Hugging Face's logo

mlfoundations-dev
/
hp_ablations_mistral_epoch3

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
ffe28f2
•
1 Parent(s): 17c719b

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 sha256:5dcd6652b36325640355d9dc807db656bbf5747d4b7fe72934eb3f68b7213916
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4957d560df9b2d44fa01c328a9d3e63f2d2b0c7d8a50687c24fd42e234a1c17
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37028ddcc0eef174a6dbc0baaaf5fa1b113016a67b72b8b21872fc42074341d4
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd017f7648addbe617773bfc1e38cbf72369c5eaa8e9bbfae6f03ce632f1f098
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:cfb4b03c6e0fc0bec16e4f5154cf10e19c40c14f2211207b8a7c3ebf726271cc
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00583b2ceedc5aae74de8c0c7e55ee28a9be672ea3fc102f53249fcc62fa06d7
3
  size 4540516344
trainer_log.jsonl CHANGED
@@ -99,3 +99,51 @@
99
  {"current_steps": 980, "total_steps": 1479, "loss": 0.4805, "lr": 5e-06, "epoch": 1.9853164556962026, "percentage": 66.26, "elapsed_time": "7:46:11", "remaining_time": "3:57:22"}
100
  {"current_steps": 987, "total_steps": 1479, "eval_loss": 0.13782347738742828, "epoch": 1.999493670886076, "percentage": 66.73, "elapsed_time": "7:53:41", "remaining_time": "3:56:07"}
101
  {"current_steps": 990, "total_steps": 1479, "loss": 0.4496, "lr": 5e-06, "epoch": 2.0060759493670886, "percentage": 66.94, "elapsed_time": "7:55:59", "remaining_time": "3:55:06"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
99
  {"current_steps": 980, "total_steps": 1479, "loss": 0.4805, "lr": 5e-06, "epoch": 1.9853164556962026, "percentage": 66.26, "elapsed_time": "7:46:11", "remaining_time": "3:57:22"}
100
  {"current_steps": 987, "total_steps": 1479, "eval_loss": 0.13782347738742828, "epoch": 1.999493670886076, "percentage": 66.73, "elapsed_time": "7:53:41", "remaining_time": "3:56:07"}
101
  {"current_steps": 990, "total_steps": 1479, "loss": 0.4496, "lr": 5e-06, "epoch": 2.0060759493670886, "percentage": 66.94, "elapsed_time": "7:55:59", "remaining_time": "3:55:06"}
102
+ {"current_steps": 1000, "total_steps": 1479, "loss": 0.3864, "lr": 5e-06, "epoch": 2.0263291139240507, "percentage": 67.61, "elapsed_time": "8:00:41", "remaining_time": "3:50:15"}
103
+ {"current_steps": 1010, "total_steps": 1479, "loss": 0.3795, "lr": 5e-06, "epoch": 2.046582278481013, "percentage": 68.29, "elapsed_time": "8:05:24", "remaining_time": "3:45:24"}
104
+ {"current_steps": 1020, "total_steps": 1479, "loss": 0.377, "lr": 5e-06, "epoch": 2.0668354430379745, "percentage": 68.97, "elapsed_time": "8:10:07", "remaining_time": "3:40:33"}
105
+ {"current_steps": 1030, "total_steps": 1479, "loss": 0.3767, "lr": 5e-06, "epoch": 2.0870886075949366, "percentage": 69.64, "elapsed_time": "8:14:50", "remaining_time": "3:35:42"}
106
+ {"current_steps": 1040, "total_steps": 1479, "loss": 0.3739, "lr": 5e-06, "epoch": 2.1073417721518988, "percentage": 70.32, "elapsed_time": "8:19:33", "remaining_time": "3:30:52"}
107
+ {"current_steps": 1050, "total_steps": 1479, "loss": 0.3846, "lr": 5e-06, "epoch": 2.127594936708861, "percentage": 70.99, "elapsed_time": "8:24:16", "remaining_time": "3:26:01"}
108
+ {"current_steps": 1060, "total_steps": 1479, "loss": 0.3804, "lr": 5e-06, "epoch": 2.1478481012658226, "percentage": 71.67, "elapsed_time": "8:28:59", "remaining_time": "3:21:11"}
109
+ {"current_steps": 1070, "total_steps": 1479, "loss": 0.382, "lr": 5e-06, "epoch": 2.1681012658227847, "percentage": 72.35, "elapsed_time": "8:33:41", "remaining_time": "3:16:21"}
110
