Hugging Face's logo

mlfoundations-dev
/
hp_ablations_mistral_scheduler_cosine_warmup0.10

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
371ae57
·
verified ·
1 Parent(s): d55aea8

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:ad88fb5f2a6e5665c034925cb02f3948e5af75be570529ab4ac3597877e1cf3d
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a0f4eeaae6083e0a48d955a73ecce8d78c09147c1a49906e334dbc83124a430
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:ce283e3f4acaee738257afe76e7b52a2960ecace2b0ef69d7eba2a1a90ef97b1
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a77ee2ba1bfb2c5b0d9a2cbfa498fa990d47e95c230533253723c65d22f4e491
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69b6dd72477308107fd6e95e3f9f8166063810de3df8b4d9e5c15af7ead8ccda
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d34de4eaf0fd26954b3b72576072c782f972f71b5bf24ae5a1658f139c44054
3
  size 4540516344
trainer_log.jsonl CHANGED
@@ -98,3 +98,52 @@
98
  {"current_steps": 970, "total_steps": 1479, "loss": 0.482, "learning_rate": 1.5973813550487183e-06, "epoch": 1.9645569620253165, "percentage": 65.58, "elapsed_time": "15:00:08", "remaining_time": "7:52:20"}
99
  {"current_steps": 980, "total_steps": 1479, "loss": 0.4812, "learning_rate": 1.542610005733623e-06, "epoch": 1.9848101265822784, "percentage": 66.26, "elapsed_time": "15:09:19", "remaining_time": "7:43:00"}
100
  {"current_steps": 987, "total_steps": 1479, "eval_loss": 0.0676623284816742, "epoch": 1.998987341772152, "percentage": 66.73, "elapsed_time": "15:24:26", "remaining_time": "7:40:48"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
98
  {"current_steps": 970, "total_steps": 1479, "loss": 0.482, "learning_rate": 1.5973813550487183e-06, "epoch": 1.9645569620253165, "percentage": 65.58, "elapsed_time": "15:00:08", "remaining_time": "7:52:20"}
99
  {"current_steps": 980, "total_steps": 1479, "loss": 0.4812, "learning_rate": 1.542610005733623e-06, "epoch": 1.9848101265822784, "percentage": 66.26, "elapsed_time": "15:09:19", "remaining_time": "7:43:00"}
100
  {"current_steps": 987, "total_steps": 1479, "eval_loss": 0.0676623284816742, "epoch": 1.998987341772152, "percentage": 66.73, "elapsed_time": "15:24:26", "remaining_time": "7:40:48"}
101
+ {"current_steps": 990, "total_steps": 1479, "loss": 0.4585, "learning_rate": 1.4883720064880946e-06, "epoch": 2.0050632911392405, "percentage": 66.94, "elapsed_time": "15:27:54", "remaining_time": "7:38:19"}
102
+ {"current_steps": 1000, "total_steps": 1479, "loss": 0.4105, "learning_rate": 1.4346975726275655e-06, "epoch": 2.0253164556962027, "percentage": 67.61, "elapsed_time": "15:37:05", "remaining_time": "7:28:52"}
103
+ {"current_steps": 1010, "total_steps": 1479, "loss": 0.4094, "learning_rate": 1.3816166055121985e-06, "epoch": 2.0455696202531644, "percentage": 68.29, "elapsed_time": "15:46:16", "remaining_time": "7:19:24"}
104
+ {"current_steps": 1020, "total_steps": 1479, "loss": 0.4053, "learning_rate": 1.3291586758892061e-06, "epoch": 2.0658227848101265, "percentage": 68.97, "elapsed_time": "15:55:28", "remaining_time": "7:09:57"}
105
