Hugging Face's logo

mlfoundations-dev
/
hp_ablations_qwen_adambeta2_0.995

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
e55ec84
•
1 Parent(s): 06fc157

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:f36abc0d4ab0ffb963465874eecfd327cc1513df7671db4e47ad7f654456d6a4
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:295da0d25e9781fc177197b7351b8a81fd49de77659c2d2ebd0ec50adbe01e0f
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:852f66aadc46e7ad125f629df63abe09c0d9eade0140e29ce80db963abc9e089
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cec1938ac7b77cefa99dca6a71a28139834cd044f5e33dd93fe4e46a8c9c0f9
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:b5f842d103ac813ce0415ac1975adf2c02fdec2c25056095735dde848db498b1
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9808c750ec6a573991d61a492c6d0b7e8da1adfcf3eb45e8f390cbccb220a0c8
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a59dbb8dab740f81d138489b433198ab599b29f56154cd264d8a60991bc1ae0
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35b332c4f5c6a0ef392e321dc91db088349e12a2d2a515a3ca2e069cb1f200a2
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -87,3 +87,47 @@
87
  {"current_steps": 860, "total_steps": 1314, "loss": 0.5987, "learning_rate": 5e-06, "epoch": 1.9606837606837608, "percentage": 65.45, "elapsed_time": "12:39:47", "remaining_time": "6:41:05"}
88
  {"current_steps": 870, "total_steps": 1314, "loss": 0.5962, "learning_rate": 5e-06, "epoch": 1.9834757834757835, "percentage": 66.21, "elapsed_time": "12:48:32", "remaining_time": "6:32:13"}
89
  {"current_steps": 877, "total_steps": 1314, "eval_loss": 0.6187165379524231, "epoch": 1.9994301994301993, "percentage": 66.74, "elapsed_time": "13:01:56", "remaining_time": "6:29:38"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
87
  {"current_steps": 860, "total_steps": 1314, "loss": 0.5987, "learning_rate": 5e-06, "epoch": 1.9606837606837608, "percentage": 65.45, "elapsed_time": "12:39:47", "remaining_time": "6:41:05"}
88
  {"current_steps": 870, "total_steps": 1314, "loss": 0.5962, "learning_rate": 5e-06, "epoch": 1.9834757834757835, "percentage": 66.21, "elapsed_time": "12:48:32", "remaining_time": "6:32:13"}
89
  {"current_steps": 877, "total_steps": 1314, "eval_loss": 0.6187165379524231, "epoch": 1.9994301994301993, "percentage": 66.74, "elapsed_time": "13:01:56", "remaining_time": "6:29:38"}
90
+ {"current_steps": 880, "total_steps": 1314, "loss": 0.6156, "learning_rate": 5e-06, "epoch": 2.006837606837607, "percentage": 66.97, "elapsed_time": "13:05:42", "remaining_time": "6:27:30"}
91
+ {"current_steps": 890, "total_steps": 1314, "loss": 0.5549, "learning_rate": 5e-06, "epoch": 2.0296296296296297, "percentage": 67.73, "elapsed_time": "13:14:28", "remaining_time": "6:18:29"}
92
+ {"current_steps": 900, "total_steps": 1314, "loss": 0.57, "learning_rate": 5e-06, "epoch": 2.0524216524216525, "percentage": 68.49, "elapsed_time": "13:23:13", "remaining_time": "6:09:29"}
93
+ {"current_steps": 910, "total_steps": 1314, "loss": 0.5682, "learning_rate": 5e-06, "epoch": 2.0752136752136754, "percentage": 69.25, "elapsed_time": "13:31:58", "remaining_time": "6:00:28"}
94
+ {"current_steps": 920, "total_steps": 1314, "loss": 0.5712, "learning_rate": 5e-06, "epoch": 2.098005698005698, "percentage": 70.02, "elapsed_time": "13:40:42", "remaining_time": "5:51:28"}
95
+ {"current_steps": 930, "total_steps": 1314, "loss": 0.5692, "learning_rate": 5e-06, "epoch": 2.1207977207977207, "percentage": 70.78, "elapsed_time": "13:49:28", "remaining_time": "5:42:29"}
96
+ {"current_steps": 940, "total_steps": 1314, "loss": 0.564, "learning_rate": 5e-06, "epoch": 2.1435897435897435, "percentage": 71.54, "elapsed_time": "13:58:14", "remaining_time": "5:33:30"}
