Hugging Face's logo

mlfoundations-dev
/
hp_ablations_gemma_lr1e-5

Text Generation
Transformers
Safetensors
gemma2
llama-factory
full
Generated from Trainer
text-generation-inference
Model card Files
xet
Community
sedrickkeh commited on
Commit
2d5eb9e
·
verified ·
1 Parent(s): 7a743d5

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:d765c580228f9572516ab474bab082e0bdc04fa626ad0a147ad12ae6a3efa21d
3
  size 4903351912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2d290557a3c90784b207ffc4887b12483a08a4e56f8655923feb9d0773339dd
3
  size 4903351912
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57621ff256c1b4783a9fc0e93ae5bde41727cdf40dc49e0c0ac857f8625863bf
3
  size 4947570872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b138091963772b0d042bc4cb3d3ee34506fa8bef9156c001e5211686b39e2fa5
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:a438604bec9fe1aae64f36608689141cb7243963918ac5e029df90bef8ad77f1
3
  size 4962221464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cad533614925775217a605c1a4b1a1e96aaf5967aeb224e539434f2845ecb2fd
3
  size 4962221464
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8255396b5e7c9892e3721e0c48cd5441267ef377fe2dc95949ac91320d109874
3
  size 3670322200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d1673eb355b7c7fb461c872c97afbce8f9aa4735b5da4d803c420b34299ab5b
3
  size 3670322200
trainer_log.jsonl CHANGED
@@ -88,3 +88,47 @@
88
  {"current_steps": 870, "total_steps": 1329, "loss": 0.5283, "learning_rate": 1e-05, "epoch": 1.9633286318758816, "percentage": 65.46, "elapsed_time": "21:35:48", "remaining_time": "11:23:39"}
89
  {"current_steps": 880, "total_steps": 1329, "loss": 0.5266, "learning_rate": 1e-05, "epoch": 1.9858956276445698, "percentage": 66.22, "elapsed_time": "21:50:34", "remaining_time": "11:08:41"}
90
  {"current_steps": 886, "total_steps": 1329, "eval_loss": 0.5968770980834961, "epoch": 1.9994358251057829, "percentage": 66.67, "elapsed_time": "22:11:10", "remaining_time": "11:05:35"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
88
  {"current_steps": 870, "total_steps": 1329, "loss": 0.5283, "learning_rate": 1e-05, "epoch": 1.9633286318758816, "percentage": 65.46, "elapsed_time": "21:35:48", "remaining_time": "11:23:39"}
89
  {"current_steps": 880, "total_steps": 1329, "loss": 0.5266, "learning_rate": 1e-05, "epoch": 1.9858956276445698, "percentage": 66.22, "elapsed_time": "21:50:34", "remaining_time": "11:08:41"}
90
  {"current_steps": 886, "total_steps": 1329, "eval_loss": 0.5968770980834961, "epoch": 1.9994358251057829, "percentage": 66.67, "elapsed_time": "22:11:10", "remaining_time": "11:05:35"}
91
+ {"current_steps": 890, "total_steps": 1329, "loss": 0.5349, "learning_rate": 1e-05, "epoch": 2.008462623413258, "percentage": 66.97, "elapsed_time": "22:18:07", "remaining_time": "11:00:02"}
92
+ {"current_steps": 900, "total_steps": 1329, "loss": 0.424, "learning_rate": 1e-05, "epoch": 2.0310296191819464, "percentage": 67.72, "elapsed_time": "22:32:52", "remaining_time": "10:44:52"}
93
+ {"current_steps": 910, "total_steps": 1329, "loss": 0.4237, "learning_rate": 1e-05, "epoch": 2.0535966149506346, "percentage": 68.47, "elapsed_time": "22:47:37", "remaining_time": "10:29:42"}
94
+ {"current_steps": 920, "total_steps": 1329, "loss": 0.4165, "learning_rate": 1e-05, "epoch": 2.076163610719323, "percentage": 69.22, "elapsed_time": "23:02:22", "remaining_time": "10:14:33"}
95
+ {"current_steps": 930, "total_steps": 1329, "loss": 0.4236, "learning_rate": 1e-05, "epoch": 2.098730606488011, "percentage": 69.98, "elapsed_time": "23:17:07", "remaining_time": "9:59:24"}
96
+ {"current_steps": 940, "total_steps": 1329, "loss": 0.4282, "learning_rate": 1e-05, "epoch": 2.1212976022566994, "percentage": 70.73, "elapsed_time": "23:31:52", "remaining_time": "9:44:16"}
97
