Hugging Face's logo

mlfoundations-dev
/
hp_ablations_qwen_adambeta1_0.85

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
c9e8f32
·
verified ·
1 Parent(s): 0986602

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 sha256:9be68bcf43a196f8c268fa82773db94bb8ed1421821f400f98f0a1d26679f349
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1033258b81c5860ce094d6a269fe262e80ce3cc852b11dcec7f751569513b1c6
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:944873d9eb8eb80a56c8fdc084276f1a9b6412082d4074c6819660b34805d052
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4949dbc006b8cd762727c34a40905ca4eff8fccfb8e211e68a0717666b9eaf3c
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52d8878fd4fe25eb437724fccce79d67b8dccfcaf540d5490f4c9a61c8a04df1
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0788dd9c93f71d6ce85fe7dc62ab058ce0baca6e7eb71538eb2d20651cf46b0d
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8cbc09a5614daa52034cd278dd525e9def78f1b50890b86f2400cf24d62885ab
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73946219f23ac8051db91ed7a5bcd80848b85656e48fcc1e5c2d94197889315f
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -87,3 +87,47 @@
87
  {"current_steps": 860, "total_steps": 1314, "loss": 0.5989, "learning_rate": 5e-06, "epoch": 1.9606837606837608, "percentage": 65.45, "elapsed_time": "12:40:14", "remaining_time": "6:41:20"}
88
  {"current_steps": 870, "total_steps": 1314, "loss": 0.5964, "learning_rate": 5e-06, "epoch": 1.9834757834757835, "percentage": 66.21, "elapsed_time": "12:48:58", "remaining_time": "6:32:26"}
89
  {"current_steps": 877, "total_steps": 1314, "eval_loss": 0.6190649271011353, "epoch": 1.9994301994301993, "percentage": 66.74, "elapsed_time": "13:02:24", "remaining_time": "6:29:51"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
87
  {"current_steps": 860, "total_steps": 1314, "loss": 0.5989, "learning_rate": 5e-06, "epoch": 1.9606837606837608, "percentage": 65.45, "elapsed_time": "12:40:14", "remaining_time": "6:41:20"}
88
  {"current_steps": 870, "total_steps": 1314, "loss": 0.5964, "learning_rate": 5e-06, "epoch": 1.9834757834757835, "percentage": 66.21, "elapsed_time": "12:48:58", "remaining_time": "6:32:26"}
89
  {"current_steps": 877, "total_steps": 1314, "eval_loss": 0.6190649271011353, "epoch": 1.9994301994301993, "percentage": 66.74, "elapsed_time": "13:02:24", "remaining_time": "6:29:51"}
90
+ {"current_steps": 880, "total_steps": 1314, "loss": 0.6158, "learning_rate": 5e-06, "epoch": 2.006837606837607, "percentage": 66.97, "elapsed_time": "13:06:11", "remaining_time": "6:27:43"}
91
+ {"current_steps": 890, "total_steps": 1314, "loss": 0.5549, "learning_rate": 5e-06, "epoch": 2.0296296296296297, "percentage": 67.73, "elapsed_time": "13:14:55", "remaining_time": "6:18:42"}
92
+ {"current_steps": 900, "total_steps": 1314, "loss": 0.5702, "learning_rate": 5e-06, "epoch": 2.0524216524216525, "percentage": 68.49, "elapsed_time": "13:23:39", "remaining_time": "6:09:41"}
93
+ {"current_steps": 910, "total_steps": 1314, "loss": 0.5684, "learning_rate": 5e-06, "epoch": 2.0752136752136754, "percentage": 69.25, "elapsed_time": "13:32:25", "remaining_time": "6:00:40"}
94
+ {"current_steps": 920, "total_steps": 1314, "loss": 0.5714, "learning_rate": 5e-06, "epoch": 2.098005698005698, "percentage": 70.02, "elapsed_time": "13:41:10", "remaining_time": "5:51:40"}
95
+ {"current_steps": 930, "total_steps": 1314, "loss": 0.5696, "learning_rate": 5e-06, "epoch": 2.1207977207977207, "percentage": 70.78, "elapsed_time": "13:49:55", "remaining_time": "5:42:40"}
96