+ {"current_steps": 1030, "total_steps": 1479, "loss": 0.405, "learning_rate": 1.2773530074193526e-06, "epoch": 2.0860759493670886, "percentage": 69.64, "elapsed_time": "16:04:39", "remaining_time": "7:00:31"}
106
+ {"current_steps": 1040, "total_steps": 1479, "loss": 0.4016, "learning_rate": 1.2262284603968226e-06, "epoch": 2.1063291139240508, "percentage": 70.32, "elapsed_time": "16:13:51", "remaining_time": "6:51:04"}
107
+ {"current_steps": 1050, "total_steps": 1479, "loss": 0.4103, "learning_rate": 1.1758135156715043e-06, "epoch": 2.1265822784810124, "percentage": 70.99, "elapsed_time": "16:23:02", "remaining_time": "6:41:38"}
108
+ {"current_steps": 1060, "total_steps": 1479, "loss": 0.4043, "learning_rate": 1.126136258782662e-06, "epoch": 2.1468354430379746, "percentage": 71.67, "elapsed_time": "16:32:14", "remaining_time": "6:32:12"}
109
+ {"current_steps": 1070, "total_steps": 1479, "loss": 0.4068, "learning_rate": 1.0772243643128342e-06, "epoch": 2.1670886075949367, "percentage": 72.35, "elapsed_time": "16:41:25", "remaining_time": "6:22:47"}
110
+ {"current_steps": 1080, "total_steps": 1479, "loss": 0.4051, "learning_rate": 1.0291050804706668e-06, "epoch": 2.187341772151899, "percentage": 73.02, "elapsed_time": "16:50:36", "remaining_time": "6:13:21"}
111
+ {"current_steps": 1090, "total_steps": 1479, "loss": 0.4023, "learning_rate": 9.818052139112707e-07, "epoch": 2.207594936708861, "percentage": 73.7, "elapsed_time": "16:59:47", "remaining_time": "6:03:56"}
112
+ {"current_steps": 1100, "total_steps": 1479, "loss": 0.4108, "learning_rate": 9.353511148025731e-07, "epoch": 2.2278481012658227, "percentage": 74.37, "elapsed_time": "17:08:59", "remaining_time": "5:54:31"}
113
+ {"current_steps": 1110, "total_steps": 1479, "loss": 0.4061, "learning_rate": 8.897686621459631e-07, "epoch": 2.248101265822785, "percentage": 75.05, "elapsed_time": "17:18:10", "remaining_time": "5:45:07"}
114
+ {"current_steps": 1120, "total_steps": 1479, "loss": 0.4071, "learning_rate": 8.450832493594214e-07, "epoch": 2.268354430379747, "percentage": 75.73, "elapsed_time": "17:27:22", "remaining_time": "5:35:43"}
115
+ {"current_steps": 1130, "total_steps": 1479, "loss": 0.4083, "learning_rate": 8.013197701311637e-07, "epoch": 2.2886075949367086, "percentage": 76.4, "elapsed_time": "17:36:32", "remaining_time": "5:26:18"}
116
+ {"current_steps": 1140, "total_steps": 1479, "loss": 0.4033, "learning_rate": 7.585026045516777e-07, "epoch": 2.3088607594936708, "percentage": 77.08, "elapsed_time": "17:45:44", "remaining_time": "5:16:54"}
117
+ {"current_steps": 1150, "total_steps": 1479, "loss": 0.4097, "learning_rate": 7.166556055318727e-07, "epoch": 2.329113924050633, "percentage": 77.76, "elapsed_time": "17:54:54", "remaining_time": "5:07:31"}
118
+ {"current_steps": 1160, "total_steps": 1479, "loss": 0.4086, "learning_rate": 6.75802085514925e-07, "epoch": 2.349367088607595, "percentage": 78.43, "elapsed_time": "18:04:05", "remaining_time": "4:58:07"}
119
+ {"current_steps": 1170, "total_steps": 1479, "loss": 0.4078, "learning_rate": 6.359648034892033e-07, "epoch": 2.369620253164557, "percentage": 79.11, "elapsed_time": "18:13:16", "remaining_time": "4:48:44"}
120
