Hugging Face's logo

mlfoundations-dev
/
hp_ablations_mistral_scheduler_constant

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
d1442fe
•
1 Parent(s): 6109b69

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 +49 -0
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:952612b591e676ab709e3fcda22d7c18866357d5894aad8a5afca1322763c87c
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34bb2e8defede2ecd69f5fd85e6da85a2c58850936af106d694f794e85036801
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1348e8487d5b0078b702765780b7310d4732fe43b47436da3895e1f697f338af
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0362043420ebdb97239d890306c49aba369bee2dac4bcbd9a35f6e21a9dbe14
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e1d17fbb1abf5c11f9e50e8d04ba97940051feffad68efa09356feddfb0b8c9
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76af9ae6f966b341eeead7c5bce47b1b3cc5e5213fd714b3c5b6377af73ac177
3
  size 4540516344
trainer_log.jsonl CHANGED
@@ -98,3 +98,52 @@
98
  {"current_steps": 970, "total_steps": 1479, "loss": 0.4849, "learning_rate": 5e-06, "epoch": 1.9645569620253165, "percentage": 65.58, "elapsed_time": "15:14:21", "remaining_time": "7:59:48"}
99
  {"current_steps": 980, "total_steps": 1479, "loss": 0.485, "learning_rate": 5e-06, "epoch": 1.9848101265822784, "percentage": 66.26, "elapsed_time": "15:23:42", "remaining_time": "7:50:20"}
100
  {"current_steps": 987, "total_steps": 1479, "eval_loss": 0.0688759982585907, "epoch": 1.998987341772152, "percentage": 66.73, "elapsed_time": "15:39:06", "remaining_time": "7:48:07"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
98
  {"current_steps": 970, "total_steps": 1479, "loss": 0.4849, "learning_rate": 5e-06, "epoch": 1.9645569620253165, "percentage": 65.58, "elapsed_time": "15:14:21", "remaining_time": "7:59:48"}
99
  {"current_steps": 980, "total_steps": 1479, "loss": 0.485, "learning_rate": 5e-06, "epoch": 1.9848101265822784, "percentage": 66.26, "elapsed_time": "15:23:42", "remaining_time": "7:50:20"}
100
  {"current_steps": 987, "total_steps": 1479, "eval_loss": 0.0688759982585907, "epoch": 1.998987341772152, "percentage": 66.73, "elapsed_time": "15:39:06", "remaining_time": "7:48:07"}
101
+ {"current_steps": 990, "total_steps": 1479, "loss": 0.457, "learning_rate": 5e-06, "epoch": 2.0050632911392405, "percentage": 66.94, "elapsed_time": "15:42:37", "remaining_time": "7:45:35"}
102
+ {"current_steps": 1000, "total_steps": 1479, "loss": 0.3901, "learning_rate": 5e-06, "epoch": 2.0253164556962027, "percentage": 67.61, "elapsed_time": "15:51:56", "remaining_time": "7:35:58"}
103
+ {"current_steps": 1010, "total_steps": 1479, "loss": 0.386, "learning_rate": 5e-06, "epoch": 2.0455696202531644, "percentage": 68.29, "elapsed_time": "16:01:16", "remaining_time": "7:26:22"}
104
+ {"current_steps": 1020, "total_steps": 1479, "loss": 0.3814, "learning_rate": 5e-06, "epoch": 2.0658227848101265, "percentage": 68.97, "elapsed_time": "16:10:35", "remaining_time": "7:16:45"}
105
+ {"current_steps": 1030, "total_steps": 1479, "loss": 0.381, "learning_rate": 5e-06, "epoch": 2.0860759493670886, "percentage": 69.64, "elapsed_time": "16:19:55", "remaining_time": "7:07:10"}
106
+ {"current_steps": 1040, "total_steps": 1479, "loss": 0.379, "learning_rate": 5e-06, "epoch": 2.1063291139240508, "percentage": 70.32, "elapsed_time": "16:29:14", "remaining_time": "6:57:34"}
107
+ {"current_steps": 1050, "total_steps": 1479, "loss": 0.389, "learning_rate": 5e-06, "epoch": 2.1265822784810124, "percentage": 70.99, "elapsed_time": "16:38:34", "remaining_time": "6:47:59"}
108
+ {"current_steps": 1060, "total_steps": 1479, "loss": 0.3849, "learning_rate": 5e-06, "epoch": 2.1468354430379746, "percentage": 71.67, "elapsed_time": "16:47:54", "remaining_time": "6:38:24"}
109
+ {"current_steps": 1070, "total_steps": 1479, "loss": 0.3886, "learning_rate": 5e-06, "epoch": 2.1670886075949367, "percentage": 72.35, "elapsed_time": "16:57:14", "remaining_time": "6:28:50"}
