Hugging Face's logo

mlfoundations-dev
/
hp_ablations_mistral_adambeta2_0.95

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
5e7ddc2
·
verified ·
1 Parent(s): 9f4ab16

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:a0c535c946ab6151d92b1c030fd14272cd8b2a63e71d3ec806db37ebe41d191d
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52d8342edee5e6139618e7cc4ec7204a8e07d0043c1596e1f6b549b025dd1b03
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:49ab3d486d5f20dc5ed65c099755c26cadc2e93ab010b2337467672d25c6d3c0
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:098ff59c10d33820a8c0ffa3aaf3ba991c985e2a7207dc5c56cd7a7b285c6a06
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:fa7e35135cf7a657256e5c580fcdcfdf7ebc3876e17e6e44649ca27aba028a98
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94558abfefac5e9f1a21d3830f91be661b23eeed4dc6dcff886e6f0e4744b838
3
  size 4540516344
trainer_log.jsonl CHANGED
@@ -98,3 +98,52 @@
98
  {"current_steps": 970, "total_steps": 1479, "loss": 0.4829, "learning_rate": 5e-06, "epoch": 1.9645569620253165, "percentage": 65.58, "elapsed_time": "15:24:11", "remaining_time": "8:04:57"}
99
  {"current_steps": 980, "total_steps": 1479, "loss": 0.4834, "learning_rate": 5e-06, "epoch": 1.9848101265822784, "percentage": 66.26, "elapsed_time": "15:33:37", "remaining_time": "7:55:23"}
100
  {"current_steps": 987, "total_steps": 1479, "eval_loss": 0.06870175153017044, "epoch": 1.998987341772152, "percentage": 66.73, "elapsed_time": "15:49:09", "remaining_time": "7:53:08"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
98
  {"current_steps": 970, "total_steps": 1479, "loss": 0.4829, "learning_rate": 5e-06, "epoch": 1.9645569620253165, "percentage": 65.58, "elapsed_time": "15:24:11", "remaining_time": "8:04:57"}
99
  {"current_steps": 980, "total_steps": 1479, "loss": 0.4834, "learning_rate": 5e-06, "epoch": 1.9848101265822784, "percentage": 66.26, "elapsed_time": "15:33:37", "remaining_time": "7:55:23"}
100
  {"current_steps": 987, "total_steps": 1479, "eval_loss": 0.06870175153017044, "epoch": 1.998987341772152, "percentage": 66.73, "elapsed_time": "15:49:09", "remaining_time": "7:53:08"}
101
+ {"current_steps": 990, "total_steps": 1479, "loss": 0.4569, "learning_rate": 5e-06, "epoch": 2.0050632911392405, "percentage": 66.94, "elapsed_time": "15:52:44", "remaining_time": "7:50:35"}
102
+ {"current_steps": 1000, "total_steps": 1479, "loss": 0.3942, "learning_rate": 5e-06, "epoch": 2.0253164556962027, "percentage": 67.61, "elapsed_time": "16:02:10", "remaining_time": "7:40:52"}
103
+ {"current_steps": 1010, "total_steps": 1479, "loss": 0.391, "learning_rate": 5e-06, "epoch": 2.0455696202531644, "percentage": 68.29, "elapsed_time": "16:11:35", "remaining_time": "7:31:10"}
104
+ {"current_steps": 1020, "total_steps": 1479, "loss": 0.387, "learning_rate": 5e-06, "epoch": 2.0658227848101265, "percentage": 68.97, "elapsed_time": "16:21:01", "remaining_time": "7:21:27"}
105
+ {"current_steps": 1030, "total_steps": 1479, "loss": 0.3871, "learning_rate": 5e-06, "epoch": 2.0860759493670886, "percentage": 69.64, "elapsed_time": "16:30:27", "remaining_time": "7:11:45"}
106
+ {"current_steps": 1040, "total_steps": 1479, "loss": 0.3851, "learning_rate": 5e-06, "epoch": 2.1063291139240508, "percentage": 70.32, "elapsed_time": "16:39:53", "remaining_time": "7:02:04"}
107
+ {"current_steps": 1050, "total_steps": 1479, "loss": 0.3943, "learning_rate": 5e-06, "epoch": 2.1265822784810124, "percentage": 70.99, "elapsed_time": "16:49:19", "remaining_time": "6:52:22"}
108
+ {"current_steps": 1060, "total_steps": 1479, "loss": 0.3897, "learning_rate": 5e-06, "epoch": 2.1468354430379746, "percentage": 71.67, "elapsed_time": "16:58:45", "remaining_time": "6:42:41"}
109
+ {"current_steps": 1070, "total_steps": 1479, "loss": 0.3931, "learning_rate": 5e-06, "epoch": 2.1670886075949367, "percentage": 72.35, "elapsed_time": "17:08:11", "remaining_time": "6:33:01"}
