Hugging Face's logo

mlfoundations-dev
/
hp_ablations_mistral_adambeta2_0.9995

Text Generation
Transformers
Safetensors
mistral
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
6aa897f
•
1 Parent(s): c89b0e8

Training in progress, epoch 2

Browse files
Files changed (4) hide show
  1. model-00001-of-00003.safetensors +1 -1
  2. model-00002-of-00003.safetensors +1 -1
  3. model-00003-of-00003.safetensors +1 -1
  4. trainer_log.jsonl +48 -0
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1749e8283cfe47e69e471c16ca542c0bf3f48ad4de330342e13ca8bdc7ba1c5c
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:136d8c3dc7ca01110e2aaaa7cd76b99240d959aa42e2b4960c9167bbdc257465
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8d4f5b5239daa502cf36a2cd2d8e79b31f11ec2338cfa06ad71d895417c15f0
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59ad63b44a12035c04913c2b2d9e90365714b8aa6aafafae249942fd8dd667e5
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:70f459bad2ce3f78e41bd4544302be7511ce65f148fa6b8caf5a5a89c48fad48
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd05581df393a08ef7b42de3ca6bec140fd037c3f7f35265f1a366889bc3fa90
3
  size 4540516344
trainer_log.jsonl CHANGED
@@ -99,3 +99,51 @@
99
  {"current_steps": 980, "total_steps": 1479, "loss": 0.481, "learning_rate": 5e-06, "epoch": 1.9848101265822784, "percentage": 66.26, "elapsed_time": "15:21:32", "remaining_time": "7:49:14"}
100
  {"current_steps": 987, "total_steps": 1479, "eval_loss": 0.06875930726528168, "epoch": 1.998987341772152, "percentage": 66.73, "elapsed_time": "15:36:54", "remaining_time": "7:47:01"}
101
  {"current_steps": 990, "total_steps": 1479, "loss": 0.4531, "learning_rate": 5e-06, "epoch": 2.0050632911392405, "percentage": 66.94, "elapsed_time": "15:40:20", "remaining_time": "7:44:28"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
99
  {"current_steps": 980, "total_steps": 1479, "loss": 0.481, "learning_rate": 5e-06, "epoch": 1.9848101265822784, "percentage": 66.26, "elapsed_time": "15:21:32", "remaining_time": "7:49:14"}
100
  {"current_steps": 987, "total_steps": 1479, "eval_loss": 0.06875930726528168, "epoch": 1.998987341772152, "percentage": 66.73, "elapsed_time": "15:36:54", "remaining_time": "7:47:01"}
101
  {"current_steps": 990, "total_steps": 1479, "loss": 0.4531, "learning_rate": 5e-06, "epoch": 2.0050632911392405, "percentage": 66.94, "elapsed_time": "15:40:20", "remaining_time": "7:44:28"}
102
+ {"current_steps": 1000, "total_steps": 1479, "loss": 0.3866, "learning_rate": 5e-06, "epoch": 2.0253164556962027, "percentage": 67.61, "elapsed_time": "15:49:39", "remaining_time": "7:34:53"}
103
+ {"current_steps": 1010, "total_steps": 1479, "loss": 0.3822, "learning_rate": 5e-06, "epoch": 2.0455696202531644, "percentage": 68.29, "elapsed_time": "15:58:59", "remaining_time": "7:25:18"}
104
+ {"current_steps": 1020, "total_steps": 1479, "loss": 0.3784, "learning_rate": 5e-06, "epoch": 2.0658227848101265, "percentage": 68.97, "elapsed_time": "16:08:19", "remaining_time": "7:15:44"}
105
+ {"current_steps": 1030, "total_steps": 1479, "loss": 0.3788, "learning_rate": 5e-06, "epoch": 2.0860759493670886, "percentage": 69.64, "elapsed_time": "16:17:38", "remaining_time": "7:06:10"}
106
+ {"current_steps": 1040, "total_steps": 1479, "loss": 0.3764, "learning_rate": 5e-06, "epoch": 2.1063291139240508, "percentage": 70.32, "elapsed_time": "16:26:58", "remaining_time": "6:56:37"}
107
+ {"current_steps": 1050, "total_steps": 1479, "loss": 0.3868, "learning_rate": 5e-06, "epoch": 2.1265822784810124, "percentage": 70.99, "elapsed_time": "16:36:18", "remaining_time": "6:47:03"}
108
+ {"current_steps": 1060, "total_steps": 1479, "loss": 0.3822, "learning_rate": 5e-06, "epoch": 2.1468354430379746, "percentage": 71.67, "elapsed_time": "16:45:38", "remaining_time": "6:37:30"}
109
+ {"current_steps": 1070, "total_steps": 1479, "loss": 0.3862, "learning_rate": 5e-06, "epoch": 2.1670886075949367, "percentage": 72.35, "elapsed_time": "16:54:59", "remaining_time": "6:27:58"}