110
+ {"current_steps": 1080, "total_steps": 1479, "loss": 0.3867, "learning_rate": 5e-06, "epoch": 2.187341772151899, "percentage": 73.02, "elapsed_time": "17:06:34", "remaining_time": "6:19:15"}
111
+ {"current_steps": 1090, "total_steps": 1479, "loss": 0.3844, "learning_rate": 5e-06, "epoch": 2.207594936708861, "percentage": 73.7, "elapsed_time": "17:15:55", "remaining_time": "6:09:42"}
112
+ {"current_steps": 1100, "total_steps": 1479, "loss": 0.3934, "learning_rate": 5e-06, "epoch": 2.2278481012658227, "percentage": 74.37, "elapsed_time": "17:25:16", "remaining_time": "6:00:08"}
113
+ {"current_steps": 1110, "total_steps": 1479, "loss": 0.3891, "learning_rate": 5e-06, "epoch": 2.248101265822785, "percentage": 75.05, "elapsed_time": "17:34:36", "remaining_time": "5:50:35"}
114
+ {"current_steps": 1120, "total_steps": 1479, "loss": 0.3917, "learning_rate": 5e-06, "epoch": 2.268354430379747, "percentage": 75.73, "elapsed_time": "17:43:56", "remaining_time": "5:41:01"}
115
+ {"current_steps": 1130, "total_steps": 1479, "loss": 0.3926, "learning_rate": 5e-06, "epoch": 2.2886075949367086, "percentage": 76.4, "elapsed_time": "17:53:15", "remaining_time": "5:31:28"}
116
+ {"current_steps": 1140, "total_steps": 1479, "loss": 0.3891, "learning_rate": 5e-06, "epoch": 2.3088607594936708, "percentage": 77.08, "elapsed_time": "18:02:35", "remaining_time": "5:21:55"}
117
+ {"current_steps": 1150, "total_steps": 1479, "loss": 0.3956, "learning_rate": 5e-06, "epoch": 2.329113924050633, "percentage": 77.76, "elapsed_time": "18:11:55", "remaining_time": "5:12:23"}
118
+ {"current_steps": 1160, "total_steps": 1479, "loss": 0.3962, "learning_rate": 5e-06, "epoch": 2.349367088607595, "percentage": 78.43, "elapsed_time": "18:21:14", "remaining_time": "5:02:50"}
119
+ {"current_steps": 1170, "total_steps": 1479, "loss": 0.3968, "learning_rate": 5e-06, "epoch": 2.369620253164557, "percentage": 79.11, "elapsed_time": "18:30:34", "remaining_time": "4:53:18"}
120
+ {"current_steps": 1180, "total_steps": 1479, "loss": 0.3956, "learning_rate": 5e-06, "epoch": 2.389873417721519, "percentage": 79.78, "elapsed_time": "18:39:54", "remaining_time": "4:43:46"}
121
+ {"current_steps": 1190, "total_steps": 1479, "loss": 0.396, "learning_rate": 5e-06, "epoch": 2.410126582278481, "percentage": 80.46, "elapsed_time": "18:49:15", "remaining_time": "4:34:14"}
122
+ {"current_steps": 1200, "total_steps": 1479, "loss": 0.3945, "learning_rate": 5e-06, "epoch": 2.430379746835443, "percentage": 81.14, "elapsed_time": "18:58:34", "remaining_time": "4:24:43"}
123
+ {"current_steps": 1210, "total_steps": 1479, "loss": 0.394, "learning_rate": 5e-06, "epoch": 2.4506329113924052, "percentage": 81.81, "elapsed_time": "19:07:56", "remaining_time": "4:15:12"}
124
+ {"current_steps": 1220, "total_steps": 1479, "loss": 0.3978, "learning_rate": 5e-06, "epoch": 2.470886075949367, "percentage": 82.49, "elapsed_time": "19:17:17", "remaining_time": "4:05:41"}
125
+ {"current_steps": 1230, "total_steps": 1479, "loss": 0.3975, "learning_rate": 5e-06, "epoch": 2.491139240506329, "percentage": 83.16, "elapsed_time": "19:26:37", "remaining_time": "3:56:10"}
126
+ {"current_steps": 1240, "total_steps": 1479, "loss": 0.4019, "learning_rate": 5e-06, "epoch": 2.511392405063291, "percentage": 83.84, "elapsed_time": "19:35:58", "remaining_time": "3:46:39"}
127
+ {"current_steps": 1250, "total_steps": 1479, "loss": 0.3956, "learning_rate": 5e-06, "epoch": 2.5316455696202533, "percentage": 84.52, "elapsed_time": "19:45:17", "remaining_time": "3:37:08"}
128
+ {"current_steps": 1260, "total_steps": 1479, "loss": 0.3915, "learning_rate": 5e-06, "epoch": 2.5518987341772155, "percentage": 85.19, "elapsed_time": "19:54:36", "remaining_time": "3:27:38"}
129
+ {"current_steps": 1270, "total_steps": 1479, "loss": 0.3972, "learning_rate": 5e-06, "epoch": 2.572151898734177, "percentage": 85.87, "elapsed_time": "20:03:57", "remaining_time": "3:18:07"}
