Hugging Face's logo

mlfoundations-dev
/
hp_ablations_qwen_lr8e-6

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
 Community
1
sedrickkeh commited on
Commit
ed9babc
·
verified ·
1 Parent(s): 0f88e91

Training in progress, epoch 2

Browse files
Files changed (5) hide show
  1. model-00001-of-00004.safetensors +1 -1
  2. model-00002-of-00004.safetensors +1 -1
  3. model-00003-of-00004.safetensors +1 -1
  4. model-00004-of-00004.safetensors +1 -1
  5. trainer_log.jsonl +44 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:033ce675178d4558adf5813f4fc2e4bf1d4d5cfe81fad296e2b41c70f6748c43
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cbb0b2b02bfbf95fe6d07b91fbbfdd9520bdd5a6a36fdfb02a9c7715fc1f20d
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6fe8bb5ee83da42ff35cd6ff0f18c25666fd694349bb6a31e33e142adb2a39da
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b3763f7cd8e61a5c7b7ac194a117d722b6fdf764b47c453eee1b7c192cd6ebf
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23e3eaeb79381c6936a57ed8aaa24c51103a23c232eda45046646a8e9ad0994a
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82e52585ae7a330681cd8a48a4a2076948d79b9e6ee60c183623f073b55baab0
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6cd42d51462286fcdbe5e68bbaad82e1eb7c17501fc0f08193ccfc0efd1f57ff
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:177dbb5e39f752146d6da90b8667123851c68cffe2b7fa30cc69cc1ab439a539
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -87,3 +87,47 @@
87
  {"current_steps": 860, "total_steps": 1314, "loss": 0.5864, "learning_rate": 8e-06, "epoch": 1.9606837606837608, "percentage": 65.45, "elapsed_time": "12:40:22", "remaining_time": "6:41:24"}
88
  {"current_steps": 870, "total_steps": 1314, "loss": 0.5839, "learning_rate": 8e-06, "epoch": 1.9834757834757835, "percentage": 66.21, "elapsed_time": "12:49:06", "remaining_time": "6:32:30"}
89
  {"current_steps": 877, "total_steps": 1314, "eval_loss": 0.6177216172218323, "epoch": 1.9994301994301993, "percentage": 66.74, "elapsed_time": "13:02:32", "remaining_time": "6:29:55"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
87
  {"current_steps": 860, "total_steps": 1314, "loss": 0.5864, "learning_rate": 8e-06, "epoch": 1.9606837606837608, "percentage": 65.45, "elapsed_time": "12:40:22", "remaining_time": "6:41:24"}
88
  {"current_steps": 870, "total_steps": 1314, "loss": 0.5839, "learning_rate": 8e-06, "epoch": 1.9834757834757835, "percentage": 66.21, "elapsed_time": "12:49:06", "remaining_time": "6:32:30"}
89
  {"current_steps": 877, "total_steps": 1314, "eval_loss": 0.6177216172218323, "epoch": 1.9994301994301993, "percentage": 66.74, "elapsed_time": "13:02:32", "remaining_time": "6:29:55"}
90
+ {"current_steps": 880, "total_steps": 1314, "loss": 0.5988, "learning_rate": 8e-06, "epoch": 2.006837606837607, "percentage": 66.97, "elapsed_time": "13:06:13", "remaining_time": "6:27:45"}
91
+ {"current_steps": 890, "total_steps": 1314, "loss": 0.529, "learning_rate": 8e-06, "epoch": 2.0296296296296297, "percentage": 67.73, "elapsed_time": "13:14:58", "remaining_time": "6:18:43"}
92
+ {"current_steps": 900, "total_steps": 1314, "loss": 0.5431, "learning_rate": 8e-06, "epoch": 2.0524216524216525, "percentage": 68.49, "elapsed_time": "13:23:43", "remaining_time": "6:09:42"}
93
+ {"current_steps": 910, "total_steps": 1314, "loss": 0.5415, "learning_rate": 8e-06, "epoch": 2.0752136752136754, "percentage": 69.25, "elapsed_time": "13:32:28", "remaining_time": "6:00:42"}
94
+ {"current_steps": 920, "total_steps": 1314, "loss": 0.5444, "learning_rate": 8e-06, "epoch": 2.098005698005698, "percentage": 70.02, "elapsed_time": "13:41:13", "remaining_time": "5:51:42"}
95
+ {"current_steps": 930, "total_steps": 1314, "loss": 0.5431, "learning_rate": 8e-06, "epoch": 2.1207977207977207, "percentage": 70.78, "elapsed_time": "13:49:59", "remaining_time": "5:42:42"}