+ {"current_steps": 950, "total_steps": 1329, "loss": 0.4303, "learning_rate": 1e-05, "epoch": 2.143864598025388, "percentage": 71.48, "elapsed_time": "23:46:37", "remaining_time": "9:29:08"}
98
+ {"current_steps": 960, "total_steps": 1329, "loss": 0.4271, "learning_rate": 1e-05, "epoch": 2.1664315937940763, "percentage": 72.23, "elapsed_time": "1 day, 0:01:22", "remaining_time": "9:14:01"}
99
+ {"current_steps": 970, "total_steps": 1329, "loss": 0.4268, "learning_rate": 1e-05, "epoch": 2.1889985895627646, "percentage": 72.99, "elapsed_time": "1 day, 0:16:07", "remaining_time": "8:58:55"}
100
+ {"current_steps": 980, "total_steps": 1329, "loss": 0.4228, "learning_rate": 1e-05, "epoch": 2.211565585331453, "percentage": 73.74, "elapsed_time": "1 day, 0:30:53", "remaining_time": "8:43:49"}
101
+ {"current_steps": 990, "total_steps": 1329, "loss": 0.4235, "learning_rate": 1e-05, "epoch": 2.234132581100141, "percentage": 74.49, "elapsed_time": "1 day, 0:45:38", "remaining_time": "8:28:43"}
102
+ {"current_steps": 1000, "total_steps": 1329, "loss": 0.4311, "learning_rate": 1e-05, "epoch": 2.2566995768688294, "percentage": 75.24, "elapsed_time": "1 day, 1:00:23", "remaining_time": "8:13:37"}
103
+ {"current_steps": 1010, "total_steps": 1329, "loss": 0.4372, "learning_rate": 1e-05, "epoch": 2.2792665726375176, "percentage": 76.0, "elapsed_time": "1 day, 1:15:09", "remaining_time": "7:58:32"}
104
+ {"current_steps": 1020, "total_steps": 1329, "loss": 0.4334, "learning_rate": 1e-05, "epoch": 2.301833568406206, "percentage": 76.75, "elapsed_time": "1 day, 1:29:54", "remaining_time": "7:43:28"}
105
+ {"current_steps": 1030, "total_steps": 1329, "loss": 0.4375, "learning_rate": 1e-05, "epoch": 2.324400564174894, "percentage": 77.5, "elapsed_time": "1 day, 1:44:39", "remaining_time": "7:28:24"}
106
+ {"current_steps": 1040, "total_steps": 1329, "loss": 0.4363, "learning_rate": 1e-05, "epoch": 2.3469675599435824, "percentage": 78.25, "elapsed_time": "1 day, 1:59:24", "remaining_time": "7:13:20"}
107
+ {"current_steps": 1050, "total_steps": 1329, "loss": 0.4348, "learning_rate": 1e-05, "epoch": 2.3695345557122707, "percentage": 79.01, "elapsed_time": "1 day, 2:14:09", "remaining_time": "6:58:16"}
108
+ {"current_steps": 1060, "total_steps": 1329, "loss": 0.4342, "learning_rate": 1e-05, "epoch": 2.392101551480959, "percentage": 79.76, "elapsed_time": "1 day, 2:28:55", "remaining_time": "6:43:13"}
109
+ {"current_steps": 1070, "total_steps": 1329, "loss": 0.4358, "learning_rate": 1e-05, "epoch": 2.414668547249647, "percentage": 80.51, "elapsed_time": "1 day, 2:43:40", "remaining_time": "6:28:10"}
110
+ {"current_steps": 1080, "total_steps": 1329, "loss": 0.4385, "learning_rate": 1e-05, "epoch": 2.4372355430183354, "percentage": 81.26, "elapsed_time": "1 day, 2:58:25", "remaining_time": "6:13:08"}
111
+ {"current_steps": 1090, "total_steps": 1329, "loss": 0.4376, "learning_rate": 1e-05, "epoch": 2.459802538787024, "percentage": 82.02, "elapsed_time": "1 day, 3:13:11", "remaining_time": "5:58:06"}
112
+ {"current_steps": 1100, "total_steps": 1329, "loss": 0.4416, "learning_rate": 1e-05, "epoch": 2.4823695345557124, "percentage": 82.77, "elapsed_time": "1 day, 3:27:56", "remaining_time": "5:43:04"}
113
+ {"current_steps": 1110, "total_steps": 1329, "loss": 0.4442, "learning_rate": 1e-05, "epoch": 2.5049365303244007, "percentage": 83.52, "elapsed_time": "1 day, 3:42:41", "remaining_time": "5:28:02"}
114
+ {"current_steps": 1120, "total_steps": 1329, "loss": 0.4367, "learning_rate": 1e-05, "epoch": 2.527503526093089, "percentage": 84.27, "elapsed_time": "1 day, 3:57:26", "remaining_time": "5:13:01"}
115
+ {"current_steps": 1130, "total_steps": 1329, "loss": 0.4413, "learning_rate": 1e-05, "epoch": 2.550070521861777, "percentage": 85.03, "elapsed_time": "1 day, 4:12:11", "remaining_time": "4:58:00"}
116
