Hugging Face's logo

mlfoundations-dev
/
hp_ablations_gemma_adambeta2_0.98

Text Generation
Transformers
Safetensors
gemma2
llama-factory
full
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
19b6e3f
·
verified ·
1 Parent(s): 12ba200

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 sha256:58be671e8e38d0420e87d8b23c46ca0587dac012cb1022ea6e2885c3ea0dbb2a
3
  size 4903351912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e2585cbd7b99bb7b1dce3c866fdfdec13cf82f57f78992ca75cdf0ef68a4f53
3
  size 4903351912
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8510f198a80af42f941ccc0e99923ac76393c46b105b41711720ec654d85606f
3
  size 4947570872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a715a766e69ff78ace926becb18f6c1636b70ef35603508000d58cbcb1aea95
3
  size 4947570872
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c7e7e738ba7277c5cea40499d5e5f78f7f6dee31fb4dcec208c24aec66d9a5f
3
  size 4962221464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6224fc785470294cf6f33edd71e5571a6c1136ee8d0c3c87d72f085a5aae3218
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:ae3db0c452a9bedd1f026aac7320cb5bd5fc215859433d4cb6c4b671814d112a
3
  size 3670322200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e722d488309dcdeca480a4b31f35d153fe753d079027dddadff944d2c49fc3b9
3
  size 3670322200
trainer_log.jsonl CHANGED
@@ -88,3 +88,47 @@
88
  {"current_steps": 870, "total_steps": 1329, "loss": 0.5454, "learning_rate": 5e-06, "epoch": 1.9633286318758816, "percentage": 65.46, "elapsed_time": "21:47:57", "remaining_time": "11:30:03"}
89
  {"current_steps": 880, "total_steps": 1329, "loss": 0.5436, "learning_rate": 5e-06, "epoch": 1.9858956276445698, "percentage": 66.22, "elapsed_time": "22:02:52", "remaining_time": "11:14:58"}
90
  {"current_steps": 886, "total_steps": 1329, "eval_loss": 0.5872226357460022, "epoch": 1.9994358251057829, "percentage": 66.67, "elapsed_time": "22:23:37", "remaining_time": "11:11:48"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
88
  {"current_steps": 870, "total_steps": 1329, "loss": 0.5454, "learning_rate": 5e-06, "epoch": 1.9633286318758816, "percentage": 65.46, "elapsed_time": "21:47:57", "remaining_time": "11:30:03"}
89
  {"current_steps": 880, "total_steps": 1329, "loss": 0.5436, "learning_rate": 5e-06, "epoch": 1.9858956276445698, "percentage": 66.22, "elapsed_time": "22:02:52", "remaining_time": "11:14:58"}
90
  {"current_steps": 886, "total_steps": 1329, "eval_loss": 0.5872226357460022, "epoch": 1.9994358251057829, "percentage": 66.67, "elapsed_time": "22:23:37", "remaining_time": "11:11:48"}
91
+ {"current_steps": 890, "total_steps": 1329, "loss": 0.5673, "learning_rate": 5e-06, "epoch": 2.008462623413258, "percentage": 66.97, "elapsed_time": "22:30:34", "remaining_time": "11:06:10"}
92
+ {"current_steps": 900, "total_steps": 1329, "loss": 0.479, "learning_rate": 5e-06, "epoch": 2.0310296191819464, "percentage": 67.72, "elapsed_time": "22:45:29", "remaining_time": "10:50:52"}
93
+ {"current_steps": 910, "total_steps": 1329, "loss": 0.4807, "learning_rate": 5e-06, "epoch": 2.0535966149506346, "percentage": 68.47, "elapsed_time": "23:00:24", "remaining_time": "10:35:35"}
94
+ {"current_steps": 920, "total_steps": 1329, "loss": 0.473, "learning_rate": 5e-06, "epoch": 2.076163610719323, "percentage": 69.22, "elapsed_time": "23:15:20", "remaining_time": "10:20:19"}
95
+ {"current_steps": 930, "total_steps": 1329, "loss": 0.4804, "learning_rate": 5e-06, "epoch": 2.098730606488011, "percentage": 69.98, "elapsed_time": "23:30:15", "remaining_time": "10:05:02"}
96
+ {"current_steps": 940, "total_steps": 1329, "loss": 0.4843, "learning_rate": 5e-06, "epoch": 2.1212976022566994, "percentage": 70.73, "elapsed_time": "23:45:09", "remaining_time": "9:49:46"}
97
