Hugging Face's logo

mlfoundations-dev
/
hp_ablations_gemma_bsz512

Text Generation
Transformers
Safetensors
gemma2
llama-factory
full
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
c01a919
·
verified ·
1 Parent(s): 7b403e0

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:b921ae986d40c57377351ab0759cd728f44691d226e2beffd2ea996055ff3af0
3
  size 4903351912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ee78e249f79f3d42ca25bfdb7c3709c9b898902fba4a84e8a6bf7761ca183f3
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:e25ac706ebd7934760853351d456ed3f9ba96ff18515c244e7daff06204d40e5
3
  size 4947570872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce8eab3e958c300d44844e05ee39c77c4c68e0fd408b983b67e9aa7ba8691f3e
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:e2f83ee63677e5e544bd1c60faba7df6c87eaea3bab6f9e93daebfe1c0d68dfb
3
  size 4962221464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb02e1b86c1efdd70dd86e18b87222af4946d03a828f29cb52b01df419478da4
3
  size 4962221464
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:443e48154fadd0f4740f7db341cb8993d9835db9f6c54a8fde3f9ac271c2abc2
3
  size 3670322200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e230add5f8da9e86971db0fe6fb4245bf09df7fee6efd86fef1e09019506edcb
3
  size 3670322200
trainer_log.jsonl CHANGED
@@ -88,3 +88,47 @@
88
  {"current_steps": 870, "total_steps": 1329, "loss": 0.5456, "learning_rate": 5e-06, "epoch": 1.9633286318758816, "percentage": 65.46, "elapsed_time": "21:53:20", "remaining_time": "11:32:54"}
89
  {"current_steps": 880, "total_steps": 1329, "loss": 0.5439, "learning_rate": 5e-06, "epoch": 1.9858956276445698, "percentage": 66.22, "elapsed_time": "22:08:17", "remaining_time": "11:17:43"}
90
  {"current_steps": 886, "total_steps": 1329, "eval_loss": 0.5872690677642822, "epoch": 1.9994358251057829, "percentage": 66.67, "elapsed_time": "22:29:11", "remaining_time": "11:14:35"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
88
  {"current_steps": 870, "total_steps": 1329, "loss": 0.5456, "learning_rate": 5e-06, "epoch": 1.9633286318758816, "percentage": 65.46, "elapsed_time": "21:53:20", "remaining_time": "11:32:54"}
89
  {"current_steps": 880, "total_steps": 1329, "loss": 0.5439, "learning_rate": 5e-06, "epoch": 1.9858956276445698, "percentage": 66.22, "elapsed_time": "22:08:17", "remaining_time": "11:17:43"}
90
  {"current_steps": 886, "total_steps": 1329, "eval_loss": 0.5872690677642822, "epoch": 1.9994358251057829, "percentage": 66.67, "elapsed_time": "22:29:11", "remaining_time": "11:14:35"}
91
+ {"current_steps": 890, "total_steps": 1329, "loss": 0.5671, "learning_rate": 5e-06, "epoch": 2.008462623413258, "percentage": 66.97, "elapsed_time": "22:36:13", "remaining_time": "11:08:57"}
92
+ {"current_steps": 900, "total_steps": 1329, "loss": 0.4778, "learning_rate": 5e-06, "epoch": 2.0310296191819464, "percentage": 67.72, "elapsed_time": "22:51:11", "remaining_time": "10:53:35"}
93
+ {"current_steps": 910, "total_steps": 1329, "loss": 0.4796, "learning_rate": 5e-06, "epoch": 2.0535966149506346, "percentage": 68.47, "elapsed_time": "23:06:08", "remaining_time": "10:38:13"}
94
+ {"current_steps": 920, "total_steps": 1329, "loss": 0.4721, "learning_rate": 5e-06, "epoch": 2.076163610719323, "percentage": 69.22, "elapsed_time": "23:21:05", "remaining_time": "10:22:52"}
95
+ {"current_steps": 930, "total_steps": 1329, "loss": 0.4795, "learning_rate": 5e-06, "epoch": 2.098730606488011, "percentage": 69.98, "elapsed_time": "23:36:04", "remaining_time": "10:07:32"}
96
+ {"current_steps": 940, "total_steps": 1329, "loss": 0.4837, "learning_rate": 5e-06, "epoch": 2.1212976022566994, "percentage": 70.73, "elapsed_time": "23:51:00", "remaining_time": "9:52:11"}
97
