Hugging Face's logo

mlfoundations-dev
/
hp_ablations_gemma_lr2e-6

Text Generation
Transformers
Safetensors
gemma2
llama-factory
full
Generated from Trainer
text-generation-inference
Model card Files
xet
Community
sedrickkeh commited on
Commit
b575471
·
verified ·
1 Parent(s): f38a076

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 sha256:39cb26ea3cd57911fc18ad9437e1256bc5a55ef465f051856ecdbd8f29c10635
3
  size 4903351912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d2380102de6d93b7c5a8eacb39afbb7044e4f973d98087938f990bcc0de9c8f
3
  size 4903351912
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ee3ecbf47bc4e64ec8349661350a5b3518ae4d6719788823f34d8df9848f5bc
3
  size 4947570872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c67b73b7ff203731dd75ccf898fb50096102af492c1445e5c0cc4810e111343e
3
  size 4947570872
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e0d7ebc189c7ef1986404937a0b97038ff0c709f5b6a2f4f125aea3f8001cc6
3
  size 4962221464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c7c33004a83aa91ef55ac5939fb45eeb225a9c89ad37d92afc0b6f2494f93f8
3
  size 4962221464
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7caf28c3bddd05c0f5735e948f5f029d307e54fc31dceba543b6c5379f50115d
3
  size 3670322200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e41f872faa94efed96d24cdb7e14968da15e302b99d4e53ff0fa01e6ea4fb640
3
  size 3670322200
trainer_log.jsonl CHANGED
@@ -88,3 +88,47 @@
88
  {"current_steps": 870, "total_steps": 1329, "loss": 0.5712, "learning_rate": 2e-06, "epoch": 1.9633286318758816, "percentage": 65.46, "elapsed_time": "21:43:02", "remaining_time": "11:27:27"}
89
  {"current_steps": 880, "total_steps": 1329, "loss": 0.5692, "learning_rate": 2e-06, "epoch": 1.9858956276445698, "percentage": 66.22, "elapsed_time": "21:57:53", "remaining_time": "11:12:25"}
90
  {"current_steps": 886, "total_steps": 1329, "eval_loss": 0.5890958905220032, "epoch": 1.9994358251057829, "percentage": 66.67, "elapsed_time": "22:18:35", "remaining_time": "11:09:17"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
88
  {"current_steps": 870, "total_steps": 1329, "loss": 0.5712, "learning_rate": 2e-06, "epoch": 1.9633286318758816, "percentage": 65.46, "elapsed_time": "21:43:02", "remaining_time": "11:27:27"}
89
  {"current_steps": 880, "total_steps": 1329, "loss": 0.5692, "learning_rate": 2e-06, "epoch": 1.9858956276445698, "percentage": 66.22, "elapsed_time": "21:57:53", "remaining_time": "11:12:25"}
90
  {"current_steps": 886, "total_steps": 1329, "eval_loss": 0.5890958905220032, "epoch": 1.9994358251057829, "percentage": 66.67, "elapsed_time": "22:18:35", "remaining_time": "11:09:17"}
91
+ {"current_steps": 890, "total_steps": 1329, "loss": 0.6066, "learning_rate": 2e-06, "epoch": 2.008462623413258, "percentage": 66.97, "elapsed_time": "22:25:33", "remaining_time": "11:03:42"}
92
+ {"current_steps": 900, "total_steps": 1329, "loss": 0.5346, "learning_rate": 2e-06, "epoch": 2.0310296191819464, "percentage": 67.72, "elapsed_time": "22:40:23", "remaining_time": "10:48:27"}
93
+ {"current_steps": 910, "total_steps": 1329, "loss": 0.5375, "learning_rate": 2e-06, "epoch": 2.0535966149506346, "percentage": 68.47, "elapsed_time": "22:55:13", "remaining_time": "10:33:12"}
94
+ {"current_steps": 920, "total_steps": 1329, "loss": 0.5296, "learning_rate": 2e-06, "epoch": 2.076163610719323, "percentage": 69.22, "elapsed_time": "23:10:02", "remaining_time": "10:17:57"}
95
+ {"current_steps": 930, "total_steps": 1329, "loss": 0.537, "learning_rate": 2e-06, "epoch": 2.098730606488011, "percentage": 69.98, "elapsed_time": "23:24:51", "remaining_time": "10:02:43"}
96
+ {"current_steps": 940, "total_steps": 1329, "loss": 0.5406, "learning_rate": 2e-06, "epoch": 2.1212976022566994, "percentage": 70.73, "elapsed_time": "23:39:39", "remaining_time": "9:47:29"}
97
