Hugging Face's logo

mlfoundations-dev
/
hp_ablations_mistral_adambeta2_0.98

Text Generation
Transformers
Safetensors
mistral
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
 Community
sedrickkeh commited on
Commit
558cf23
·
verified ·
1 Parent(s): 5ed9b56

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:f6ac9acb90a0a803e67953956a04eb6aa0fad12c1cce03e6f3b00928ead69bd0
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8f6087df366a46b07fd7f89d20fbd7b65ad16c98478a0ffbf589e8de316e752
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bd9ba9525770ea8a6670bf2ca56844627cfed9ec0c71d1953092384e21bc17b
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a1552903c78b4070d9af9672dc836e7acf987bc11b7c28a25503266713e86e4
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:652cab4053a903f2630b76135f5c73bb3d89a90e3e1f42925c678fe8f0421e60
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8751b9b3ee493ab6de5f9b490d5493305077a9958013a61a360b15915dd34e7
3
  size 4540516344
trainer_log.jsonl CHANGED
@@ -98,3 +98,52 @@
98
  {"current_steps": 970, "total_steps": 1479, "loss": 0.4827, "learning_rate": 5e-06, "epoch": 1.9645569620253165, "percentage": 65.58, "elapsed_time": "15:15:46", "remaining_time": "8:00:32"}
99
  {"current_steps": 980, "total_steps": 1479, "loss": 0.4833, "learning_rate": 5e-06, "epoch": 1.9848101265822784, "percentage": 66.26, "elapsed_time": "15:25:07", "remaining_time": "7:51:03"}
100
  {"current_steps": 987, "total_steps": 1479, "eval_loss": 0.06866126507520676, "epoch": 1.998987341772152, "percentage": 66.73, "elapsed_time": "15:40:29", "remaining_time": "7:48:48"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
98
  {"current_steps": 970, "total_steps": 1479, "loss": 0.4827, "learning_rate": 5e-06, "epoch": 1.9645569620253165, "percentage": 65.58, "elapsed_time": "15:15:46", "remaining_time": "8:00:32"}
99
  {"current_steps": 980, "total_steps": 1479, "loss": 0.4833, "learning_rate": 5e-06, "epoch": 1.9848101265822784, "percentage": 66.26, "elapsed_time": "15:25:07", "remaining_time": "7:51:03"}
100
  {"current_steps": 987, "total_steps": 1479, "eval_loss": 0.06866126507520676, "epoch": 1.998987341772152, "percentage": 66.73, "elapsed_time": "15:40:29", "remaining_time": "7:48:48"}
101
+ {"current_steps": 990, "total_steps": 1479, "loss": 0.4557, "learning_rate": 5e-06, "epoch": 2.0050632911392405, "percentage": 66.94, "elapsed_time": "15:43:59", "remaining_time": "7:46:16"}
102
+ {"current_steps": 1000, "total_steps": 1479, "loss": 0.3926, "learning_rate": 5e-06, "epoch": 2.0253164556962027, "percentage": 67.61, "elapsed_time": "15:53:21", "remaining_time": "7:36:39"}
103
+ {"current_steps": 1010, "total_steps": 1479, "loss": 0.3891, "learning_rate": 5e-06, "epoch": 2.0455696202531644, "percentage": 68.29, "elapsed_time": "16:02:43", "remaining_time": "7:27:02"}
104
+ {"current_steps": 1020, "total_steps": 1479, "loss": 0.3852, "learning_rate": 5e-06, "epoch": 2.0658227848101265, "percentage": 68.97, "elapsed_time": "16:12:05", "remaining_time": "7:17:26"}
105
+ {"current_steps": 1030, "total_steps": 1479, "loss": 0.3857, "learning_rate": 5e-06, "epoch": 2.0860759493670886, "percentage": 69.64, "elapsed_time": "16:21:26", "remaining_time": "7:07:49"}
106
+ {"current_steps": 1040, "total_steps": 1479, "loss": 0.3835, "learning_rate": 5e-06, "epoch": 2.1063291139240508, "percentage": 70.32, "elapsed_time": "16:30:47", "remaining_time": "6:58:13"}
107
+ {"current_steps": 1050, "total_steps": 1479, "loss": 0.3936, "learning_rate": 5e-06, "epoch": 2.1265822784810124, "percentage": 70.99, "elapsed_time": "16:40:10", "remaining_time": "6:48:38"}
108
+ {"current_steps": 1060, "total_steps": 1479, "loss": 0.3881, "learning_rate": 5e-06, "epoch": 2.1468354430379746, "percentage": 71.67, "elapsed_time": "16:49:31", "remaining_time": "6:39:02"}
109
+ {"current_steps": 1070, "total_steps": 1479, "loss": 0.3919, "learning_rate": 5e-06, "epoch": 2.1670886075949367, "percentage": 72.35, "elapsed_time": "16:58:53", "remaining_time": "6:29:27"}