110
+ {"current_steps": 1080, "total_steps": 1479, "loss": 0.3916, "learning_rate": 5e-06, "epoch": 2.187341772151899, "percentage": 73.02, "elapsed_time": "17:17:37", "remaining_time": "6:23:20"}
111
+ {"current_steps": 1090, "total_steps": 1479, "loss": 0.389, "learning_rate": 5e-06, "epoch": 2.207594936708861, "percentage": 73.7, "elapsed_time": "17:27:02", "remaining_time": "6:13:39"}
112
+ {"current_steps": 1100, "total_steps": 1479, "loss": 0.3983, "learning_rate": 5e-06, "epoch": 2.2278481012658227, "percentage": 74.37, "elapsed_time": "17:36:27", "remaining_time": "6:04:00"}
113
+ {"current_steps": 1110, "total_steps": 1479, "loss": 0.3934, "learning_rate": 5e-06, "epoch": 2.248101265822785, "percentage": 75.05, "elapsed_time": "17:45:53", "remaining_time": "5:54:20"}
114
+ {"current_steps": 1120, "total_steps": 1479, "loss": 0.3961, "learning_rate": 5e-06, "epoch": 2.268354430379747, "percentage": 75.73, "elapsed_time": "17:55:18", "remaining_time": "5:44:40"}
115
+ {"current_steps": 1130, "total_steps": 1479, "loss": 0.3977, "learning_rate": 5e-06, "epoch": 2.2886075949367086, "percentage": 76.4, "elapsed_time": "18:04:42", "remaining_time": "5:35:00"}
116
+ {"current_steps": 1140, "total_steps": 1479, "loss": 0.3933, "learning_rate": 5e-06, "epoch": 2.3088607594936708, "percentage": 77.08, "elapsed_time": "18:14:07", "remaining_time": "5:25:21"}
117
+ {"current_steps": 1150, "total_steps": 1479, "loss": 0.3993, "learning_rate": 5e-06, "epoch": 2.329113924050633, "percentage": 77.76, "elapsed_time": "18:23:33", "remaining_time": "5:15:42"}
118
+ {"current_steps": 1160, "total_steps": 1479, "loss": 0.3991, "learning_rate": 5e-06, "epoch": 2.349367088607595, "percentage": 78.43, "elapsed_time": "18:32:58", "remaining_time": "5:06:04"}
119
+ {"current_steps": 1170, "total_steps": 1479, "loss": 0.3994, "learning_rate": 5e-06, "epoch": 2.369620253164557, "percentage": 79.11, "elapsed_time": "18:42:23", "remaining_time": "4:56:25"}
120
+ {"current_steps": 1180, "total_steps": 1479, "loss": 0.3997, "learning_rate": 5e-06, "epoch": 2.389873417721519, "percentage": 79.78, "elapsed_time": "18:51:48", "remaining_time": "4:46:47"}
121
+ {"current_steps": 1190, "total_steps": 1479, "loss": 0.3992, "learning_rate": 5e-06, "epoch": 2.410126582278481, "percentage": 80.46, "elapsed_time": "19:01:14", "remaining_time": "4:37:09"}
122
+ {"current_steps": 1200, "total_steps": 1479, "loss": 0.3978, "learning_rate": 5e-06, "epoch": 2.430379746835443, "percentage": 81.14, "elapsed_time": "19:10:40", "remaining_time": "4:27:31"}
123
+ {"current_steps": 1210, "total_steps": 1479, "loss": 0.3973, "learning_rate": 5e-06, "epoch": 2.4506329113924052, "percentage": 81.81, "elapsed_time": "19:20:05", "remaining_time": "4:17:54"}
124
+ {"current_steps": 1220, "total_steps": 1479, "loss": 0.4011, "learning_rate": 5e-06, "epoch": 2.470886075949367, "percentage": 82.49, "elapsed_time": "19:29:31", "remaining_time": "4:08:17"}
125
+ {"current_steps": 1230, "total_steps": 1479, "loss": 0.4009, "learning_rate": 5e-06, "epoch": 2.491139240506329, "percentage": 83.16, "elapsed_time": "19:38:57", "remaining_time": "3:58:40"}
126
+ {"current_steps": 1240, "total_steps": 1479, "loss": 0.4048, "learning_rate": 5e-06, "epoch": 2.511392405063291, "percentage": 83.84, "elapsed_time": "19:48:23", "remaining_time": "3:49:03"}
127
+ {"current_steps": 1250, "total_steps": 1479, "loss": 0.3985, "learning_rate": 5e-06, "epoch": 2.5316455696202533, "percentage": 84.52, "elapsed_time": "19:57:50", "remaining_time": "3:39:26"}
128
+ {"current_steps": 1260, "total_steps": 1479, "loss": 0.3942, "learning_rate": 5e-06, "epoch": 2.5518987341772155, "percentage": 85.19, "elapsed_time": "20:07:16", "remaining_time": "3:29:50"}
129
+ {"current_steps": 1270, "total_steps": 1479, "loss": 0.4009, "learning_rate": 5e-06, "epoch": 2.572151898734177, "percentage": 85.87, "elapsed_time": "20:16:41", "remaining_time": "3:20:13"}
130