+ {"current_steps": 1140, "total_steps": 1329, "loss": 0.4398, "learning_rate": 1e-05, "epoch": 2.5726375176304654, "percentage": 85.78, "elapsed_time": "1 day, 4:26:57", "remaining_time": "4:42:59"}
117
+ {"current_steps": 1150, "total_steps": 1329, "loss": 0.4405, "learning_rate": 1e-05, "epoch": 2.5952045133991537, "percentage": 86.53, "elapsed_time": "1 day, 4:41:42", "remaining_time": "4:27:59"}
118
+ {"current_steps": 1160, "total_steps": 1329, "loss": 0.4442, "learning_rate": 1e-05, "epoch": 2.617771509167842, "percentage": 87.28, "elapsed_time": "1 day, 4:56:27", "remaining_time": "4:12:59"}
119
+ {"current_steps": 1170, "total_steps": 1329, "loss": 0.435, "learning_rate": 1e-05, "epoch": 2.64033850493653, "percentage": 88.04, "elapsed_time": "1 day, 5:11:12", "remaining_time": "3:57:59"}
120
+ {"current_steps": 1180, "total_steps": 1329, "loss": 0.4449, "learning_rate": 1e-05, "epoch": 2.6629055007052185, "percentage": 88.79, "elapsed_time": "1 day, 5:25:58", "remaining_time": "3:42:59"}
121
+ {"current_steps": 1190, "total_steps": 1329, "loss": 0.4456, "learning_rate": 1e-05, "epoch": 2.685472496473907, "percentage": 89.54, "elapsed_time": "1 day, 5:40:43", "remaining_time": "3:27:59"}
122
+ {"current_steps": 1200, "total_steps": 1329, "loss": 0.4447, "learning_rate": 1e-05, "epoch": 2.7080394922425954, "percentage": 90.29, "elapsed_time": "1 day, 5:55:27", "remaining_time": "3:13:00"}
123
+ {"current_steps": 1210, "total_steps": 1329, "loss": 0.4459, "learning_rate": 1e-05, "epoch": 2.7306064880112837, "percentage": 91.05, "elapsed_time": "1 day, 6:10:12", "remaining_time": "2:58:01"}
124
+ {"current_steps": 1220, "total_steps": 1329, "loss": 0.4434, "learning_rate": 1e-05, "epoch": 2.753173483779972, "percentage": 91.8, "elapsed_time": "1 day, 6:24:57", "remaining_time": "2:43:02"}
125
+ {"current_steps": 1230, "total_steps": 1329, "loss": 0.4496, "learning_rate": 1e-05, "epoch": 2.77574047954866, "percentage": 92.55, "elapsed_time": "1 day, 6:39:42", "remaining_time": "2:28:04"}
126
+ {"current_steps": 1240, "total_steps": 1329, "loss": 0.4476, "learning_rate": 1e-05, "epoch": 2.7983074753173485, "percentage": 93.3, "elapsed_time": "1 day, 6:54:27", "remaining_time": "2:13:06"}
127
+ {"current_steps": 1250, "total_steps": 1329, "loss": 0.4485, "learning_rate": 1e-05, "epoch": 2.8208744710860367, "percentage": 94.06, "elapsed_time": "1 day, 7:09:12", "remaining_time": "1:58:08"}
128
+ {"current_steps": 1260, "total_steps": 1329, "loss": 0.4503, "learning_rate": 1e-05, "epoch": 2.843441466854725, "percentage": 94.81, "elapsed_time": "1 day, 7:23:56", "remaining_time": "1:43:10"}
129
+ {"current_steps": 1270, "total_steps": 1329, "loss": 0.448, "learning_rate": 1e-05, "epoch": 2.8660084626234132, "percentage": 95.56, "elapsed_time": "1 day, 7:38:41", "remaining_time": "1:28:12"}
130
+ {"current_steps": 1280, "total_steps": 1329, "loss": 0.4467, "learning_rate": 1e-05, "epoch": 2.8885754583921015, "percentage": 96.31, "elapsed_time": "1 day, 7:53:26", "remaining_time": "1:13:14"}
131
+ {"current_steps": 1290, "total_steps": 1329, "loss": 0.4495, "learning_rate": 1e-05, "epoch": 2.9111424541607898, "percentage": 97.07, "elapsed_time": "1 day, 8:08:11", "remaining_time": "0:58:17"}
132
+ {"current_steps": 1300, "total_steps": 1329, "loss": 0.446, "learning_rate": 1e-05, "epoch": 2.933709449929478, "percentage": 97.82, "elapsed_time": "1 day, 8:22:56", "remaining_time": "0:43:20"}
133
+ {"current_steps": 1310, "total_steps": 1329, "loss": 0.4494, "learning_rate": 1e-05, "epoch": 2.9562764456981663, "percentage": 98.57, "elapsed_time": "1 day, 8:37:41", "remaining_time": "0:28:23"}
134
+ {"current_steps": 1320, "total_steps": 1329, "loss": 0.4473, "learning_rate": 1e-05, "epoch": 2.9788434414668545, "percentage": 99.32, "elapsed_time": "1 day, 8:52:26", "remaining_time": "0:13:26"}