130
+ {"current_steps": 1280, "total_steps": 1479, "loss": 0.3989, "learning_rate": 5e-06, "epoch": 2.5924050632911393, "percentage": 86.54, "elapsed_time": "20:13:18", "remaining_time": "3:08:37"}
131
+ {"current_steps": 1290, "total_steps": 1479, "loss": 0.4039, "learning_rate": 5e-06, "epoch": 2.6126582278481014, "percentage": 87.22, "elapsed_time": "20:22:39", "remaining_time": "2:59:07"}
132
+ {"current_steps": 1300, "total_steps": 1479, "loss": 0.3986, "learning_rate": 5e-06, "epoch": 2.632911392405063, "percentage": 87.9, "elapsed_time": "20:31:59", "remaining_time": "2:49:38"}
133
+ {"current_steps": 1310, "total_steps": 1479, "loss": 0.3982, "learning_rate": 5e-06, "epoch": 2.6531645569620252, "percentage": 88.57, "elapsed_time": "20:41:18", "remaining_time": "2:40:08"}
134
+ {"current_steps": 1320, "total_steps": 1479, "loss": 0.4008, "learning_rate": 5e-06, "epoch": 2.6734177215189874, "percentage": 89.25, "elapsed_time": "20:50:38", "remaining_time": "2:30:38"}
135
+ {"current_steps": 1330, "total_steps": 1479, "loss": 0.4033, "learning_rate": 5e-06, "epoch": 2.6936708860759495, "percentage": 89.93, "elapsed_time": "20:59:58", "remaining_time": "2:21:09"}
136
+ {"current_steps": 1340, "total_steps": 1479, "loss": 0.4017, "learning_rate": 5e-06, "epoch": 2.7139240506329116, "percentage": 90.6, "elapsed_time": "21:09:18", "remaining_time": "2:11:40"}
137
+ {"current_steps": 1350, "total_steps": 1479, "loss": 0.402, "learning_rate": 5e-06, "epoch": 2.7341772151898733, "percentage": 91.28, "elapsed_time": "21:18:38", "remaining_time": "2:02:10"}
138
+ {"current_steps": 1360, "total_steps": 1479, "loss": 0.3975, "learning_rate": 5e-06, "epoch": 2.7544303797468355, "percentage": 91.95, "elapsed_time": "21:27:58", "remaining_time": "1:52:41"}
139
+ {"current_steps": 1370, "total_steps": 1479, "loss": 0.4035, "learning_rate": 5e-06, "epoch": 2.7746835443037976, "percentage": 92.63, "elapsed_time": "21:37:18", "remaining_time": "1:43:13"}
140
+ {"current_steps": 1380, "total_steps": 1479, "loss": 0.4008, "learning_rate": 5e-06, "epoch": 2.7949367088607593, "percentage": 93.31, "elapsed_time": "21:46:38", "remaining_time": "1:33:44"}
141
+ {"current_steps": 1390, "total_steps": 1479, "loss": 0.4034, "learning_rate": 5e-06, "epoch": 2.8151898734177214, "percentage": 93.98, "elapsed_time": "21:55:57", "remaining_time": "1:24:15"}
142
+ {"current_steps": 1400, "total_steps": 1479, "loss": 0.3973, "learning_rate": 5e-06, "epoch": 2.8354430379746836, "percentage": 94.66, "elapsed_time": "22:05:17", "remaining_time": "1:14:47"}
143
+ {"current_steps": 1410, "total_steps": 1479, "loss": 0.4057, "learning_rate": 5e-06, "epoch": 2.8556962025316457, "percentage": 95.33, "elapsed_time": "22:14:36", "remaining_time": "1:05:18"}
144
+ {"current_steps": 1420, "total_steps": 1479, "loss": 0.4016, "learning_rate": 5e-06, "epoch": 2.875949367088608, "percentage": 96.01, "elapsed_time": "22:23:56", "remaining_time": "0:55:50"}
145
+ {"current_steps": 1430, "total_steps": 1479, "loss": 0.4028, "learning_rate": 5e-06, "epoch": 2.8962025316455695, "percentage": 96.69, "elapsed_time": "22:33:16", "remaining_time": "0:46:22"}
146
+ {"current_steps": 1440, "total_steps": 1479, "loss": 0.4044, "learning_rate": 5e-06, "epoch": 2.9164556962025316, "percentage": 97.36, "elapsed_time": "22:42:37", "remaining_time": "0:36:54"}
147
+ {"current_steps": 1450, "total_steps": 1479, "loss": 0.4133, "learning_rate": 5e-06, "epoch": 2.9367088607594938, "percentage": 98.04, "elapsed_time": "22:51:56", "remaining_time": "0:27:26"}
148
+ {"current_steps": 1460, "total_steps": 1479, "loss": 0.4017, "learning_rate": 5e-06, "epoch": 2.9569620253164555, "percentage": 98.72, "elapsed_time": "23:01:15", "remaining_time": "0:17:58"}
149
+ {"current_steps": 1470, "total_steps": 1479, "loss": 0.4059, "learning_rate": 5e-06, "epoch": 2.9772151898734176, "percentage": 99.39, "elapsed_time": "23:10:34", "remaining_time": "0:08:30"}