96
+ {"current_steps": 940, "total_steps": 1314, "loss": 0.538, "learning_rate": 8e-06, "epoch": 2.1435897435897435, "percentage": 71.54, "elapsed_time": "13:58:44", "remaining_time": "5:33:42"}
97
+ {"current_steps": 950, "total_steps": 1314, "loss": 0.5388, "learning_rate": 8e-06, "epoch": 2.1663817663817664, "percentage": 72.3, "elapsed_time": "14:07:29", "remaining_time": "5:24:43"}
98
+ {"current_steps": 960, "total_steps": 1314, "loss": 0.544, "learning_rate": 8e-06, "epoch": 2.1891737891737892, "percentage": 73.06, "elapsed_time": "14:16:14", "remaining_time": "5:15:44"}
99
+ {"current_steps": 970, "total_steps": 1314, "loss": 0.5438, "learning_rate": 8e-06, "epoch": 2.211965811965812, "percentage": 73.82, "elapsed_time": "14:24:58", "remaining_time": "5:06:45"}
100
+ {"current_steps": 980, "total_steps": 1314, "loss": 0.5341, "learning_rate": 8e-06, "epoch": 2.234757834757835, "percentage": 74.58, "elapsed_time": "14:33:43", "remaining_time": "4:57:46"}
101
+ {"current_steps": 990, "total_steps": 1314, "loss": 0.543, "learning_rate": 8e-06, "epoch": 2.2575498575498574, "percentage": 75.34, "elapsed_time": "14:42:28", "remaining_time": "4:48:48"}
102
+ {"current_steps": 1000, "total_steps": 1314, "loss": 0.5435, "learning_rate": 8e-06, "epoch": 2.2803418803418802, "percentage": 76.1, "elapsed_time": "14:51:13", "remaining_time": "4:39:50"}
103
+ {"current_steps": 1010, "total_steps": 1314, "loss": 0.541, "learning_rate": 8e-06, "epoch": 2.303133903133903, "percentage": 76.86, "elapsed_time": "14:59:58", "remaining_time": "4:30:53"}
104
+ {"current_steps": 1020, "total_steps": 1314, "loss": 0.5441, "learning_rate": 8e-06, "epoch": 2.325925925925926, "percentage": 77.63, "elapsed_time": "15:08:43", "remaining_time": "4:21:55"}
105
+ {"current_steps": 1030, "total_steps": 1314, "loss": 0.5454, "learning_rate": 8e-06, "epoch": 2.348717948717949, "percentage": 78.39, "elapsed_time": "15:17:27", "remaining_time": "4:12:58"}
106
+ {"current_steps": 1040, "total_steps": 1314, "loss": 0.5438, "learning_rate": 8e-06, "epoch": 2.3715099715099717, "percentage": 79.15, "elapsed_time": "15:26:12", "remaining_time": "4:04:01"}
107
+ {"current_steps": 1050, "total_steps": 1314, "loss": 0.5431, "learning_rate": 8e-06, "epoch": 2.394301994301994, "percentage": 79.91, "elapsed_time": "15:34:56", "remaining_time": "3:55:04"}
108
+ {"current_steps": 1060, "total_steps": 1314, "loss": 0.5512, "learning_rate": 8e-06, "epoch": 2.417094017094017, "percentage": 80.67, "elapsed_time": "15:43:41", "remaining_time": "3:46:07"}
109
+ {"current_steps": 1070, "total_steps": 1314, "loss": 0.5539, "learning_rate": 8e-06, "epoch": 2.43988603988604, "percentage": 81.43, "elapsed_time": "15:52:26", "remaining_time": "3:37:11"}
110
+ {"current_steps": 1080, "total_steps": 1314, "loss": 0.5494, "learning_rate": 8e-06, "epoch": 2.4626780626780627, "percentage": 82.19, "elapsed_time": "16:01:12", "remaining_time": "3:28:15"}
111
+ {"current_steps": 1090, "total_steps": 1314, "loss": 0.5476, "learning_rate": 8e-06, "epoch": 2.4854700854700855, "percentage": 82.95, "elapsed_time": "16:09:58", "remaining_time": "3:19:19"}
112
+ {"current_steps": 1100, "total_steps": 1314, "loss": 0.5535, "learning_rate": 8e-06, "epoch": 2.5082621082621084, "percentage": 83.71, "elapsed_time": "16:18:42", "remaining_time": "3:10:24"}
113
+ {"current_steps": 1110, "total_steps": 1314, "loss": 0.5477, "learning_rate": 8e-06, "epoch": 2.5310541310541312, "percentage": 84.47, "elapsed_time": "16:27:27", "remaining_time": "3:01:28"}
114
+ {"current_steps": 1120, "total_steps": 1314, "loss": 0.5458, "learning_rate": 8e-06, "epoch": 2.5538461538461537, "percentage": 85.24, "elapsed_time": "16:36:12", "remaining_time": "2:52:33"}