97
+ {"current_steps": 950, "total_steps": 1314, "loss": 0.5649, "learning_rate": 5e-06, "epoch": 2.1663817663817664, "percentage": 72.3, "elapsed_time": "14:06:59", "remaining_time": "5:24:32"}
98
+ {"current_steps": 960, "total_steps": 1314, "loss": 0.5699, "learning_rate": 5e-06, "epoch": 2.1891737891737892, "percentage": 73.06, "elapsed_time": "14:15:45", "remaining_time": "5:15:33"}
99
+ {"current_steps": 970, "total_steps": 1314, "loss": 0.5694, "learning_rate": 5e-06, "epoch": 2.211965811965812, "percentage": 73.82, "elapsed_time": "14:24:30", "remaining_time": "5:06:35"}
100
+ {"current_steps": 980, "total_steps": 1314, "loss": 0.559, "learning_rate": 5e-06, "epoch": 2.234757834757835, "percentage": 74.58, "elapsed_time": "14:33:16", "remaining_time": "4:57:37"}
101
+ {"current_steps": 990, "total_steps": 1314, "loss": 0.5681, "learning_rate": 5e-06, "epoch": 2.2575498575498574, "percentage": 75.34, "elapsed_time": "14:42:02", "remaining_time": "4:48:39"}
102
+ {"current_steps": 1000, "total_steps": 1314, "loss": 0.5684, "learning_rate": 5e-06, "epoch": 2.2803418803418802, "percentage": 76.1, "elapsed_time": "14:50:48", "remaining_time": "4:39:42"}
103
+ {"current_steps": 1010, "total_steps": 1314, "loss": 0.5658, "learning_rate": 5e-06, "epoch": 2.303133903133903, "percentage": 76.86, "elapsed_time": "14:59:33", "remaining_time": "4:30:45"}
104
+ {"current_steps": 1020, "total_steps": 1314, "loss": 0.5689, "learning_rate": 5e-06, "epoch": 2.325925925925926, "percentage": 77.63, "elapsed_time": "15:08:18", "remaining_time": "4:21:48"}
105
+ {"current_steps": 1030, "total_steps": 1314, "loss": 0.5702, "learning_rate": 5e-06, "epoch": 2.348717948717949, "percentage": 78.39, "elapsed_time": "15:17:03", "remaining_time": "4:12:51"}
106
+ {"current_steps": 1040, "total_steps": 1314, "loss": 0.5682, "learning_rate": 5e-06, "epoch": 2.3715099715099717, "percentage": 79.15, "elapsed_time": "15:25:48", "remaining_time": "4:03:55"}
107
+ {"current_steps": 1050, "total_steps": 1314, "loss": 0.5675, "learning_rate": 5e-06, "epoch": 2.394301994301994, "percentage": 79.91, "elapsed_time": "15:34:34", "remaining_time": "3:54:58"}
108
+ {"current_steps": 1060, "total_steps": 1314, "loss": 0.5758, "learning_rate": 5e-06, "epoch": 2.417094017094017, "percentage": 80.67, "elapsed_time": "15:43:21", "remaining_time": "3:46:02"}
109
+ {"current_steps": 1070, "total_steps": 1314, "loss": 0.5786, "learning_rate": 5e-06, "epoch": 2.43988603988604, "percentage": 81.43, "elapsed_time": "15:52:07", "remaining_time": "3:37:07"}
110
+ {"current_steps": 1080, "total_steps": 1314, "loss": 0.5739, "learning_rate": 5e-06, "epoch": 2.4626780626780627, "percentage": 82.19, "elapsed_time": "16:00:52", "remaining_time": "3:28:11"}
111
+ {"current_steps": 1090, "total_steps": 1314, "loss": 0.5716, "learning_rate": 5e-06, "epoch": 2.4854700854700855, "percentage": 82.95, "elapsed_time": "16:09:38", "remaining_time": "3:19:15"}
112
+ {"current_steps": 1100, "total_steps": 1314, "loss": 0.578, "learning_rate": 5e-06, "epoch": 2.5082621082621084, "percentage": 83.71, "elapsed_time": "16:18:24", "remaining_time": "3:10:20"}
113
+ {"current_steps": 1110, "total_steps": 1314, "loss": 0.5715, "learning_rate": 5e-06, "epoch": 2.5310541310541312, "percentage": 84.47, "elapsed_time": "16:27:09", "remaining_time": "3:01:25"}
114
+ {"current_steps": 1120, "total_steps": 1314, "loss": 0.5696, "learning_rate": 5e-06, "epoch": 2.5538461538461537, "percentage": 85.24, "elapsed_time": "16:35:54", "remaining_time": "2:52:30"}
115