+ {"current_steps": 950, "total_steps": 1329, "loss": 0.5421, "learning_rate": 2e-06, "epoch": 2.143864598025388, "percentage": 71.48, "elapsed_time": "23:54:27", "remaining_time": "9:32:16"}
98
+ {"current_steps": 960, "total_steps": 1329, "loss": 0.5381, "learning_rate": 2e-06, "epoch": 2.1664315937940763, "percentage": 72.23, "elapsed_time": "1 day, 0:09:16", "remaining_time": "9:17:03"}
99
+ {"current_steps": 970, "total_steps": 1329, "loss": 0.5349, "learning_rate": 2e-06, "epoch": 2.1889985895627646, "percentage": 72.99, "elapsed_time": "1 day, 0:24:04", "remaining_time": "9:01:51"}
100
+ {"current_steps": 980, "total_steps": 1329, "loss": 0.5289, "learning_rate": 2e-06, "epoch": 2.211565585331453, "percentage": 73.74, "elapsed_time": "1 day, 0:38:53", "remaining_time": "8:46:40"}
101
+ {"current_steps": 990, "total_steps": 1329, "loss": 0.5283, "learning_rate": 2e-06, "epoch": 2.234132581100141, "percentage": 74.49, "elapsed_time": "1 day, 0:53:42", "remaining_time": "8:31:29"}
102
+ {"current_steps": 1000, "total_steps": 1329, "loss": 0.5384, "learning_rate": 2e-06, "epoch": 2.2566995768688294, "percentage": 75.24, "elapsed_time": "1 day, 1:08:32", "remaining_time": "8:16:18"}
103
+ {"current_steps": 1010, "total_steps": 1329, "loss": 0.5449, "learning_rate": 2e-06, "epoch": 2.2792665726375176, "percentage": 76.0, "elapsed_time": "1 day, 1:23:21", "remaining_time": "8:01:08"}
104
+ {"current_steps": 1020, "total_steps": 1329, "loss": 0.5378, "learning_rate": 2e-06, "epoch": 2.301833568406206, "percentage": 76.75, "elapsed_time": "1 day, 1:38:10", "remaining_time": "7:45:58"}
105
+ {"current_steps": 1030, "total_steps": 1329, "loss": 0.5424, "learning_rate": 2e-06, "epoch": 2.324400564174894, "percentage": 77.5, "elapsed_time": "1 day, 1:52:59", "remaining_time": "7:30:49"}
106
+ {"current_steps": 1040, "total_steps": 1329, "loss": 0.5393, "learning_rate": 2e-06, "epoch": 2.3469675599435824, "percentage": 78.25, "elapsed_time": "1 day, 2:07:49", "remaining_time": "7:15:40"}
107
+ {"current_steps": 1050, "total_steps": 1329, "loss": 0.5363, "learning_rate": 2e-06, "epoch": 2.3695345557122707, "percentage": 79.01, "elapsed_time": "1 day, 2:22:39", "remaining_time": "7:00:32"}
108
+ {"current_steps": 1060, "total_steps": 1329, "loss": 0.5357, "learning_rate": 2e-06, "epoch": 2.392101551480959, "percentage": 79.76, "elapsed_time": "1 day, 2:37:27", "remaining_time": "6:45:23"}
109
+ {"current_steps": 1070, "total_steps": 1329, "loss": 0.5361, "learning_rate": 2e-06, "epoch": 2.414668547249647, "percentage": 80.51, "elapsed_time": "1 day, 2:52:16", "remaining_time": "6:30:15"}
110
+ {"current_steps": 1080, "total_steps": 1329, "loss": 0.5399, "learning_rate": 2e-06, "epoch": 2.4372355430183354, "percentage": 81.26, "elapsed_time": "1 day, 3:07:05", "remaining_time": "6:15:08"}
111
+ {"current_steps": 1090, "total_steps": 1329, "loss": 0.538, "learning_rate": 2e-06, "epoch": 2.459802538787024, "percentage": 82.02, "elapsed_time": "1 day, 3:21:54", "remaining_time": "6:00:00"}
112
+ {"current_steps": 1100, "total_steps": 1329, "loss": 0.5405, "learning_rate": 2e-06, "epoch": 2.4823695345557124, "percentage": 82.77, "elapsed_time": "1 day, 3:36:42", "remaining_time": "5:44:53"}
113
+ {"current_steps": 1110, "total_steps": 1329, "loss": 0.544, "learning_rate": 2e-06, "epoch": 2.5049365303244007, "percentage": 83.52, "elapsed_time": "1 day, 3:51:32", "remaining_time": "5:29:47"}
114
+ {"current_steps": 1120, "total_steps": 1329, "loss": 0.5332, "learning_rate": 2e-06, "epoch": 2.527503526093089, "percentage": 84.27, "elapsed_time": "1 day, 4:06:23", "remaining_time": "5:14:41"}
115
+ {"current_steps": 1130, "total_steps": 1329, "loss": 0.5387, "learning_rate": 2e-06, "epoch": 2.550070521861777, "percentage": 85.03, "elapsed_time": "1 day, 4:21:12", "remaining_time": "4:59:35"}
116