+ {"current_steps": 940, "total_steps": 1314, "loss": 0.5642, "learning_rate": 5e-06, "epoch": 2.1435897435897435, "percentage": 71.54, "elapsed_time": "13:58:40", "remaining_time": "5:33:41"}
97
+ {"current_steps": 950, "total_steps": 1314, "loss": 0.5651, "learning_rate": 5e-06, "epoch": 2.1663817663817664, "percentage": 72.3, "elapsed_time": "14:07:25", "remaining_time": "5:24:41"}
98
+ {"current_steps": 960, "total_steps": 1314, "loss": 0.5702, "learning_rate": 5e-06, "epoch": 2.1891737891737892, "percentage": 73.06, "elapsed_time": "14:16:11", "remaining_time": "5:15:43"}
99
+ {"current_steps": 970, "total_steps": 1314, "loss": 0.5696, "learning_rate": 5e-06, "epoch": 2.211965811965812, "percentage": 73.82, "elapsed_time": "14:24:57", "remaining_time": "5:06:44"}
100
+ {"current_steps": 980, "total_steps": 1314, "loss": 0.5593, "learning_rate": 5e-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": 0.5683, "learning_rate": 5e-06, "epoch": 2.2575498575498574, "percentage": 75.34, "elapsed_time": "14:42:29", "remaining_time": "4:48:49"}
102
+ {"current_steps": 1000, "total_steps": 1314, "loss": 0.5686, "learning_rate": 5e-06, "epoch": 2.2803418803418802, "percentage": 76.1, "elapsed_time": "14:51:14", "remaining_time": "4:39:51"}
103
+ {"current_steps": 1010, "total_steps": 1314, "loss": 0.566, "learning_rate": 5e-06, "epoch": 2.303133903133903, "percentage": 76.86, "elapsed_time": "15:00:00", "remaining_time": "4:30:53"}
104
+ {"current_steps": 1020, "total_steps": 1314, "loss": 0.5691, "learning_rate": 5e-06, "epoch": 2.325925925925926, "percentage": 77.63, "elapsed_time": "15:08:46", "remaining_time": "4:21:56"}
105
+ {"current_steps": 1030, "total_steps": 1314, "loss": 0.5704, "learning_rate": 5e-06, "epoch": 2.348717948717949, "percentage": 78.39, "elapsed_time": "15:17:30", "remaining_time": "4:12:58"}
106
+ {"current_steps": 1040, "total_steps": 1314, "loss": 0.5684, "learning_rate": 5e-06, "epoch": 2.3715099715099717, "percentage": 79.15, "elapsed_time": "15:26:15", "remaining_time": "4:04:02"}
107
+ {"current_steps": 1050, "total_steps": 1314, "loss": 0.5677, "learning_rate": 5e-06, "epoch": 2.394301994301994, "percentage": 79.91, "elapsed_time": "15:35:00", "remaining_time": "3:55:05"}
108
+ {"current_steps": 1060, "total_steps": 1314, "loss": 0.576, "learning_rate": 5e-06, "epoch": 2.417094017094017, "percentage": 80.67, "elapsed_time": "15:43:46", "remaining_time": "3:46:09"}
109
+ {"current_steps": 1070, "total_steps": 1314, "loss": 0.5789, "learning_rate": 5e-06, "epoch": 2.43988603988604, "percentage": 81.43, "elapsed_time": "15:52:32", "remaining_time": "3:37:12"}
110
+ {"current_steps": 1080, "total_steps": 1314, "loss": 0.5742, "learning_rate": 5e-06, "epoch": 2.4626780626780627, "percentage": 82.19, "elapsed_time": "16:01:17", "remaining_time": "3:28:16"}
111
+ {"current_steps": 1090, "total_steps": 1314, "loss": 0.5718, "learning_rate": 5e-06, "epoch": 2.4854700854700855, "percentage": 82.95, "elapsed_time": "16:10:04", "remaining_time": "3:19:21"}
112
+ {"current_steps": 1100, "total_steps": 1314, "loss": 0.5783, "learning_rate": 5e-06, "epoch": 2.5082621082621084, "percentage": 83.71, "elapsed_time": "16:18:50", "remaining_time": "3:10:25"}
113
+ {"current_steps": 1110, "total_steps": 1314, "loss": 0.5718, "learning_rate": 5e-06, "epoch": 2.5310541310541312, "percentage": 84.47, "elapsed_time": "16:27:36", "remaining_time": "3:01:30"}
114
+ {"current_steps": 1120, "total_steps": 1314, "loss": 0.5699, "learning_rate": 5e-06, "epoch": 2.5538461538461537, "percentage": 85.24, "elapsed_time": "16:36:21", "remaining_time": "2:52:35"}
115