+ {"current_steps": 1130, "total_steps": 1314, "loss": 0.5691, "learning_rate": 5e-06, "epoch": 2.5766381766381765, "percentage": 86.0, "elapsed_time": "16:44:39", "remaining_time": "2:43:35"}
116
+ {"current_steps": 1140, "total_steps": 1314, "loss": 0.5687, "learning_rate": 5e-06, "epoch": 2.5994301994301994, "percentage": 86.76, "elapsed_time": "16:53:25", "remaining_time": "2:34:40"}
117
+ {"current_steps": 1150, "total_steps": 1314, "loss": 0.569, "learning_rate": 5e-06, "epoch": 2.6222222222222222, "percentage": 87.52, "elapsed_time": "17:02:09", "remaining_time": "2:25:46"}
118
+ {"current_steps": 1160, "total_steps": 1314, "loss": 0.5701, "learning_rate": 5e-06, "epoch": 2.645014245014245, "percentage": 88.28, "elapsed_time": "17:10:53", "remaining_time": "2:16:51"}
119
+ {"current_steps": 1170, "total_steps": 1314, "loss": 0.5729, "learning_rate": 5e-06, "epoch": 2.667806267806268, "percentage": 89.04, "elapsed_time": "17:19:38", "remaining_time": "2:07:57"}
120
+ {"current_steps": 1180, "total_steps": 1314, "loss": 0.5681, "learning_rate": 5e-06, "epoch": 2.690598290598291, "percentage": 89.8, "elapsed_time": "17:28:23", "remaining_time": "1:59:03"}
121
+ {"current_steps": 1190, "total_steps": 1314, "loss": 0.5691, "learning_rate": 5e-06, "epoch": 2.7133903133903132, "percentage": 90.56, "elapsed_time": "17:37:07", "remaining_time": "1:50:09"}
122
+ {"current_steps": 1200, "total_steps": 1314, "loss": 0.5724, "learning_rate": 5e-06, "epoch": 2.736182336182336, "percentage": 91.32, "elapsed_time": "17:45:53", "remaining_time": "1:41:15"}
123
+ {"current_steps": 1210, "total_steps": 1314, "loss": 0.5757, "learning_rate": 5e-06, "epoch": 2.758974358974359, "percentage": 92.09, "elapsed_time": "17:54:38", "remaining_time": "1:32:21"}
124
+ {"current_steps": 1220, "total_steps": 1314, "loss": 0.5656, "learning_rate": 5e-06, "epoch": 2.781766381766382, "percentage": 92.85, "elapsed_time": "18:03:24", "remaining_time": "1:23:28"}
125
+ {"current_steps": 1230, "total_steps": 1314, "loss": 0.5641, "learning_rate": 5e-06, "epoch": 2.8045584045584047, "percentage": 93.61, "elapsed_time": "18:12:10", "remaining_time": "1:14:35"}
126
+ {"current_steps": 1240, "total_steps": 1314, "loss": 0.5789, "learning_rate": 5e-06, "epoch": 2.827350427350427, "percentage": 94.37, "elapsed_time": "18:20:56", "remaining_time": "1:05:42"}
127
+ {"current_steps": 1250, "total_steps": 1314, "loss": 0.5755, "learning_rate": 5e-06, "epoch": 2.8501424501424504, "percentage": 95.13, "elapsed_time": "18:29:42", "remaining_time": "0:56:49"}
128
+ {"current_steps": 1260, "total_steps": 1314, "loss": 0.5727, "learning_rate": 5e-06, "epoch": 2.872934472934473, "percentage": 95.89, "elapsed_time": "18:38:28", "remaining_time": "0:47:56"}
129
+ {"current_steps": 1270, "total_steps": 1314, "loss": 0.5736, "learning_rate": 5e-06, "epoch": 2.8957264957264957, "percentage": 96.65, "elapsed_time": "18:47:14", "remaining_time": "0:39:03"}
130
+ {"current_steps": 1280, "total_steps": 1314, "loss": 0.5638, "learning_rate": 5e-06, "epoch": 2.9185185185185185, "percentage": 97.41, "elapsed_time": "18:56:00", "remaining_time": "0:30:10"}
131
+ {"current_steps": 1290, "total_steps": 1314, "loss": 0.564, "learning_rate": 5e-06, "epoch": 2.9413105413105414, "percentage": 98.17, "elapsed_time": "19:04:45", "remaining_time": "0:21:17"}
132
+ {"current_steps": 1300, "total_steps": 1314, "loss": 0.5652, "learning_rate": 5e-06, "epoch": 2.9641025641025642, "percentage": 98.93, "elapsed_time": "19:13:30", "remaining_time": "0:12:25"}
133
+ {"current_steps": 1310, "total_steps": 1314, "loss": 0.575, "learning_rate": 5e-06, "epoch": 2.9868945868945866, "percentage": 99.7, "elapsed_time": "19:22:15", "remaining_time": "0:03:32"}