110
+ {"current_steps": 1080, "total_steps": 1479, "loss": 0.384, "learning_rate": 5e-06, "epoch": 2.187341772151899, "percentage": 73.02, "elapsed_time": "17:04:19", "remaining_time": "6:18:25"}
111
+ {"current_steps": 1090, "total_steps": 1479, "loss": 0.3819, "learning_rate": 5e-06, "epoch": 2.207594936708861, "percentage": 73.7, "elapsed_time": "17:13:38", "remaining_time": "6:08:53"}
112
+ {"current_steps": 1100, "total_steps": 1479, "loss": 0.3912, "learning_rate": 5e-06, "epoch": 2.2278481012658227, "percentage": 74.37, "elapsed_time": "17:22:58", "remaining_time": "5:59:21"}
113
+ {"current_steps": 1110, "total_steps": 1479, "loss": 0.3874, "learning_rate": 5e-06, "epoch": 2.248101265822785, "percentage": 75.05, "elapsed_time": "17:32:19", "remaining_time": "5:49:49"}
114
+ {"current_steps": 1120, "total_steps": 1479, "loss": 0.39, "learning_rate": 5e-06, "epoch": 2.268354430379747, "percentage": 75.73, "elapsed_time": "17:41:39", "remaining_time": "5:40:17"}
115
+ {"current_steps": 1130, "total_steps": 1479, "loss": 0.3915, "learning_rate": 5e-06, "epoch": 2.2886075949367086, "percentage": 76.4, "elapsed_time": "17:50:59", "remaining_time": "5:30:46"}
116
+ {"current_steps": 1140, "total_steps": 1479, "loss": 0.3875, "learning_rate": 5e-06, "epoch": 2.3088607594936708, "percentage": 77.08, "elapsed_time": "18:00:19", "remaining_time": "5:21:15"}
117
+ {"current_steps": 1150, "total_steps": 1479, "loss": 0.3941, "learning_rate": 5e-06, "epoch": 2.329113924050633, "percentage": 77.76, "elapsed_time": "18:09:39", "remaining_time": "5:11:44"}
118
+ {"current_steps": 1160, "total_steps": 1479, "loss": 0.3937, "learning_rate": 5e-06, "epoch": 2.349367088607595, "percentage": 78.43, "elapsed_time": "18:19:00", "remaining_time": "5:02:13"}
119
+ {"current_steps": 1170, "total_steps": 1479, "loss": 0.3929, "learning_rate": 5e-06, "epoch": 2.369620253164557, "percentage": 79.11, "elapsed_time": "18:28:21", "remaining_time": "4:52:43"}
120
+ {"current_steps": 1180, "total_steps": 1479, "loss": 0.3925, "learning_rate": 5e-06, "epoch": 2.389873417721519, "percentage": 79.78, "elapsed_time": "18:37:43", "remaining_time": "4:43:13"}
121
+ {"current_steps": 1190, "total_steps": 1479, "loss": 0.3926, "learning_rate": 5e-06, "epoch": 2.410126582278481, "percentage": 80.46, "elapsed_time": "18:47:04", "remaining_time": "4:33:43"}
122
+ {"current_steps": 1200, "total_steps": 1479, "loss": 0.3917, "learning_rate": 5e-06, "epoch": 2.430379746835443, "percentage": 81.14, "elapsed_time": "18:56:25", "remaining_time": "4:24:13"}
123
+ {"current_steps": 1210, "total_steps": 1479, "loss": 0.392, "learning_rate": 5e-06, "epoch": 2.4506329113924052, "percentage": 81.81, "elapsed_time": "19:05:46", "remaining_time": "4:14:43"}
124
+ {"current_steps": 1220, "total_steps": 1479, "loss": 0.3945, "learning_rate": 5e-06, "epoch": 2.470886075949367, "percentage": 82.49, "elapsed_time": "19:15:07", "remaining_time": "4:05:13"}
125
+ {"current_steps": 1230, "total_steps": 1479, "loss": 0.3948, "learning_rate": 5e-06, "epoch": 2.491139240506329, "percentage": 83.16, "elapsed_time": "19:24:28", "remaining_time": "3:55:44"}
126
+ {"current_steps": 1240, "total_steps": 1479, "loss": 0.3994, "learning_rate": 5e-06, "epoch": 2.511392405063291, "percentage": 83.84, "elapsed_time": "19:33:48", "remaining_time": "3:46:14"}
127
+ {"current_steps": 1250, "total_steps": 1479, "loss": 0.3936, "learning_rate": 5e-06, "epoch": 2.5316455696202533, "percentage": 84.52, "elapsed_time": "19:43:09", "remaining_time": "3:36:45"}
128
+ {"current_steps": 1260, "total_steps": 1479, "loss": 0.3887, "learning_rate": 5e-06, "epoch": 2.5518987341772155, "percentage": 85.19, "elapsed_time": "19:52:30", "remaining_time": "3:27:16"}
129
+ {"current_steps": 1270, "total_steps": 1479, "loss": 0.3951, "learning_rate": 5e-06, "epoch": 2.572151898734177, "percentage": 85.87, "elapsed_time": "20:01:50", "remaining_time": "3:17:47"}