+ {"current_steps": 950, "total_steps": 1329, "loss": 0.486, "learning_rate": 5e-06, "epoch": 2.143864598025388, "percentage": 71.48, "elapsed_time": "1 day, 0:00:02", "remaining_time": "9:34:29"}
98
+ {"current_steps": 960, "total_steps": 1329, "loss": 0.482, "learning_rate": 5e-06, "epoch": 2.1664315937940763, "percentage": 72.23, "elapsed_time": "1 day, 0:14:56", "remaining_time": "9:19:14"}
99
+ {"current_steps": 970, "total_steps": 1329, "loss": 0.48, "learning_rate": 5e-06, "epoch": 2.1889985895627646, "percentage": 72.99, "elapsed_time": "1 day, 0:29:50", "remaining_time": "9:03:59"}
100
+ {"current_steps": 980, "total_steps": 1329, "loss": 0.475, "learning_rate": 5e-06, "epoch": 2.211565585331453, "percentage": 73.74, "elapsed_time": "1 day, 0:44:43", "remaining_time": "8:48:44"}
101
+ {"current_steps": 990, "total_steps": 1329, "loss": 0.4749, "learning_rate": 5e-06, "epoch": 2.234132581100141, "percentage": 74.49, "elapsed_time": "1 day, 0:59:37", "remaining_time": "8:33:30"}
102
+ {"current_steps": 1000, "total_steps": 1329, "loss": 0.4837, "learning_rate": 5e-06, "epoch": 2.2566995768688294, "percentage": 75.24, "elapsed_time": "1 day, 1:14:31", "remaining_time": "8:18:16"}
103
+ {"current_steps": 1010, "total_steps": 1329, "loss": 0.4899, "learning_rate": 5e-06, "epoch": 2.2792665726375176, "percentage": 76.0, "elapsed_time": "1 day, 1:29:25", "remaining_time": "8:03:03"}
104
+ {"current_steps": 1020, "total_steps": 1329, "loss": 0.4842, "learning_rate": 5e-06, "epoch": 2.301833568406206, "percentage": 76.75, "elapsed_time": "1 day, 1:44:17", "remaining_time": "7:47:49"}
105
+ {"current_steps": 1030, "total_steps": 1329, "loss": 0.4885, "learning_rate": 5e-06, "epoch": 2.324400564174894, "percentage": 77.5, "elapsed_time": "1 day, 1:59:12", "remaining_time": "7:32:37"}
106
+ {"current_steps": 1040, "total_steps": 1329, "loss": 0.4865, "learning_rate": 5e-06, "epoch": 2.3469675599435824, "percentage": 78.25, "elapsed_time": "1 day, 2:14:06", "remaining_time": "7:17:25"}
107
+ {"current_steps": 1050, "total_steps": 1329, "loss": 0.4841, "learning_rate": 5e-06, "epoch": 2.3695345557122707, "percentage": 79.01, "elapsed_time": "1 day, 2:29:01", "remaining_time": "7:02:13"}
108
+ {"current_steps": 1060, "total_steps": 1329, "loss": 0.4834, "learning_rate": 5e-06, "epoch": 2.392101551480959, "percentage": 79.76, "elapsed_time": "1 day, 2:43:55", "remaining_time": "6:47:01"}
109
+ {"current_steps": 1070, "total_steps": 1329, "loss": 0.4844, "learning_rate": 5e-06, "epoch": 2.414668547249647, "percentage": 80.51, "elapsed_time": "1 day, 2:58:49", "remaining_time": "6:31:50"}
110
+ {"current_steps": 1080, "total_steps": 1329, "loss": 0.4877, "learning_rate": 5e-06, "epoch": 2.4372355430183354, "percentage": 81.26, "elapsed_time": "1 day, 3:13:42", "remaining_time": "6:16:39"}
111
+ {"current_steps": 1090, "total_steps": 1329, "loss": 0.4858, "learning_rate": 5e-06, "epoch": 2.459802538787024, "percentage": 82.02, "elapsed_time": "1 day, 3:28:36", "remaining_time": "6:01:29"}
112
+ {"current_steps": 1100, "total_steps": 1329, "loss": 0.489, "learning_rate": 5e-06, "epoch": 2.4823695345557124, "percentage": 82.77, "elapsed_time": "1 day, 3:43:28", "remaining_time": "5:46:18"}
113
+ {"current_steps": 1110, "total_steps": 1329, "loss": 0.4922, "learning_rate": 5e-06, "epoch": 2.5049365303244007, "percentage": 83.52, "elapsed_time": "1 day, 3:58:24", "remaining_time": "5:31:08"}
114
+ {"current_steps": 1120, "total_steps": 1329, "loss": 0.483, "learning_rate": 5e-06, "epoch": 2.527503526093089, "percentage": 84.27, "elapsed_time": "1 day, 4:13:18", "remaining_time": "5:15:58"}
115
+ {"current_steps": 1130, "total_steps": 1329, "loss": 0.488, "learning_rate": 5e-06, "epoch": 2.550070521861777, "percentage": 85.03, "elapsed_time": "1 day, 4:28:15", "remaining_time": "5:00:50"}
116
