Hugging Face's logo

mlfoundations-dev
/
hp_ablations_mistral_lr8e-6

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
8ac4e19
•
1 Parent(s): 5926430

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 sha256:0ceb83a822514418c85c85f11a2afcf83106708f1601b8d708d1489979762468
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb353802ae8a00e30476a20c12ffa86bc1deb6d7989104e23f1d87a01bd003b4
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6943bf53c42c4c17f1d40a763d87ae3f4e6a413415d5ae62bda815cb6f864a52
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5f0344067322ad5f3c0120cad708d234f4f15caaa92f71a49361893d0248e38
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:653a97732bbf16a96518bca56c8daf90f3eb0cd0c43a5b170899a370169a6b6f
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:790267ffb4c8e9bd83cf1215d1980b3e089935d258ce38608ced1050a54183db
3
  size 4540516344
trainer_log.jsonl CHANGED
@@ -99,3 +99,51 @@
99
  {"current_steps": 980, "total_steps": 1479, "loss": 0.4701, "learning_rate": 8e-06, "epoch": 1.9848101265822784, "percentage": 66.26, "elapsed_time": "15:25:53", "remaining_time": "7:51:26"}
100
  {"current_steps": 987, "total_steps": 1479, "eval_loss": 0.07048599421977997, "epoch": 1.998987341772152, "percentage": 66.73, "elapsed_time": "15:41:21", "remaining_time": "7:49:15"}
101
  {"current_steps": 990, "total_steps": 1479, "loss": 0.4369, "learning_rate": 8e-06, "epoch": 2.0050632911392405, "percentage": 66.94, "elapsed_time": "15:44:49", "remaining_time": "7:46:41"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
99
  {"current_steps": 980, "total_steps": 1479, "loss": 0.4701, "learning_rate": 8e-06, "epoch": 1.9848101265822784, "percentage": 66.26, "elapsed_time": "15:25:53", "remaining_time": "7:51:26"}
100
  {"current_steps": 987, "total_steps": 1479, "eval_loss": 0.07048599421977997, "epoch": 1.998987341772152, "percentage": 66.73, "elapsed_time": "15:41:21", "remaining_time": "7:49:15"}
101
  {"current_steps": 990, "total_steps": 1479, "loss": 0.4369, "learning_rate": 8e-06, "epoch": 2.0050632911392405, "percentage": 66.94, "elapsed_time": "15:44:49", "remaining_time": "7:46:41"}
102
+ {"current_steps": 1000, "total_steps": 1479, "loss": 0.3497, "learning_rate": 8e-06, "epoch": 2.0253164556962027, "percentage": 67.61, "elapsed_time": "15:54:11", "remaining_time": "7:37:03"}
103
+ {"current_steps": 1010, "total_steps": 1479, "loss": 0.3424, "learning_rate": 8e-06, "epoch": 2.0455696202531644, "percentage": 68.29, "elapsed_time": "16:03:33", "remaining_time": "7:27:25"}
104
+ {"current_steps": 1020, "total_steps": 1479, "loss": 0.3358, "learning_rate": 8e-06, "epoch": 2.0658227848101265, "percentage": 68.97, "elapsed_time": "16:12:54", "remaining_time": "7:17:48"}
105
+ {"current_steps": 1030, "total_steps": 1479, "loss": 0.3358, "learning_rate": 8e-06, "epoch": 2.0860759493670886, "percentage": 69.64, "elapsed_time": "16:22:17", "remaining_time": "7:08:12"}
106
+ {"current_steps": 1040, "total_steps": 1479, "loss": 0.3338, "learning_rate": 8e-06, "epoch": 2.1063291139240508, "percentage": 70.32, "elapsed_time": "16:31:40", "remaining_time": "6:58:35"}
107
+ {"current_steps": 1050, "total_steps": 1479, "loss": 0.3438, "learning_rate": 8e-06, "epoch": 2.1265822784810124, "percentage": 70.99, "elapsed_time": "16:41:02", "remaining_time": "6:48:59"}
108
+ {"current_steps": 1060, "total_steps": 1479, "loss": 0.3403, "learning_rate": 8e-06, "epoch": 2.1468354430379746, "percentage": 71.67, "elapsed_time": "16:50:24", "remaining_time": "6:39:23"}
109
+ {"current_steps": 1070, "total_steps": 1479, "loss": 0.3442, "learning_rate": 8e-06, "epoch": 2.1670886075949367, "percentage": 72.35, "elapsed_time": "16:59:45", "remaining_time": "6:29:47"}
110
+ {"current_steps": 1080, "total_steps": 1479, "loss": 0.3428, "learning_rate": 8e-06, "epoch": 2.187341772151899, "percentage": 73.02, "elapsed_time": "17:09:06", "remaining_time": "6:20:11"}