+ {"current_steps": 1130, "total_steps": 1314, "loss": 0.5693, "learning_rate": 5e-06, "epoch": 2.5766381766381765, "percentage": 86.0, "elapsed_time": "16:45:06", "remaining_time": "2:43:39"}
116
+ {"current_steps": 1140, "total_steps": 1314, "loss": 0.5689, "learning_rate": 5e-06, "epoch": 2.5994301994301994, "percentage": 86.76, "elapsed_time": "16:53:51", "remaining_time": "2:34:44"}
117
+ {"current_steps": 1150, "total_steps": 1314, "loss": 0.5692, "learning_rate": 5e-06, "epoch": 2.6222222222222222, "percentage": 87.52, "elapsed_time": "17:02:36", "remaining_time": "2:25:49"}
118
+ {"current_steps": 1160, "total_steps": 1314, "loss": 0.5703, "learning_rate": 5e-06, "epoch": 2.645014245014245, "percentage": 88.28, "elapsed_time": "17:11:21", "remaining_time": "2:16:55"}
119
+ {"current_steps": 1170, "total_steps": 1314, "loss": 0.5731, "learning_rate": 5e-06, "epoch": 2.667806267806268, "percentage": 89.04, "elapsed_time": "17:20:06", "remaining_time": "2:08:00"}
120
+ {"current_steps": 1180, "total_steps": 1314, "loss": 0.5683, "learning_rate": 5e-06, "epoch": 2.690598290598291, "percentage": 89.8, "elapsed_time": "17:28:50", "remaining_time": "1:59:06"}
121
+ {"current_steps": 1190, "total_steps": 1314, "loss": 0.5694, "learning_rate": 5e-06, "epoch": 2.7133903133903132, "percentage": 90.56, "elapsed_time": "17:37:36", "remaining_time": "1:50:12"}
122
+ {"current_steps": 1200, "total_steps": 1314, "loss": 0.5726, "learning_rate": 5e-06, "epoch": 2.736182336182336, "percentage": 91.32, "elapsed_time": "17:46:21", "remaining_time": "1:41:18"}
123
+ {"current_steps": 1210, "total_steps": 1314, "loss": 0.576, "learning_rate": 5e-06, "epoch": 2.758974358974359, "percentage": 92.09, "elapsed_time": "17:55:06", "remaining_time": "1:32:24"}
124
+ {"current_steps": 1220, "total_steps": 1314, "loss": 0.5658, "learning_rate": 5e-06, "epoch": 2.781766381766382, "percentage": 92.85, "elapsed_time": "18:03:51", "remaining_time": "1:23:30"}
125
+ {"current_steps": 1230, "total_steps": 1314, "loss": 0.5643, "learning_rate": 5e-06, "epoch": 2.8045584045584047, "percentage": 93.61, "elapsed_time": "18:12:36", "remaining_time": "1:14:37"}
126
+ {"current_steps": 1240, "total_steps": 1314, "loss": 0.5791, "learning_rate": 5e-06, "epoch": 2.827350427350427, "percentage": 94.37, "elapsed_time": "18:21:20", "remaining_time": "1:05:43"}
127
+ {"current_steps": 1250, "total_steps": 1314, "loss": 0.5757, "learning_rate": 5e-06, "epoch": 2.8501424501424504, "percentage": 95.13, "elapsed_time": "18:30:04", "remaining_time": "0:56:50"}
128
+ {"current_steps": 1260, "total_steps": 1314, "loss": 0.5729, "learning_rate": 5e-06, "epoch": 2.872934472934473, "percentage": 95.89, "elapsed_time": "18:38:49", "remaining_time": "0:47:56"}
129
+ {"current_steps": 1270, "total_steps": 1314, "loss": 0.5739, "learning_rate": 5e-06, "epoch": 2.8957264957264957, "percentage": 96.65, "elapsed_time": "18:47:33", "remaining_time": "0:39:03"}
130
+ {"current_steps": 1280, "total_steps": 1314, "loss": 0.5641, "learning_rate": 5e-06, "epoch": 2.9185185185185185, "percentage": 97.41, "elapsed_time": "18:56:18", "remaining_time": "0:30:11"}
131
+ {"current_steps": 1290, "total_steps": 1314, "loss": 0.5643, "learning_rate": 5e-06, "epoch": 2.9413105413105414, "percentage": 98.17, "elapsed_time": "19:05:04", "remaining_time": "0:21:18"}
132
+ {"current_steps": 1300, "total_steps": 1314, "loss": 0.5654, "learning_rate": 5e-06, "epoch": 2.9641025641025642, "percentage": 98.93, "elapsed_time": "19:13:48", "remaining_time": "0:12:25"}
133
+ {"current_steps": 1310, "total_steps": 1314, "loss": 0.5752, "learning_rate": 5e-06, "epoch": 2.9868945868945866, "percentage": 99.7, "elapsed_time": "19:22:33", "remaining_time": "0:03:32"}