110
+ {"current_steps": 1080, "total_steps": 1479, "loss": 0.3896, "learning_rate": 5e-06, "epoch": 2.187341772151899, "percentage": 73.02, "elapsed_time": "17:08:15", "remaining_time": "6:19:52"}
111
+ {"current_steps": 1090, "total_steps": 1479, "loss": 0.3877, "learning_rate": 5e-06, "epoch": 2.207594936708861, "percentage": 73.7, "elapsed_time": "17:17:36", "remaining_time": "6:10:18"}
112
+ {"current_steps": 1100, "total_steps": 1479, "loss": 0.3969, "learning_rate": 5e-06, "epoch": 2.2278481012658227, "percentage": 74.37, "elapsed_time": "17:26:58", "remaining_time": "6:00:43"}
113
+ {"current_steps": 1110, "total_steps": 1479, "loss": 0.3928, "learning_rate": 5e-06, "epoch": 2.248101265822785, "percentage": 75.05, "elapsed_time": "17:36:20", "remaining_time": "5:51:09"}
114
+ {"current_steps": 1120, "total_steps": 1479, "loss": 0.3956, "learning_rate": 5e-06, "epoch": 2.268354430379747, "percentage": 75.73, "elapsed_time": "17:45:43", "remaining_time": "5:41:36"}
115
+ {"current_steps": 1130, "total_steps": 1479, "loss": 0.3963, "learning_rate": 5e-06, "epoch": 2.2886075949367086, "percentage": 76.4, "elapsed_time": "17:55:05", "remaining_time": "5:32:02"}
116
+ {"current_steps": 1140, "total_steps": 1479, "loss": 0.3922, "learning_rate": 5e-06, "epoch": 2.3088607594936708, "percentage": 77.08, "elapsed_time": "18:04:26", "remaining_time": "5:22:28"}
117
+ {"current_steps": 1150, "total_steps": 1479, "loss": 0.3987, "learning_rate": 5e-06, "epoch": 2.329113924050633, "percentage": 77.76, "elapsed_time": "18:13:47", "remaining_time": "5:12:55"}
118
+ {"current_steps": 1160, "total_steps": 1479, "loss": 0.3989, "learning_rate": 5e-06, "epoch": 2.349367088607595, "percentage": 78.43, "elapsed_time": "18:23:08", "remaining_time": "5:03:21"}
119
+ {"current_steps": 1170, "total_steps": 1479, "loss": 0.3992, "learning_rate": 5e-06, "epoch": 2.369620253164557, "percentage": 79.11, "elapsed_time": "18:32:30", "remaining_time": "4:53:48"}
120
+ {"current_steps": 1180, "total_steps": 1479, "loss": 0.3989, "learning_rate": 5e-06, "epoch": 2.389873417721519, "percentage": 79.78, "elapsed_time": "18:41:52", "remaining_time": "4:44:16"}
121
+ {"current_steps": 1190, "total_steps": 1479, "loss": 0.3979, "learning_rate": 5e-06, "epoch": 2.410126582278481, "percentage": 80.46, "elapsed_time": "18:51:14", "remaining_time": "4:34:43"}
122
+ {"current_steps": 1200, "total_steps": 1479, "loss": 0.3969, "learning_rate": 5e-06, "epoch": 2.430379746835443, "percentage": 81.14, "elapsed_time": "19:00:36", "remaining_time": "4:25:11"}
123
+ {"current_steps": 1210, "total_steps": 1479, "loss": 0.3964, "learning_rate": 5e-06, "epoch": 2.4506329113924052, "percentage": 81.81, "elapsed_time": "19:09:57", "remaining_time": "4:15:39"}
124
+ {"current_steps": 1220, "total_steps": 1479, "loss": 0.4, "learning_rate": 5e-06, "epoch": 2.470886075949367, "percentage": 82.49, "elapsed_time": "19:19:19", "remaining_time": "4:06:07"}
125
+ {"current_steps": 1230, "total_steps": 1479, "loss": 0.4001, "learning_rate": 5e-06, "epoch": 2.491139240506329, "percentage": 83.16, "elapsed_time": "19:28:41", "remaining_time": "3:56:35"}
126
+ {"current_steps": 1240, "total_steps": 1479, "loss": 0.4039, "learning_rate": 5e-06, "epoch": 2.511392405063291, "percentage": 83.84, "elapsed_time": "19:38:03", "remaining_time": "3:47:03"}
127
+ {"current_steps": 1250, "total_steps": 1479, "loss": 0.3977, "learning_rate": 5e-06, "epoch": 2.5316455696202533, "percentage": 84.52, "elapsed_time": "19:47:24", "remaining_time": "3:37:32"}
128
+ {"current_steps": 1260, "total_steps": 1479, "loss": 0.3936, "learning_rate": 5e-06, "epoch": 2.5518987341772155, "percentage": 85.19, "elapsed_time": "19:56:47", "remaining_time": "3:28:00"}
129
+ {"current_steps": 1270, "total_steps": 1479, "loss": 0.4, "learning_rate": 5e-06, "epoch": 2.572151898734177, "percentage": 85.87, "elapsed_time": "20:06:09", "remaining_time": "3:18:29"}