111
+ {"current_steps": 1090, "total_steps": 1479, "loss": 0.3416, "learning_rate": 8e-06, "epoch": 2.207594936708861, "percentage": 73.7, "elapsed_time": "17:18:27", "remaining_time": "6:10:36"}
112
+ {"current_steps": 1100, "total_steps": 1479, "loss": 0.3499, "learning_rate": 8e-06, "epoch": 2.2278481012658227, "percentage": 74.37, "elapsed_time": "17:27:49", "remaining_time": "6:01:01"}
113
+ {"current_steps": 1110, "total_steps": 1479, "loss": 0.3452, "learning_rate": 8e-06, "epoch": 2.248101265822785, "percentage": 75.05, "elapsed_time": "17:37:11", "remaining_time": "5:51:26"}
114
+ {"current_steps": 1120, "total_steps": 1479, "loss": 0.3479, "learning_rate": 8e-06, "epoch": 2.268354430379747, "percentage": 75.73, "elapsed_time": "17:46:33", "remaining_time": "5:41:52"}
115
+ {"current_steps": 1130, "total_steps": 1479, "loss": 0.3481, "learning_rate": 8e-06, "epoch": 2.2886075949367086, "percentage": 76.4, "elapsed_time": "17:55:56", "remaining_time": "5:32:18"}
116
+ {"current_steps": 1140, "total_steps": 1479, "loss": 0.3456, "learning_rate": 8e-06, "epoch": 2.3088607594936708, "percentage": 77.08, "elapsed_time": "18:05:18", "remaining_time": "5:22:44"}
117
+ {"current_steps": 1150, "total_steps": 1479, "loss": 0.3517, "learning_rate": 8e-06, "epoch": 2.329113924050633, "percentage": 77.76, "elapsed_time": "18:14:39", "remaining_time": "5:13:10"}
118
+ {"current_steps": 1160, "total_steps": 1479, "loss": 0.3532, "learning_rate": 8e-06, "epoch": 2.349367088607595, "percentage": 78.43, "elapsed_time": "18:24:01", "remaining_time": "5:03:36"}
119
+ {"current_steps": 1170, "total_steps": 1479, "loss": 0.3583, "learning_rate": 8e-06, "epoch": 2.369620253164557, "percentage": 79.11, "elapsed_time": "18:33:22", "remaining_time": "4:54:02"}
120
+ {"current_steps": 1180, "total_steps": 1479, "loss": 0.3536, "learning_rate": 8e-06, "epoch": 2.389873417721519, "percentage": 79.78, "elapsed_time": "18:42:44", "remaining_time": "4:44:29"}
121
+ {"current_steps": 1190, "total_steps": 1479, "loss": 0.3529, "learning_rate": 8e-06, "epoch": 2.410126582278481, "percentage": 80.46, "elapsed_time": "18:52:07", "remaining_time": "4:34:56"}
122
+ {"current_steps": 1200, "total_steps": 1479, "loss": 0.3519, "learning_rate": 8e-06, "epoch": 2.430379746835443, "percentage": 81.14, "elapsed_time": "19:01:29", "remaining_time": "4:25:23"}
123
+ {"current_steps": 1210, "total_steps": 1479, "loss": 0.351, "learning_rate": 8e-06, "epoch": 2.4506329113924052, "percentage": 81.81, "elapsed_time": "19:10:53", "remaining_time": "4:15:51"}
124
+ {"current_steps": 1220, "total_steps": 1479, "loss": 0.355, "learning_rate": 8e-06, "epoch": 2.470886075949367, "percentage": 82.49, "elapsed_time": "19:20:15", "remaining_time": "4:06:19"}
125
+ {"current_steps": 1230, "total_steps": 1479, "loss": 0.3531, "learning_rate": 8e-06, "epoch": 2.491139240506329, "percentage": 83.16, "elapsed_time": "19:29:38", "remaining_time": "3:56:46"}
126
+ {"current_steps": 1240, "total_steps": 1479, "loss": 0.3567, "learning_rate": 8e-06, "epoch": 2.511392405063291, "percentage": 83.84, "elapsed_time": "19:39:01", "remaining_time": "3:47:14"}
127
+ {"current_steps": 1250, "total_steps": 1479, "loss": 0.3508, "learning_rate": 8e-06, "epoch": 2.5316455696202533, "percentage": 84.52, "elapsed_time": "19:48:24", "remaining_time": "3:37:42"}
128
+ {"current_steps": 1260, "total_steps": 1479, "loss": 0.3467, "learning_rate": 8e-06, "epoch": 2.5518987341772155, "percentage": 85.19, "elapsed_time": "19:57:46", "remaining_time": "3:28:10"}
129
+ {"current_steps": 1270, "total_steps": 1479, "loss": 0.3528, "learning_rate": 8e-06, "epoch": 2.572151898734177, "percentage": 85.87, "elapsed_time": "20:07:07", "remaining_time": "3:18:39"}
130