+ {"current_steps": 1280, "total_steps": 1479, "loss": 0.4023, "learning_rate": 5e-06, "epoch": 2.5924050632911393, "percentage": 86.54, "elapsed_time": "20:26:07", "remaining_time": "3:10:37"}
131
+ {"current_steps": 1290, "total_steps": 1479, "loss": 0.4075, "learning_rate": 5e-06, "epoch": 2.6126582278481014, "percentage": 87.22, "elapsed_time": "20:35:34", "remaining_time": "3:01:01"}
132
+ {"current_steps": 1300, "total_steps": 1479, "loss": 0.4019, "learning_rate": 5e-06, "epoch": 2.632911392405063, "percentage": 87.9, "elapsed_time": "20:45:01", "remaining_time": "2:51:25"}
133
+ {"current_steps": 1310, "total_steps": 1479, "loss": 0.4019, "learning_rate": 5e-06, "epoch": 2.6531645569620252, "percentage": 88.57, "elapsed_time": "20:54:28", "remaining_time": "2:41:50"}
134
+ {"current_steps": 1320, "total_steps": 1479, "loss": 0.404, "learning_rate": 5e-06, "epoch": 2.6734177215189874, "percentage": 89.25, "elapsed_time": "21:03:54", "remaining_time": "2:32:14"}
135
+ {"current_steps": 1330, "total_steps": 1479, "loss": 0.4067, "learning_rate": 5e-06, "epoch": 2.6936708860759495, "percentage": 89.93, "elapsed_time": "21:13:19", "remaining_time": "2:22:39"}
136
+ {"current_steps": 1340, "total_steps": 1479, "loss": 0.4051, "learning_rate": 5e-06, "epoch": 2.7139240506329116, "percentage": 90.6, "elapsed_time": "21:22:45", "remaining_time": "2:13:03"}
137
+ {"current_steps": 1350, "total_steps": 1479, "loss": 0.4047, "learning_rate": 5e-06, "epoch": 2.7341772151898733, "percentage": 91.28, "elapsed_time": "21:32:12", "remaining_time": "2:03:28"}
138
+ {"current_steps": 1360, "total_steps": 1479, "loss": 0.4003, "learning_rate": 5e-06, "epoch": 2.7544303797468355, "percentage": 91.95, "elapsed_time": "21:41:37", "remaining_time": "1:53:53"}
139
+ {"current_steps": 1370, "total_steps": 1479, "loss": 0.4064, "learning_rate": 5e-06, "epoch": 2.7746835443037976, "percentage": 92.63, "elapsed_time": "21:51:02", "remaining_time": "1:44:18"}
140
+ {"current_steps": 1380, "total_steps": 1479, "loss": 0.404, "learning_rate": 5e-06, "epoch": 2.7949367088607593, "percentage": 93.31, "elapsed_time": "22:00:28", "remaining_time": "1:34:43"}
141
+ {"current_steps": 1390, "total_steps": 1479, "loss": 0.4067, "learning_rate": 5e-06, "epoch": 2.8151898734177214, "percentage": 93.98, "elapsed_time": "22:09:53", "remaining_time": "1:25:09"}
142
+ {"current_steps": 1400, "total_steps": 1479, "loss": 0.4002, "learning_rate": 5e-06, "epoch": 2.8354430379746836, "percentage": 94.66, "elapsed_time": "22:19:20", "remaining_time": "1:15:34"}
143
+ {"current_steps": 1410, "total_steps": 1479, "loss": 0.4088, "learning_rate": 5e-06, "epoch": 2.8556962025316457, "percentage": 95.33, "elapsed_time": "22:28:46", "remaining_time": "1:06:00"}
144
+ {"current_steps": 1420, "total_steps": 1479, "loss": 0.4049, "learning_rate": 5e-06, "epoch": 2.875949367088608, "percentage": 96.01, "elapsed_time": "22:38:11", "remaining_time": "0:56:25"}
145
+ {"current_steps": 1430, "total_steps": 1479, "loss": 0.4055, "learning_rate": 5e-06, "epoch": 2.8962025316455695, "percentage": 96.69, "elapsed_time": "22:47:39", "remaining_time": "0:46:51"}
146
+ {"current_steps": 1440, "total_steps": 1479, "loss": 0.4076, "learning_rate": 5e-06, "epoch": 2.9164556962025316, "percentage": 97.36, "elapsed_time": "22:57:06", "remaining_time": "0:37:17"}
147
+ {"current_steps": 1450, "total_steps": 1479, "loss": 0.4162, "learning_rate": 5e-06, "epoch": 2.9367088607594938, "percentage": 98.04, "elapsed_time": "23:06:32", "remaining_time": "0:27:43"}
148
+ {"current_steps": 1460, "total_steps": 1479, "loss": 0.4042, "learning_rate": 5e-06, "epoch": 2.9569620253164555, "percentage": 98.72, "elapsed_time": "23:15:58", "remaining_time": "0:18:10"}
149
+ {"current_steps": 1470, "total_steps": 1479, "loss": 0.4082, "learning_rate": 5e-06, "epoch": 2.9772151898734176, "percentage": 99.39, "elapsed_time": "23:25:24", "remaining_time": "0:08:36"}