130
+ {"current_steps": 1280, "total_steps": 1479, "loss": 0.4013, "learning_rate": 5e-06, "epoch": 2.5924050632911393, "percentage": 86.54, "elapsed_time": "20:15:31", "remaining_time": "3:08:58"}
131
+ {"current_steps": 1290, "total_steps": 1479, "loss": 0.4064, "learning_rate": 5e-06, "epoch": 2.6126582278481014, "percentage": 87.22, "elapsed_time": "20:24:53", "remaining_time": "2:59:27"}
132
+ {"current_steps": 1300, "total_steps": 1479, "loss": 0.4009, "learning_rate": 5e-06, "epoch": 2.632911392405063, "percentage": 87.9, "elapsed_time": "20:34:15", "remaining_time": "2:49:56"}
133
+ {"current_steps": 1310, "total_steps": 1479, "loss": 0.4008, "learning_rate": 5e-06, "epoch": 2.6531645569620252, "percentage": 88.57, "elapsed_time": "20:43:38", "remaining_time": "2:40:26"}
134
+ {"current_steps": 1320, "total_steps": 1479, "loss": 0.4038, "learning_rate": 5e-06, "epoch": 2.6734177215189874, "percentage": 89.25, "elapsed_time": "20:53:01", "remaining_time": "2:30:55"}
135
+ {"current_steps": 1330, "total_steps": 1479, "loss": 0.4058, "learning_rate": 5e-06, "epoch": 2.6936708860759495, "percentage": 89.93, "elapsed_time": "21:02:23", "remaining_time": "2:21:25"}
136
+ {"current_steps": 1340, "total_steps": 1479, "loss": 0.4041, "learning_rate": 5e-06, "epoch": 2.7139240506329116, "percentage": 90.6, "elapsed_time": "21:11:45", "remaining_time": "2:11:55"}
137
+ {"current_steps": 1350, "total_steps": 1479, "loss": 0.4035, "learning_rate": 5e-06, "epoch": 2.7341772151898733, "percentage": 91.28, "elapsed_time": "21:21:07", "remaining_time": "2:02:25"}
138
+ {"current_steps": 1360, "total_steps": 1479, "loss": 0.3998, "learning_rate": 5e-06, "epoch": 2.7544303797468355, "percentage": 91.95, "elapsed_time": "21:30:28", "remaining_time": "1:52:55"}
139
+ {"current_steps": 1370, "total_steps": 1479, "loss": 0.4053, "learning_rate": 5e-06, "epoch": 2.7746835443037976, "percentage": 92.63, "elapsed_time": "21:39:50", "remaining_time": "1:43:25"}
140
+ {"current_steps": 1380, "total_steps": 1479, "loss": 0.4035, "learning_rate": 5e-06, "epoch": 2.7949367088607593, "percentage": 93.31, "elapsed_time": "21:49:12", "remaining_time": "1:33:55"}
141
+ {"current_steps": 1390, "total_steps": 1479, "loss": 0.4061, "learning_rate": 5e-06, "epoch": 2.8151898734177214, "percentage": 93.98, "elapsed_time": "21:58:34", "remaining_time": "1:24:25"}
142
+ {"current_steps": 1400, "total_steps": 1479, "loss": 0.3996, "learning_rate": 5e-06, "epoch": 2.8354430379746836, "percentage": 94.66, "elapsed_time": "22:07:55", "remaining_time": "1:14:55"}
143
+ {"current_steps": 1410, "total_steps": 1479, "loss": 0.4079, "learning_rate": 5e-06, "epoch": 2.8556962025316457, "percentage": 95.33, "elapsed_time": "22:17:18", "remaining_time": "1:05:26"}
144
+ {"current_steps": 1420, "total_steps": 1479, "loss": 0.4039, "learning_rate": 5e-06, "epoch": 2.875949367088608, "percentage": 96.01, "elapsed_time": "22:26:40", "remaining_time": "0:55:57"}
145
+ {"current_steps": 1430, "total_steps": 1479, "loss": 0.4047, "learning_rate": 5e-06, "epoch": 2.8962025316455695, "percentage": 96.69, "elapsed_time": "22:36:02", "remaining_time": "0:46:27"}
146
+ {"current_steps": 1440, "total_steps": 1479, "loss": 0.4069, "learning_rate": 5e-06, "epoch": 2.9164556962025316, "percentage": 97.36, "elapsed_time": "22:45:25", "remaining_time": "0:36:58"}
147
+ {"current_steps": 1450, "total_steps": 1479, "loss": 0.4158, "learning_rate": 5e-06, "epoch": 2.9367088607594938, "percentage": 98.04, "elapsed_time": "22:54:47", "remaining_time": "0:27:29"}
148
+ {"current_steps": 1460, "total_steps": 1479, "loss": 0.4035, "learning_rate": 5e-06, "epoch": 2.9569620253164555, "percentage": 98.72, "elapsed_time": "23:04:09", "remaining_time": "0:18:00"}
149
+ {"current_steps": 1470, "total_steps": 1479, "loss": 0.4076, "learning_rate": 5e-06, "epoch": 2.9772151898734176, "percentage": 99.39, "elapsed_time": "23:13:32", "remaining_time": "0:08:31"}