+ {"current_steps": 950, "total_steps": 1329, "loss": 0.4853, "learning_rate": 5e-06, "epoch": 2.143864598025388, "percentage": 71.48, "elapsed_time": "1 day, 0:05:54", "remaining_time": "9:36:50"}
98
+ {"current_steps": 960, "total_steps": 1329, "loss": 0.4816, "learning_rate": 5e-06, "epoch": 2.1664315937940763, "percentage": 72.23, "elapsed_time": "1 day, 0:20:51", "remaining_time": "9:21:31"}
99
+ {"current_steps": 970, "total_steps": 1329, "loss": 0.4798, "learning_rate": 5e-06, "epoch": 2.1889985895627646, "percentage": 72.99, "elapsed_time": "1 day, 0:35:50", "remaining_time": "9:06:12"}
100
+ {"current_steps": 980, "total_steps": 1329, "loss": 0.4748, "learning_rate": 5e-06, "epoch": 2.211565585331453, "percentage": 73.74, "elapsed_time": "1 day, 0:50:46", "remaining_time": "8:50:54"}
101
+ {"current_steps": 990, "total_steps": 1329, "loss": 0.4747, "learning_rate": 5e-06, "epoch": 2.234132581100141, "percentage": 74.49, "elapsed_time": "1 day, 1:05:45", "remaining_time": "8:35:36"}
102
+ {"current_steps": 1000, "total_steps": 1329, "loss": 0.4836, "learning_rate": 5e-06, "epoch": 2.2566995768688294, "percentage": 75.24, "elapsed_time": "1 day, 1:20:43", "remaining_time": "8:20:18"}
103
+ {"current_steps": 1010, "total_steps": 1329, "loss": 0.4899, "learning_rate": 5e-06, "epoch": 2.2792665726375176, "percentage": 76.0, "elapsed_time": "1 day, 1:35:39", "remaining_time": "8:05:01"}
104
+ {"current_steps": 1020, "total_steps": 1329, "loss": 0.4843, "learning_rate": 5e-06, "epoch": 2.301833568406206, "percentage": 76.75, "elapsed_time": "1 day, 1:50:36", "remaining_time": "7:49:44"}
105
+ {"current_steps": 1030, "total_steps": 1329, "loss": 0.4887, "learning_rate": 5e-06, "epoch": 2.324400564174894, "percentage": 77.5, "elapsed_time": "1 day, 2:05:32", "remaining_time": "7:34:27"}
106
+ {"current_steps": 1040, "total_steps": 1329, "loss": 0.4865, "learning_rate": 5e-06, "epoch": 2.3469675599435824, "percentage": 78.25, "elapsed_time": "1 day, 2:20:28", "remaining_time": "7:19:11"}
107
+ {"current_steps": 1050, "total_steps": 1329, "loss": 0.4844, "learning_rate": 5e-06, "epoch": 2.3695345557122707, "percentage": 79.01, "elapsed_time": "1 day, 2:35:23", "remaining_time": "7:03:55"}
108
+ {"current_steps": 1060, "total_steps": 1329, "loss": 0.4837, "learning_rate": 5e-06, "epoch": 2.392101551480959, "percentage": 79.76, "elapsed_time": "1 day, 2:50:19", "remaining_time": "6:48:39"}
109
+ {"current_steps": 1070, "total_steps": 1329, "loss": 0.4849, "learning_rate": 5e-06, "epoch": 2.414668547249647, "percentage": 80.51, "elapsed_time": "1 day, 3:05:15", "remaining_time": "6:33:24"}
110
+ {"current_steps": 1080, "total_steps": 1329, "loss": 0.4883, "learning_rate": 5e-06, "epoch": 2.4372355430183354, "percentage": 81.26, "elapsed_time": "1 day, 3:20:14", "remaining_time": "6:18:10"}
111
+ {"current_steps": 1090, "total_steps": 1329, "loss": 0.4866, "learning_rate": 5e-06, "epoch": 2.459802538787024, "percentage": 82.02, "elapsed_time": "1 day, 3:35:11", "remaining_time": "6:02:55"}
112
+ {"current_steps": 1100, "total_steps": 1329, "loss": 0.4897, "learning_rate": 5e-06, "epoch": 2.4823695345557124, "percentage": 82.77, "elapsed_time": "1 day, 3:50:07", "remaining_time": "5:47:41"}
113
+ {"current_steps": 1110, "total_steps": 1329, "loss": 0.4928, "learning_rate": 5e-06, "epoch": 2.5049365303244007, "percentage": 83.52, "elapsed_time": "1 day, 4:05:06", "remaining_time": "5:32:27"}
114
+ {"current_steps": 1120, "total_steps": 1329, "loss": 0.4834, "learning_rate": 5e-06, "epoch": 2.527503526093089, "percentage": 84.27, "elapsed_time": "1 day, 4:20:03", "remaining_time": "5:17:14"}
115
+ {"current_steps": 1130, "total_steps": 1329, "loss": 0.4884, "learning_rate": 5e-06, "epoch": 2.550070521861777, "percentage": 85.03, "elapsed_time": "1 day, 4:35:00", "remaining_time": "5:02:01"}
116