+ {"current_steps": 1280, "total_steps": 1479, "loss": 0.3565, "learning_rate": 8e-06, "epoch": 2.5924050632911393, "percentage": 86.54, "elapsed_time": "20:16:29", "remaining_time": "3:09:07"}
131
+ {"current_steps": 1290, "total_steps": 1479, "loss": 0.3616, "learning_rate": 8e-06, "epoch": 2.6126582278481014, "percentage": 87.22, "elapsed_time": "20:25:51", "remaining_time": "2:59:36"}
132
+ {"current_steps": 1300, "total_steps": 1479, "loss": 0.3577, "learning_rate": 8e-06, "epoch": 2.632911392405063, "percentage": 87.9, "elapsed_time": "20:35:12", "remaining_time": "2:50:04"}
133
+ {"current_steps": 1310, "total_steps": 1479, "loss": 0.3581, "learning_rate": 8e-06, "epoch": 2.6531645569620252, "percentage": 88.57, "elapsed_time": "20:44:34", "remaining_time": "2:40:33"}
134
+ {"current_steps": 1320, "total_steps": 1479, "loss": 0.3612, "learning_rate": 8e-06, "epoch": 2.6734177215189874, "percentage": 89.25, "elapsed_time": "20:53:56", "remaining_time": "2:31:02"}
135
+ {"current_steps": 1330, "total_steps": 1479, "loss": 0.3631, "learning_rate": 8e-06, "epoch": 2.6936708860759495, "percentage": 89.93, "elapsed_time": "21:03:17", "remaining_time": "2:21:31"}
136
+ {"current_steps": 1340, "total_steps": 1479, "loss": 0.3619, "learning_rate": 8e-06, "epoch": 2.7139240506329116, "percentage": 90.6, "elapsed_time": "21:12:40", "remaining_time": "2:12:00"}
137
+ {"current_steps": 1350, "total_steps": 1479, "loss": 0.3624, "learning_rate": 8e-06, "epoch": 2.7341772151898733, "percentage": 91.28, "elapsed_time": "21:22:02", "remaining_time": "2:02:30"}
138
+ {"current_steps": 1360, "total_steps": 1479, "loss": 0.359, "learning_rate": 8e-06, "epoch": 2.7544303797468355, "percentage": 91.95, "elapsed_time": "21:31:23", "remaining_time": "1:52:59"}
139
+ {"current_steps": 1370, "total_steps": 1479, "loss": 0.3646, "learning_rate": 8e-06, "epoch": 2.7746835443037976, "percentage": 92.63, "elapsed_time": "21:40:45", "remaining_time": "1:43:29"}
140
+ {"current_steps": 1380, "total_steps": 1479, "loss": 0.3629, "learning_rate": 8e-06, "epoch": 2.7949367088607593, "percentage": 93.31, "elapsed_time": "21:50:08", "remaining_time": "1:33:59"}
141
+ {"current_steps": 1390, "total_steps": 1479, "loss": 0.3659, "learning_rate": 8e-06, "epoch": 2.8151898734177214, "percentage": 93.98, "elapsed_time": "21:59:31", "remaining_time": "1:24:29"}
142
+ {"current_steps": 1400, "total_steps": 1479, "loss": 0.3602, "learning_rate": 8e-06, "epoch": 2.8354430379746836, "percentage": 94.66, "elapsed_time": "22:08:54", "remaining_time": "1:14:59"}
143
+ {"current_steps": 1410, "total_steps": 1479, "loss": 0.3684, "learning_rate": 8e-06, "epoch": 2.8556962025316457, "percentage": 95.33, "elapsed_time": "22:18:16", "remaining_time": "1:05:29"}
144
+ {"current_steps": 1420, "total_steps": 1479, "loss": 0.3651, "learning_rate": 8e-06, "epoch": 2.875949367088608, "percentage": 96.01, "elapsed_time": "22:27:38", "remaining_time": "0:55:59"}
145
+ {"current_steps": 1430, "total_steps": 1479, "loss": 0.3659, "learning_rate": 8e-06, "epoch": 2.8962025316455695, "percentage": 96.69, "elapsed_time": "22:37:01", "remaining_time": "0:46:29"}
146
+ {"current_steps": 1440, "total_steps": 1479, "loss": 0.3671, "learning_rate": 8e-06, "epoch": 2.9164556962025316, "percentage": 97.36, "elapsed_time": "22:46:25", "remaining_time": "0:37:00"}
147
+ {"current_steps": 1450, "total_steps": 1479, "loss": 0.3762, "learning_rate": 8e-06, "epoch": 2.9367088607594938, "percentage": 98.04, "elapsed_time": "22:55:46", "remaining_time": "0:27:30"}
148
+ {"current_steps": 1460, "total_steps": 1479, "loss": 0.3658, "learning_rate": 8e-06, "epoch": 2.9569620253164555, "percentage": 98.72, "elapsed_time": "23:05:09", "remaining_time": "0:18:01"}
149
+ {"current_steps": 1470, "total_steps": 1479, "loss": 0.3691, "learning_rate": 8e-06, "epoch": 2.9772151898734176, "percentage": 99.39, "elapsed_time": "23:14:31", "remaining_time": "0:08:32"}