+ {"current_steps": 1140, "total_steps": 1329, "loss": 0.5366, "learning_rate": 2e-06, "epoch": 2.5726375176304654, "percentage": 85.78, "elapsed_time": "1 day, 4:36:01", "remaining_time": "4:44:30"}
117
+ {"current_steps": 1150, "total_steps": 1329, "loss": 0.5375, "learning_rate": 2e-06, "epoch": 2.5952045133991537, "percentage": 86.53, "elapsed_time": "1 day, 4:50:49", "remaining_time": "4:29:24"}
118
+ {"current_steps": 1160, "total_steps": 1329, "loss": 0.5411, "learning_rate": 2e-06, "epoch": 2.617771509167842, "percentage": 87.28, "elapsed_time": "1 day, 5:05:40", "remaining_time": "4:14:19"}
119
+ {"current_steps": 1170, "total_steps": 1329, "loss": 0.5286, "learning_rate": 2e-06, "epoch": 2.64033850493653, "percentage": 88.04, "elapsed_time": "1 day, 5:20:30", "remaining_time": "3:59:14"}
120
+ {"current_steps": 1180, "total_steps": 1329, "loss": 0.5404, "learning_rate": 2e-06, "epoch": 2.6629055007052185, "percentage": 88.79, "elapsed_time": "1 day, 5:35:20", "remaining_time": "3:44:10"}
121
+ {"current_steps": 1190, "total_steps": 1329, "loss": 0.541, "learning_rate": 2e-06, "epoch": 2.685472496473907, "percentage": 89.54, "elapsed_time": "1 day, 5:50:07", "remaining_time": "3:29:05"}
122
+ {"current_steps": 1200, "total_steps": 1329, "loss": 0.5393, "learning_rate": 2e-06, "epoch": 2.7080394922425954, "percentage": 90.29, "elapsed_time": "1 day, 6:04:58", "remaining_time": "3:14:02"}
123
+ {"current_steps": 1210, "total_steps": 1329, "loss": 0.5404, "learning_rate": 2e-06, "epoch": 2.7306064880112837, "percentage": 91.05, "elapsed_time": "1 day, 6:19:48", "remaining_time": "2:58:58"}
124
+ {"current_steps": 1220, "total_steps": 1329, "loss": 0.5361, "learning_rate": 2e-06, "epoch": 2.753173483779972, "percentage": 91.8, "elapsed_time": "1 day, 6:34:38", "remaining_time": "2:43:54"}
125
+ {"current_steps": 1230, "total_steps": 1329, "loss": 0.5434, "learning_rate": 2e-06, "epoch": 2.77574047954866, "percentage": 92.55, "elapsed_time": "1 day, 6:49:27", "remaining_time": "2:28:51"}
126
+ {"current_steps": 1240, "total_steps": 1329, "loss": 0.5417, "learning_rate": 2e-06, "epoch": 2.7983074753173485, "percentage": 93.3, "elapsed_time": "1 day, 7:04:16", "remaining_time": "2:13:48"}
127
+ {"current_steps": 1250, "total_steps": 1329, "loss": 0.5413, "learning_rate": 2e-06, "epoch": 2.8208744710860367, "percentage": 94.06, "elapsed_time": "1 day, 7:19:04", "remaining_time": "1:58:45"}
128
+ {"current_steps": 1260, "total_steps": 1329, "loss": 0.5431, "learning_rate": 2e-06, "epoch": 2.843441466854725, "percentage": 94.81, "elapsed_time": "1 day, 7:33:53", "remaining_time": "1:43:42"}
129
+ {"current_steps": 1270, "total_steps": 1329, "loss": 0.5396, "learning_rate": 2e-06, "epoch": 2.8660084626234132, "percentage": 95.56, "elapsed_time": "1 day, 7:48:40", "remaining_time": "1:28:40"}
130
+ {"current_steps": 1280, "total_steps": 1329, "loss": 0.5371, "learning_rate": 2e-06, "epoch": 2.8885754583921015, "percentage": 96.31, "elapsed_time": "1 day, 8:03:29", "remaining_time": "1:13:38"}
131
+ {"current_steps": 1290, "total_steps": 1329, "loss": 0.5416, "learning_rate": 2e-06, "epoch": 2.9111424541607898, "percentage": 97.07, "elapsed_time": "1 day, 8:18:20", "remaining_time": "0:58:36"}
132
+ {"current_steps": 1300, "total_steps": 1329, "loss": 0.5361, "learning_rate": 2e-06, "epoch": 2.933709449929478, "percentage": 97.82, "elapsed_time": "1 day, 8:33:09", "remaining_time": "0:43:34"}
133
+ {"current_steps": 1310, "total_steps": 1329, "loss": 0.5405, "learning_rate": 2e-06, "epoch": 2.9562764456981663, "percentage": 98.57, "elapsed_time": "1 day, 8:47:59", "remaining_time": "0:28:32"}
134
+ {"current_steps": 1320, "total_steps": 1329, "loss": 0.5356, "learning_rate": 2e-06, "epoch": 2.9788434414668545, "percentage": 99.32, "elapsed_time": "1 day, 9:02:49", "remaining_time": "0:13:31"}