115
+ {"current_steps": 1130, "total_steps": 1314, "loss": 0.5455, "learning_rate": 8e-06, "epoch": 2.5766381766381765, "percentage": 86.0, "elapsed_time": "16:44:58", "remaining_time": "2:43:38"}
116
+ {"current_steps": 1140, "total_steps": 1314, "loss": 0.5452, "learning_rate": 8e-06, "epoch": 2.5994301994301994, "percentage": 86.76, "elapsed_time": "16:53:43", "remaining_time": "2:34:43"}
117
+ {"current_steps": 1150, "total_steps": 1314, "loss": 0.5458, "learning_rate": 8e-06, "epoch": 2.6222222222222222, "percentage": 87.52, "elapsed_time": "17:02:27", "remaining_time": "2:25:48"}
118
+ {"current_steps": 1160, "total_steps": 1314, "loss": 0.547, "learning_rate": 8e-06, "epoch": 2.645014245014245, "percentage": 88.28, "elapsed_time": "17:11:12", "remaining_time": "2:16:54"}
119
+ {"current_steps": 1170, "total_steps": 1314, "loss": 0.5495, "learning_rate": 8e-06, "epoch": 2.667806267806268, "percentage": 89.04, "elapsed_time": "17:19:57", "remaining_time": "2:07:59"}
120
+ {"current_steps": 1180, "total_steps": 1314, "loss": 0.5449, "learning_rate": 8e-06, "epoch": 2.690598290598291, "percentage": 89.8, "elapsed_time": "17:28:40", "remaining_time": "1:59:05"}
121
+ {"current_steps": 1190, "total_steps": 1314, "loss": 0.5462, "learning_rate": 8e-06, "epoch": 2.7133903133903132, "percentage": 90.56, "elapsed_time": "17:37:24", "remaining_time": "1:50:11"}
122
+ {"current_steps": 1200, "total_steps": 1314, "loss": 0.5494, "learning_rate": 8e-06, "epoch": 2.736182336182336, "percentage": 91.32, "elapsed_time": "17:46:08", "remaining_time": "1:41:16"}
123
+ {"current_steps": 1210, "total_steps": 1314, "loss": 0.5526, "learning_rate": 8e-06, "epoch": 2.758974358974359, "percentage": 92.09, "elapsed_time": "17:54:53", "remaining_time": "1:32:23"}
124
+ {"current_steps": 1220, "total_steps": 1314, "loss": 0.543, "learning_rate": 8e-06, "epoch": 2.781766381766382, "percentage": 92.85, "elapsed_time": "18:03:38", "remaining_time": "1:23:29"}
125
+ {"current_steps": 1230, "total_steps": 1314, "loss": 0.5415, "learning_rate": 8e-06, "epoch": 2.8045584045584047, "percentage": 93.61, "elapsed_time": "18:12:24", "remaining_time": "1:14:36"}
126
+ {"current_steps": 1240, "total_steps": 1314, "loss": 0.5559, "learning_rate": 8e-06, "epoch": 2.827350427350427, "percentage": 94.37, "elapsed_time": "18:21:09", "remaining_time": "1:05:42"}
127
+ {"current_steps": 1250, "total_steps": 1314, "loss": 0.5525, "learning_rate": 8e-06, "epoch": 2.8501424501424504, "percentage": 95.13, "elapsed_time": "18:29:54", "remaining_time": "0:56:49"}
128
+ {"current_steps": 1260, "total_steps": 1314, "loss": 0.5499, "learning_rate": 8e-06, "epoch": 2.872934472934473, "percentage": 95.89, "elapsed_time": "18:38:39", "remaining_time": "0:47:56"}
129
+ {"current_steps": 1270, "total_steps": 1314, "loss": 0.551, "learning_rate": 8e-06, "epoch": 2.8957264957264957, "percentage": 96.65, "elapsed_time": "18:47:24", "remaining_time": "0:39:03"}
130
+ {"current_steps": 1280, "total_steps": 1314, "loss": 0.5415, "learning_rate": 8e-06, "epoch": 2.9185185185185185, "percentage": 97.41, "elapsed_time": "18:56:10", "remaining_time": "0:30:10"}
131
+ {"current_steps": 1290, "total_steps": 1314, "loss": 0.5419, "learning_rate": 8e-06, "epoch": 2.9413105413105414, "percentage": 98.17, "elapsed_time": "19:04:54", "remaining_time": "0:21:18"}
132
+ {"current_steps": 1300, "total_steps": 1314, "loss": 0.543, "learning_rate": 8e-06, "epoch": 2.9641025641025642, "percentage": 98.93, "elapsed_time": "19:13:39", "remaining_time": "0:12:25"}
133
+ {"current_steps": 1310, "total_steps": 1314, "loss": 0.5523, "learning_rate": 8e-06, "epoch": 2.9868945868945866, "percentage": 99.7, "elapsed_time": "19:22:25", "remaining_time": "0:03:32"}