+ {"current_steps": 1140, "total_steps": 1329, "loss": 0.4863, "learning_rate": 5e-06, "epoch": 2.5726375176304654, "percentage": 85.78, "elapsed_time": "1 day, 4:43:08", "remaining_time": "4:45:40"}
117
+ {"current_steps": 1150, "total_steps": 1329, "loss": 0.4872, "learning_rate": 5e-06, "epoch": 2.5952045133991537, "percentage": 86.53, "elapsed_time": "1 day, 4:58:03", "remaining_time": "4:30:31"}
118
+ {"current_steps": 1160, "total_steps": 1329, "loss": 0.4909, "learning_rate": 5e-06, "epoch": 2.617771509167842, "percentage": 87.28, "elapsed_time": "1 day, 5:12:57", "remaining_time": "4:15:23"}
119
+ {"current_steps": 1170, "total_steps": 1329, "loss": 0.48, "learning_rate": 5e-06, "epoch": 2.64033850493653, "percentage": 88.04, "elapsed_time": "1 day, 5:27:53", "remaining_time": "4:00:15"}
120
+ {"current_steps": 1180, "total_steps": 1329, "loss": 0.4907, "learning_rate": 5e-06, "epoch": 2.6629055007052185, "percentage": 88.79, "elapsed_time": "1 day, 5:42:49", "remaining_time": "3:45:07"}
121
+ {"current_steps": 1190, "total_steps": 1329, "loss": 0.4915, "learning_rate": 5e-06, "epoch": 2.685472496473907, "percentage": 89.54, "elapsed_time": "1 day, 5:57:42", "remaining_time": "3:29:59"}
122
+ {"current_steps": 1200, "total_steps": 1329, "loss": 0.4901, "learning_rate": 5e-06, "epoch": 2.7080394922425954, "percentage": 90.29, "elapsed_time": "1 day, 6:12:36", "remaining_time": "3:14:51"}
123
+ {"current_steps": 1210, "total_steps": 1329, "loss": 0.4912, "learning_rate": 5e-06, "epoch": 2.7306064880112837, "percentage": 91.05, "elapsed_time": "1 day, 6:27:32", "remaining_time": "2:59:44"}
124
+ {"current_steps": 1220, "total_steps": 1329, "loss": 0.4879, "learning_rate": 5e-06, "epoch": 2.753173483779972, "percentage": 91.8, "elapsed_time": "1 day, 6:42:27", "remaining_time": "2:44:36"}
125
+ {"current_steps": 1230, "total_steps": 1329, "loss": 0.4945, "learning_rate": 5e-06, "epoch": 2.77574047954866, "percentage": 92.55, "elapsed_time": "1 day, 6:57:24", "remaining_time": "2:29:29"}
126
+ {"current_steps": 1240, "total_steps": 1329, "loss": 0.4929, "learning_rate": 5e-06, "epoch": 2.7983074753173485, "percentage": 93.3, "elapsed_time": "1 day, 7:12:20", "remaining_time": "2:14:23"}
127
+ {"current_steps": 1250, "total_steps": 1329, "loss": 0.4929, "learning_rate": 5e-06, "epoch": 2.8208744710860367, "percentage": 94.06, "elapsed_time": "1 day, 7:27:14", "remaining_time": "1:59:16"}
128
+ {"current_steps": 1260, "total_steps": 1329, "loss": 0.4948, "learning_rate": 5e-06, "epoch": 2.843441466854725, "percentage": 94.81, "elapsed_time": "1 day, 7:42:08", "remaining_time": "1:44:09"}
129
+ {"current_steps": 1270, "total_steps": 1329, "loss": 0.4919, "learning_rate": 5e-06, "epoch": 2.8660084626234132, "percentage": 95.56, "elapsed_time": "1 day, 7:57:02", "remaining_time": "1:29:03"}
130
+ {"current_steps": 1280, "total_steps": 1329, "loss": 0.49, "learning_rate": 5e-06, "epoch": 2.8885754583921015, "percentage": 96.31, "elapsed_time": "1 day, 8:11:57", "remaining_time": "1:13:57"}
131
+ {"current_steps": 1290, "total_steps": 1329, "loss": 0.4936, "learning_rate": 5e-06, "epoch": 2.9111424541607898, "percentage": 97.07, "elapsed_time": "1 day, 8:26:51", "remaining_time": "0:58:51"}
132
+ {"current_steps": 1300, "total_steps": 1329, "loss": 0.4892, "learning_rate": 5e-06, "epoch": 2.933709449929478, "percentage": 97.82, "elapsed_time": "1 day, 8:41:44", "remaining_time": "0:43:45"}
133
+ {"current_steps": 1310, "total_steps": 1329, "loss": 0.4932, "learning_rate": 5e-06, "epoch": 2.9562764456981663, "percentage": 98.57, "elapsed_time": "1 day, 8:56:40", "remaining_time": "0:28:40"}
134
+ {"current_steps": 1320, "total_steps": 1329, "loss": 0.49, "learning_rate": 5e-06, "epoch": 2.9788434414668545, "percentage": 99.32, "elapsed_time": "1 day, 9:11:35", "remaining_time": "0:13:34"}