+ {"current_steps": 1140, "total_steps": 1329, "loss": 0.4867, "learning_rate": 5e-06, "epoch": 2.5726375176304654, "percentage": 85.78, "elapsed_time": "1 day, 4:49:56", "remaining_time": "4:46:48"}
117
+ {"current_steps": 1150, "total_steps": 1329, "loss": 0.4875, "learning_rate": 5e-06, "epoch": 2.5952045133991537, "percentage": 86.53, "elapsed_time": "1 day, 5:04:52", "remaining_time": "4:31:35"}
118
+ {"current_steps": 1160, "total_steps": 1329, "loss": 0.4911, "learning_rate": 5e-06, "epoch": 2.617771509167842, "percentage": 87.28, "elapsed_time": "1 day, 5:19:46", "remaining_time": "4:16:22"}
119
+ {"current_steps": 1170, "total_steps": 1329, "loss": 0.4803, "learning_rate": 5e-06, "epoch": 2.64033850493653, "percentage": 88.04, "elapsed_time": "1 day, 5:34:43", "remaining_time": "4:01:10"}
120
+ {"current_steps": 1180, "total_steps": 1329, "loss": 0.491, "learning_rate": 5e-06, "epoch": 2.6629055007052185, "percentage": 88.79, "elapsed_time": "1 day, 5:49:41", "remaining_time": "3:45:59"}
121
+ {"current_steps": 1190, "total_steps": 1329, "loss": 0.4917, "learning_rate": 5e-06, "epoch": 2.685472496473907, "percentage": 89.54, "elapsed_time": "1 day, 6:04:38", "remaining_time": "3:30:47"}
122
+ {"current_steps": 1200, "total_steps": 1329, "loss": 0.4903, "learning_rate": 5e-06, "epoch": 2.7080394922425954, "percentage": 90.29, "elapsed_time": "1 day, 6:19:37", "remaining_time": "3:15:36"}
123
+ {"current_steps": 1210, "total_steps": 1329, "loss": 0.4916, "learning_rate": 5e-06, "epoch": 2.7306064880112837, "percentage": 91.05, "elapsed_time": "1 day, 6:34:34", "remaining_time": "3:00:25"}
124
+ {"current_steps": 1220, "total_steps": 1329, "loss": 0.4882, "learning_rate": 5e-06, "epoch": 2.753173483779972, "percentage": 91.8, "elapsed_time": "1 day, 6:49:31", "remaining_time": "2:45:14"}
125
+ {"current_steps": 1230, "total_steps": 1329, "loss": 0.4947, "learning_rate": 5e-06, "epoch": 2.77574047954866, "percentage": 92.55, "elapsed_time": "1 day, 7:04:27", "remaining_time": "2:30:03"}
126
+ {"current_steps": 1240, "total_steps": 1329, "loss": 0.4929, "learning_rate": 5e-06, "epoch": 2.7983074753173485, "percentage": 93.3, "elapsed_time": "1 day, 7:19:25", "remaining_time": "2:14:53"}
127
+ {"current_steps": 1250, "total_steps": 1329, "loss": 0.4931, "learning_rate": 5e-06, "epoch": 2.8208744710860367, "percentage": 94.06, "elapsed_time": "1 day, 7:34:21", "remaining_time": "1:59:43"}
128
+ {"current_steps": 1260, "total_steps": 1329, "loss": 0.4949, "learning_rate": 5e-06, "epoch": 2.843441466854725, "percentage": 94.81, "elapsed_time": "1 day, 7:49:20", "remaining_time": "1:44:33"}
129
+ {"current_steps": 1270, "total_steps": 1329, "loss": 0.4918, "learning_rate": 5e-06, "epoch": 2.8660084626234132, "percentage": 95.56, "elapsed_time": "1 day, 8:04:18", "remaining_time": "1:29:23"}
130
+ {"current_steps": 1280, "total_steps": 1329, "loss": 0.4899, "learning_rate": 5e-06, "epoch": 2.8885754583921015, "percentage": 96.31, "elapsed_time": "1 day, 8:19:13", "remaining_time": "1:14:14"}
131
+ {"current_steps": 1290, "total_steps": 1329, "loss": 0.4937, "learning_rate": 5e-06, "epoch": 2.9111424541607898, "percentage": 97.07, "elapsed_time": "1 day, 8:34:11", "remaining_time": "0:59:04"}
132
+ {"current_steps": 1300, "total_steps": 1329, "loss": 0.4893, "learning_rate": 5e-06, "epoch": 2.933709449929478, "percentage": 97.82, "elapsed_time": "1 day, 8:49:09", "remaining_time": "0:43:55"}
133
+ {"current_steps": 1310, "total_steps": 1329, "loss": 0.4932, "learning_rate": 5e-06, "epoch": 2.9562764456981663, "percentage": 98.57, "elapsed_time": "1 day, 9:04:04", "remaining_time": "0:28:46"}
134
+ {"current_steps": 1320, "total_steps": 1329, "loss": 0.4896, "learning_rate": 5e-06, "epoch": 2.9788434414668545, "percentage": 99.32, "elapsed_time": "1 day, 9:19:00", "remaining_time": "0:13:37"}