130
+ {"current_steps": 1280, "total_steps": 1479, "loss": 0.3969, "learning_rate": 5e-06, "epoch": 2.5924050632911393, "percentage": 86.54, "elapsed_time": "20:11:10", "remaining_time": "3:08:18"}
131
+ {"current_steps": 1290, "total_steps": 1479, "loss": 0.4018, "learning_rate": 5e-06, "epoch": 2.6126582278481014, "percentage": 87.22, "elapsed_time": "20:20:30", "remaining_time": "2:58:49"}
132
+ {"current_steps": 1300, "total_steps": 1479, "loss": 0.397, "learning_rate": 5e-06, "epoch": 2.632911392405063, "percentage": 87.9, "elapsed_time": "20:29:51", "remaining_time": "2:49:20"}
133
+ {"current_steps": 1310, "total_steps": 1479, "loss": 0.3972, "learning_rate": 5e-06, "epoch": 2.6531645569620252, "percentage": 88.57, "elapsed_time": "20:39:11", "remaining_time": "2:39:51"}
134
+ {"current_steps": 1320, "total_steps": 1479, "loss": 0.4001, "learning_rate": 5e-06, "epoch": 2.6734177215189874, "percentage": 89.25, "elapsed_time": "20:48:32", "remaining_time": "2:30:23"}
135
+ {"current_steps": 1330, "total_steps": 1479, "loss": 0.4023, "learning_rate": 5e-06, "epoch": 2.6936708860759495, "percentage": 89.93, "elapsed_time": "20:57:52", "remaining_time": "2:20:55"}
136
+ {"current_steps": 1340, "total_steps": 1479, "loss": 0.4004, "learning_rate": 5e-06, "epoch": 2.7139240506329116, "percentage": 90.6, "elapsed_time": "21:07:12", "remaining_time": "2:11:26"}
137
+ {"current_steps": 1350, "total_steps": 1479, "loss": 0.3999, "learning_rate": 5e-06, "epoch": 2.7341772151898733, "percentage": 91.28, "elapsed_time": "21:16:33", "remaining_time": "2:01:58"}
138
+ {"current_steps": 1360, "total_steps": 1479, "loss": 0.3955, "learning_rate": 5e-06, "epoch": 2.7544303797468355, "percentage": 91.95, "elapsed_time": "21:25:54", "remaining_time": "1:52:30"}
139
+ {"current_steps": 1370, "total_steps": 1479, "loss": 0.4017, "learning_rate": 5e-06, "epoch": 2.7746835443037976, "percentage": 92.63, "elapsed_time": "21:35:15", "remaining_time": "1:43:03"}
140
+ {"current_steps": 1380, "total_steps": 1479, "loss": 0.3994, "learning_rate": 5e-06, "epoch": 2.7949367088607593, "percentage": 93.31, "elapsed_time": "21:44:36", "remaining_time": "1:33:35"}
141
+ {"current_steps": 1390, "total_steps": 1479, "loss": 0.4019, "learning_rate": 5e-06, "epoch": 2.8151898734177214, "percentage": 93.98, "elapsed_time": "21:53:56", "remaining_time": "1:24:07"}
142
+ {"current_steps": 1400, "total_steps": 1479, "loss": 0.3953, "learning_rate": 5e-06, "epoch": 2.8354430379746836, "percentage": 94.66, "elapsed_time": "22:03:17", "remaining_time": "1:14:40"}
143
+ {"current_steps": 1410, "total_steps": 1479, "loss": 0.4043, "learning_rate": 5e-06, "epoch": 2.8556962025316457, "percentage": 95.33, "elapsed_time": "22:12:38", "remaining_time": "1:05:12"}
144
+ {"current_steps": 1420, "total_steps": 1479, "loss": 0.4001, "learning_rate": 5e-06, "epoch": 2.875949367088608, "percentage": 96.01, "elapsed_time": "22:21:59", "remaining_time": "0:55:45"}
145
+ {"current_steps": 1430, "total_steps": 1479, "loss": 0.4007, "learning_rate": 5e-06, "epoch": 2.8962025316455695, "percentage": 96.69, "elapsed_time": "22:31:20", "remaining_time": "0:46:18"}
146
+ {"current_steps": 1440, "total_steps": 1479, "loss": 0.4032, "learning_rate": 5e-06, "epoch": 2.9164556962025316, "percentage": 97.36, "elapsed_time": "22:40:41", "remaining_time": "0:36:51"}
147
+ {"current_steps": 1450, "total_steps": 1479, "loss": 0.4118, "learning_rate": 5e-06, "epoch": 2.9367088607594938, "percentage": 98.04, "elapsed_time": "22:50:01", "remaining_time": "0:27:24"}
148
+ {"current_steps": 1460, "total_steps": 1479, "loss": 0.3999, "learning_rate": 5e-06, "epoch": 2.9569620253164555, "percentage": 98.72, "elapsed_time": "22:59:23", "remaining_time": "0:17:57"}
149
+ {"current_steps": 1470, "total_steps": 1479, "loss": 0.404, "learning_rate": 5e-06, "epoch": 2.9772151898734176, "percentage": 99.39, "elapsed_time": "23:08:43", "remaining_time": "0:08:30"}