+ {"current_steps": 1080, "total_steps": 1479, "loss": 0.3815, "lr": 5e-06, "epoch": 2.188354430379747, "percentage": 73.02, "elapsed_time": "8:38:24", "remaining_time": "3:11:31"}
111
+ {"current_steps": 1090, "total_steps": 1479, "loss": 0.3787, "lr": 5e-06, "epoch": 2.208607594936709, "percentage": 73.7, "elapsed_time": "8:43:07", "remaining_time": "3:06:41"}
112
+ {"current_steps": 1100, "total_steps": 1479, "loss": 0.3876, "lr": 5e-06, "epoch": 2.2288607594936707, "percentage": 74.37, "elapsed_time": "8:47:50", "remaining_time": "3:01:51"}
113
+ {"current_steps": 1110, "total_steps": 1479, "loss": 0.3856, "lr": 5e-06, "epoch": 2.249113924050633, "percentage": 75.05, "elapsed_time": "8:52:32", "remaining_time": "2:57:02"}
114
+ {"current_steps": 1120, "total_steps": 1479, "loss": 0.3843, "lr": 5e-06, "epoch": 2.269367088607595, "percentage": 75.73, "elapsed_time": "8:57:15", "remaining_time": "2:52:12"}
115
+ {"current_steps": 1130, "total_steps": 1479, "loss": 0.3873, "lr": 5e-06, "epoch": 2.289620253164557, "percentage": 76.4, "elapsed_time": "9:01:58", "remaining_time": "2:47:23"}
116
+ {"current_steps": 1140, "total_steps": 1479, "loss": 0.381, "lr": 5e-06, "epoch": 2.309873417721519, "percentage": 77.08, "elapsed_time": "9:06:40", "remaining_time": "2:42:33"}
117
+ {"current_steps": 1150, "total_steps": 1479, "loss": 0.3869, "lr": 5e-06, "epoch": 2.330126582278481, "percentage": 77.76, "elapsed_time": "9:11:23", "remaining_time": "2:37:44"}
118
+ {"current_steps": 1160, "total_steps": 1479, "loss": 0.3871, "lr": 5e-06, "epoch": 2.350379746835443, "percentage": 78.43, "elapsed_time": "9:16:05", "remaining_time": "2:32:55"}
119
+ {"current_steps": 1170, "total_steps": 1479, "loss": 0.3888, "lr": 5e-06, "epoch": 2.370632911392405, "percentage": 79.11, "elapsed_time": "9:20:48", "remaining_time": "2:28:06"}
120
+ {"current_steps": 1180, "total_steps": 1479, "loss": 0.3901, "lr": 5e-06, "epoch": 2.390886075949367, "percentage": 79.78, "elapsed_time": "9:25:30", "remaining_time": "2:23:17"}
121
+ {"current_steps": 1190, "total_steps": 1479, "loss": 0.3874, "lr": 5e-06, "epoch": 2.411139240506329, "percentage": 80.46, "elapsed_time": "9:30:13", "remaining_time": "2:18:28"}
122
+ {"current_steps": 1200, "total_steps": 1479, "loss": 0.3885, "lr": 5e-06, "epoch": 2.431392405063291, "percentage": 81.14, "elapsed_time": "9:34:56", "remaining_time": "2:13:40"}
123
+ {"current_steps": 1210, "total_steps": 1479, "loss": 0.3866, "lr": 5e-06, "epoch": 2.4516455696202533, "percentage": 81.81, "elapsed_time": "9:39:38", "remaining_time": "2:08:51"}
124
+ {"current_steps": 1220, "total_steps": 1479, "loss": 0.3892, "lr": 5e-06, "epoch": 2.4718987341772154, "percentage": 82.49, "elapsed_time": "9:44:21", "remaining_time": "2:04:03"}
125
+ {"current_steps": 1230, "total_steps": 1479, "loss": 0.3914, "lr": 5e-06, "epoch": 2.492151898734177, "percentage": 83.16, "elapsed_time": "9:49:04", "remaining_time": "1:59:15"}
126
+ {"current_steps": 1240, "total_steps": 1479, "loss": 0.3895, "lr": 5e-06, "epoch": 2.512405063291139, "percentage": 83.84, "elapsed_time": "9:53:46", "remaining_time": "1:54:26"}
127
+ {"current_steps": 1250, "total_steps": 1479, "loss": 0.3876, "lr": 5e-06, "epoch": 2.5326582278481014, "percentage": 84.52, "elapsed_time": "9:58:29", "remaining_time": "1:49:38"}
128
+ {"current_steps": 1260, "total_steps": 1479, "loss": 0.3808, "lr": 5e-06, "epoch": 2.552911392405063, "percentage": 85.19, "elapsed_time": "10:03:12", "remaining_time": "1:44:50"}
129
+ {"current_steps": 1270, "total_steps": 1479, "loss": 0.3891, "lr": 5e-06, "epoch": 2.573164556962025, "percentage": 85.87, "elapsed_time": "10:07:55", "remaining_time": "1:40:02"}
130