+ {"current_steps": 1180, "total_steps": 1479, "loss": 0.4075, "learning_rate": 5.971659523095167e-07, "epoch": 2.389873417721519, "percentage": 79.78, "elapsed_time": "18:22:27", "remaining_time": "4:39:21"}
121
+ {"current_steps": 1190, "total_steps": 1479, "loss": 0.407, "learning_rate": 5.594271463337552e-07, "epoch": 2.410126582278481, "percentage": 80.46, "elapsed_time": "18:31:38", "remaining_time": "4:29:58"}
122
+ {"current_steps": 1200, "total_steps": 1479, "loss": 0.4051, "learning_rate": 5.227694093817967e-07, "epoch": 2.430379746835443, "percentage": 81.14, "elapsed_time": "18:40:48", "remaining_time": "4:20:35"}
123
+ {"current_steps": 1210, "total_steps": 1479, "loss": 0.4038, "learning_rate": 4.872131630234003e-07, "epoch": 2.4506329113924052, "percentage": 81.81, "elapsed_time": "18:49:58", "remaining_time": "4:11:12"}
124
+ {"current_steps": 1220, "total_steps": 1479, "loss": 0.407, "learning_rate": 4.5277821520159913e-07, "epoch": 2.470886075949367, "percentage": 82.49, "elapsed_time": "18:59:09", "remaining_time": "4:01:50"}
125
+ {"current_steps": 1230, "total_steps": 1479, "loss": 0.4054, "learning_rate": 4.1948374919794757e-07, "epoch": 2.491139240506329, "percentage": 83.16, "elapsed_time": "19:08:20", "remaining_time": "3:52:28"}
126
+ {"current_steps": 1240, "total_steps": 1479, "loss": 0.4098, "learning_rate": 3.873483129457495e-07, "epoch": 2.511392405063291, "percentage": 83.84, "elapsed_time": "19:17:31", "remaining_time": "3:43:06"}
127
+ {"current_steps": 1250, "total_steps": 1479, "loss": 0.4027, "learning_rate": 3.5638980869723477e-07, "epoch": 2.5316455696202533, "percentage": 84.52, "elapsed_time": "19:26:42", "remaining_time": "3:33:44"}
128
+ {"current_steps": 1260, "total_steps": 1479, "loss": 0.3973, "learning_rate": 3.266254830504395e-07, "epoch": 2.5518987341772155, "percentage": 85.19, "elapsed_time": "19:35:53", "remaining_time": "3:24:22"}
129
+ {"current_steps": 1270, "total_steps": 1479, "loss": 0.4047, "learning_rate": 2.980719173413396e-07, "epoch": 2.572151898734177, "percentage": 85.87, "elapsed_time": "19:45:04", "remaining_time": "3:15:01"}
130
+ {"current_steps": 1280, "total_steps": 1479, "loss": 0.4059, "learning_rate": 2.707450184065927e-07, "epoch": 2.5924050632911393, "percentage": 86.54, "elapsed_time": "19:54:15", "remaining_time": "3:05:40"}
131
+ {"current_steps": 1290, "total_steps": 1479, "loss": 0.4115, "learning_rate": 2.4466000972204e-07, "epoch": 2.6126582278481014, "percentage": 87.22, "elapsed_time": "20:03:26", "remaining_time": "2:56:19"}
132
+ {"current_steps": 1300, "total_steps": 1479, "loss": 0.4049, "learning_rate": 2.1983142292189563e-07, "epoch": 2.632911392405063, "percentage": 87.9, "elapsed_time": "20:12:38", "remaining_time": "2:46:58"}
133
+ {"current_steps": 1310, "total_steps": 1479, "loss": 0.4036, "learning_rate": 1.962730897033524e-07, "epoch": 2.6531645569620252, "percentage": 88.57, "elapsed_time": "20:21:49", "remaining_time": "2:37:37"}
134
+ {"current_steps": 1320, "total_steps": 1479, "loss": 0.4053, "learning_rate": 1.7399813412111833e-07, "epoch": 2.6734177215189874, "percentage": 89.25, "elapsed_time": "20:31:00", "remaining_time": "2:28:16"}
135
