsed_time": "1 day, 3:52:53", "remaining_time": "5:12:10"}
115
+ {"current_steps": 1130, "total_steps": 1329, "loss": 0.4574, "learning_rate": 8e-06, "epoch": 2.550070521861777, "percentage": 85.03, "elapsed_time": "1 day, 4:07:36", "remaining_time": "4:57:11"}
116
+ {"current_steps": 1140, "total_steps": 1329, "loss": 0.4558, "learning_rate": 8e-06, "epoch": 2.5726375176304654, "percentage": 85.78, "elapsed_time": "1 day, 4:22:19", "remaining_time": "4:42:13"}
117
+ {"current_steps": 1150, "total_steps": 1329, "loss": 0.4565, "learning_rate": 8e-06, "epoch": 2.5952045133991537, "percentage": 86.53, "elapsed_time": "1 day, 4:37:02", "remaining_time": "4:27:15"}
118
+ {"current_steps": 1160, "total_steps": 1329, "loss": 0.4602, "learning_rate": 8e-06, "epoch": 2.617771509167842, "percentage": 87.28, "elapsed_time": "1 day, 4:51:45", "remaining_time": "4:12:18"}
119
+ {"current_steps": 1170, "total_steps": 1329, "loss": 0.4503, "learning_rate": 8e-06, "epoch": 2.64033850493653, "percentage": 88.04, "elapsed_time": "1 day, 5:06:28", "remaining_time": "3:57:20"}
120
+ {"current_steps": 1180, "total_steps": 1329, "loss": 0.4604, "learning_rate": 8e-06, "epoch": 2.6629055007052185, "percentage": 88.79, "elapsed_time": "1 day, 5:21:12", "remaining_time": "3:42:23"}
121
+ {"current_steps": 1190, "total_steps": 1329, "loss": 0.4611, "learning_rate": 8e-06, "epoch": 2.685472496473907, "percentage": 89.54, "elapsed_time": "1 day, 5:35:55", "remaining_time": "3:27:26"}
122
+ {"current_steps": 1200, "total_steps": 1329, "loss": 0.4602, "learning_rate": 8e-06, "epoch": 2.7080394922425954, "percentage": 90.29, "elapsed_time": "1 day, 5:50:39", "remaining_time": "3:12:29"}
123
+ {"current_steps": 1210, "total_steps": 1329, "loss": 0.4615, "learning_rate": 8e-06, "epoch": 2.7306064880112837, "percentage": 91.05, "elapsed_time": "1 day, 6:05:23", "remaining_time": "2:57:33"}
124
+ {"current_steps": 1220, "total_steps": 1329, "loss": 0.4588, "learning_rate": 8e-06, "epoch": 2.753173483779972, "percentage": 91.8, "elapsed_time": "1 day, 6:20:06", "remaining_time": "2:42:36"}
125
+ {"current_steps": 1230, "total_steps": 1329, "loss": 0.4652, "learning_rate": 8e-06, "epoch": 2.77574047954866, "percentage": 92.55, "elapsed_time": "1 day, 6:34:49", "remaining_time": "2:27:40"}
126
+ {"current_steps": 1240, "total_steps": 1329, "loss": 0.4633, "learning_rate": 8e-06, "epoch": 2.7983074753173485, "percentage": 93.3, "elapsed_time": "1 day, 6:49:32", "remaining_time": "2:12:44"}
127
+ {"current_steps": 1250, "total_steps": 1329, "loss": 0.4637, "learning_rate": 8e-06, "epoch": 2.8208744710860367, "percentage": 94.06, "elapsed_time": "1 day, 7:04:15", "remaining_time": "1:57:49"}
128
+ {"current_steps": 1260, "total_steps": 1329, "loss": 0.4654, "learning_rate": 8e-06, "epoch": 2.843441466854725, "percentage": 94.81, "elapsed_time": "1 day, 7:18:58", "remaining_time": "1:42:53"}
129
+ {"current_steps": 1270, "total_steps": 1329, "loss": 0.4629, "learning_rate": 8e-06, "epoch": 2.8660084626234132, "percentage": 95.56, "elapsed_time": "1 day, 7:33:41", "remaining_time": "1:27:58"}
130
+ {"current_steps": 1280, "total_steps": 1329, "loss": 0.4613, "learning_rate": 8e-06, "epoch": 2.8885754583921015, "percentage": 96.31, "elapsed_time": "1 day, 7:48:24", "remaining_time": "1:13:03"}
131
+ {"current_steps": 1290, "total_steps": 1329, "loss": 0.4645, "learning_rate": 8e-06, "epoch": 2.9111424541607898, "percentage": 97.07, "elapsed_time": "1 day, 8:03:07", "remaining_time": "0:58:08"}
132
+ {"current_steps": 1300, "total_steps": 1329, "loss": 0.4607, "learning_rate": 8e-06, "epoch": 2.933709449929478, "percentage": 97.82, "elapsed_time": "1 day, 8:17:51", "remaining_time": "0:43:13"}
133
+ {"current_steps": 1310, "total_steps": 1329, "loss": 0.4645, "learning_rate": 8e-06, "epoch": 2.9562764456981663, "percentage": 98.57, "elapsed_time": "1 day, 8:32:34", "remaining_time": "0:28:19"}
134
+ {"current_steps": 1320, "total_steps": 1329, "loss": 0.4618, "learning_rate": 8e-06, "epoch": 2.9788434414668545, "percentage": 99.32, "elapsed_time": "1 day, 8:47:16", "remaining_time": "0:13:24"}