+ {"current_steps": 1280, "total_steps": 1479, "loss": 0.3921, "lr": 5e-06, "epoch": 2.5934177215189873, "percentage": 86.54, "elapsed_time": "10:12:37", "remaining_time": "1:35:14"}
131
+ {"current_steps": 1290, "total_steps": 1479, "loss": 0.3958, "lr": 5e-06, "epoch": 2.6136708860759494, "percentage": 87.22, "elapsed_time": "10:17:20", "remaining_time": "1:30:26"}
132
+ {"current_steps": 1300, "total_steps": 1479, "loss": 0.3915, "lr": 5e-06, "epoch": 2.6339240506329116, "percentage": 87.9, "elapsed_time": "10:22:03", "remaining_time": "1:25:39"}
133
+ {"current_steps": 1310, "total_steps": 1479, "loss": 0.3917, "lr": 5e-06, "epoch": 2.6541772151898733, "percentage": 88.57, "elapsed_time": "10:26:46", "remaining_time": "1:20:51"}
134
+ {"current_steps": 1320, "total_steps": 1479, "loss": 0.3945, "lr": 5e-06, "epoch": 2.6744303797468354, "percentage": 89.25, "elapsed_time": "10:31:29", "remaining_time": "1:16:03"}
135
+ {"current_steps": 1330, "total_steps": 1479, "loss": 0.3953, "lr": 5e-06, "epoch": 2.6946835443037975, "percentage": 89.93, "elapsed_time": "10:36:11", "remaining_time": "1:11:16"}
136
+ {"current_steps": 1340, "total_steps": 1479, "loss": 0.3974, "lr": 5e-06, "epoch": 2.714936708860759, "percentage": 90.6, "elapsed_time": "10:40:53", "remaining_time": "1:06:28"}
137
+ {"current_steps": 1350, "total_steps": 1479, "loss": 0.3946, "lr": 5e-06, "epoch": 2.7351898734177214, "percentage": 91.28, "elapsed_time": "10:45:36", "remaining_time": "1:01:41"}
138
+ {"current_steps": 1360, "total_steps": 1479, "loss": 0.3904, "lr": 5e-06, "epoch": 2.7554430379746835, "percentage": 91.95, "elapsed_time": "10:50:19", "remaining_time": "0:56:54"}
139
+ {"current_steps": 1370, "total_steps": 1479, "loss": 0.3973, "lr": 5e-06, "epoch": 2.7756962025316456, "percentage": 92.63, "elapsed_time": "10:55:01", "remaining_time": "0:52:06"}
140
+ {"current_steps": 1380, "total_steps": 1479, "loss": 0.395, "lr": 5e-06, "epoch": 2.7959493670886078, "percentage": 93.31, "elapsed_time": "10:59:44", "remaining_time": "0:47:19"}
141
+ {"current_steps": 1390, "total_steps": 1479, "loss": 0.3975, "lr": 5e-06, "epoch": 2.81620253164557, "percentage": 93.98, "elapsed_time": "11:04:26", "remaining_time": "0:42:32"}
142
+ {"current_steps": 1400, "total_steps": 1479, "loss": 0.3919, "lr": 5e-06, "epoch": 2.8364556962025316, "percentage": 94.66, "elapsed_time": "11:09:09", "remaining_time": "0:37:45"}
143
+ {"current_steps": 1410, "total_steps": 1479, "loss": 0.3977, "lr": 5e-06, "epoch": 2.8567088607594937, "percentage": 95.33, "elapsed_time": "11:13:52", "remaining_time": "0:32:58"}
144
+ {"current_steps": 1420, "total_steps": 1479, "loss": 0.3945, "lr": 5e-06, "epoch": 2.876962025316456, "percentage": 96.01, "elapsed_time": "11:18:34", "remaining_time": "0:28:11"}
145
+ {"current_steps": 1430, "total_steps": 1479, "loss": 0.3944, "lr": 5e-06, "epoch": 2.8972151898734175, "percentage": 96.69, "elapsed_time": "11:23:17", "remaining_time": "0:23:24"}
146
+ {"current_steps": 1440, "total_steps": 1479, "loss": 0.3974, "lr": 5e-06, "epoch": 2.9174683544303797, "percentage": 97.36, "elapsed_time": "11:28:00", "remaining_time": "0:18:38"}
147
+ {"current_steps": 1450, "total_steps": 1479, "loss": 0.4065, "lr": 5e-06, "epoch": 2.937721518987342, "percentage": 98.04, "elapsed_time": "11:32:43", "remaining_time": "0:13:51"}
148
+ {"current_steps": 1460, "total_steps": 1479, "loss": 0.3949, "lr": 5e-06, "epoch": 2.957974683544304, "percentage": 98.72, "elapsed_time": "11:37:26", "remaining_time": "0:09:04"}
149
+ {"current_steps": 1470, "total_steps": 1479, "loss": 0.3987, "lr": 5e-06, "epoch": 2.978227848101266, "percentage": 99.39, "elapsed_time": "11:42:08", "remaining_time": "0:04:17"}