+ {"current_steps": 1330, "total_steps": 1479, "loss": 0.4079, "learning_rate": 1.53018965276166e-07, "epoch": 2.6936708860759495, "percentage": 89.93, "elapsed_time": "20:40:10", "remaining_time": "2:18:56"}
136
+ {"current_steps": 1340, "total_steps": 1479, "loss": 0.4058, "learning_rate": 1.3334727040277855e-07, "epoch": 2.7139240506329116, "percentage": 90.6, "elapsed_time": "20:49:22", "remaining_time": "2:09:35"}
137
+ {"current_steps": 1350, "total_steps": 1479, "loss": 0.4036, "learning_rate": 1.1499400835773472e-07, "epoch": 2.7341772151898733, "percentage": 91.28, "elapsed_time": "20:58:33", "remaining_time": "2:00:15"}
138
+ {"current_steps": 1360, "total_steps": 1479, "loss": 0.3997, "learning_rate": 9.796940351526841e-08, "epoch": 2.7544303797468355, "percentage": 91.95, "elapsed_time": "21:07:45", "remaining_time": "1:50:55"}
139
+ {"current_steps": 1370, "total_steps": 1479, "loss": 0.4052, "learning_rate": 8.228294007119414e-08, "epoch": 2.7746835443037976, "percentage": 92.63, "elapsed_time": "21:16:56", "remaining_time": "1:41:35"}
140
+ {"current_steps": 1380, "total_steps": 1479, "loss": 0.4027, "learning_rate": 6.79433567593818e-08, "epoch": 2.7949367088607593, "percentage": 93.31, "elapsed_time": "21:26:08", "remaining_time": "1:32:15"}
141
+ {"current_steps": 1390, "total_steps": 1479, "loss": 0.4056, "learning_rate": 5.4958641983514913e-08, "epoch": 2.8151898734177214, "percentage": 93.98, "elapsed_time": "21:35:18", "remaining_time": "1:22:56"}
142
+ {"current_steps": 1400, "total_steps": 1479, "loss": 0.3981, "learning_rate": 4.333602936685055e-08, "epoch": 2.8354430379746836, "percentage": 94.66, "elapsed_time": "21:44:30", "remaining_time": "1:13:36"}
143
+ {"current_steps": 1410, "total_steps": 1479, "loss": 0.4076, "learning_rate": 3.308199372245913e-08, "epoch": 2.8556962025316457, "percentage": 95.33, "elapsed_time": "21:53:41", "remaining_time": "1:04:17"}
144
+ {"current_steps": 1420, "total_steps": 1479, "loss": 0.402, "learning_rate": 2.4202247446183935e-08, "epoch": 2.875949367088608, "percentage": 96.01, "elapsed_time": "22:02:52", "remaining_time": "0:54:57"}
145
+ {"current_steps": 1430, "total_steps": 1479, "loss": 0.4026, "learning_rate": 1.6701737334338663e-08, "epoch": 2.8962025316455695, "percentage": 96.69, "elapsed_time": "22:12:03", "remaining_time": "0:45:38"}
146
+ {"current_steps": 1440, "total_steps": 1479, "loss": 0.4048, "learning_rate": 1.0584641827907638e-08, "epoch": 2.9164556962025316, "percentage": 97.36, "elapsed_time": "22:21:15", "remaining_time": "0:36:19"}
147
+ {"current_steps": 1450, "total_steps": 1479, "loss": 0.4129, "learning_rate": 5.8543686847881145e-09, "epoch": 2.9367088607594938, "percentage": 98.04, "elapsed_time": "22:30:26", "remaining_time": "0:27:00"}
148
+ {"current_steps": 1460, "total_steps": 1479, "loss": 0.4011, "learning_rate": 2.513553081371356e-09, "epoch": 2.9569620253164555, "percentage": 98.72, "elapsed_time": "22:39:37", "remaining_time": "0:17:41"}
149
+ {"current_steps": 1470, "total_steps": 1479, "loss": 0.4047, "learning_rate": 5.640561445177661e-10, "epoch": 2.9772151898734176, "percentage": 99.39, "elapsed_time": "22:48:48", "remaining_time": "0:08:22"}