Hugging Face's logo

mlfoundations-dev
/
hp_ablations_qwen_adambeta1_0.95

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
177946c
·
verified ·
1 Parent(s): 33f1957

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 sha256:9690e60c7f4fec6477a1616d8905b8ac3a36542bba9dffb0c5a7862ddf4150be
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80c2154de87ffe712eadd180af12a9a3abe6472705ca66dd3ab9283d54a1df76
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90476652d8fd391722814e3d84167d097d53ea41706090f5eb9e9fe95b31356b
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9373dd173e842e3fd6c2cd030fed3f4848516ccd64dbb769eb9a20d24ffb61bc
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:f0b9c0a0379f9199a74f7e2b7f6ce21eacf6cf86b7d4165661b5d2593dd0dd4c
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:795c203a3fc1e67bd7064d975c35d4ea3eba6f02909ca086769766ec6e0d0e48
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:c9a3a6e917a147b32ea0e45cfc546be91fef3931f8e888a6f196c48486b7b36b
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02582b40a518b12f10b2d362472ea2b3b873d3dfcdcd3cde04e14a5a9a79f0c7
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -87,3 +87,47 @@
87
  {"current_steps": 860, "total_steps": 1314, "loss": 0.5983, "learning_rate": 5e-06, "epoch": 1.9606837606837608, "percentage": 65.45, "elapsed_time": "12:49:47", "remaining_time": "6:46:22"}
88
  {"current_steps": 870, "total_steps": 1314, "loss": 0.5958, "learning_rate": 5e-06, "epoch": 1.9834757834757835, "percentage": 66.21, "elapsed_time": "12:58:38", "remaining_time": "6:37:22"}
89
  {"current_steps": 877, "total_steps": 1314, "eval_loss": 0.618757426738739, "epoch": 1.9994301994301993, "percentage": 66.74, "elapsed_time": "13:12:11", "remaining_time": "6:34:44"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
87
  {"current_steps": 860, "total_steps": 1314, "loss": 0.5983, "learning_rate": 5e-06, "epoch": 1.9606837606837608, "percentage": 65.45, "elapsed_time": "12:49:47", "remaining_time": "6:46:22"}
88
  {"current_steps": 870, "total_steps": 1314, "loss": 0.5958, "learning_rate": 5e-06, "epoch": 1.9834757834757835, "percentage": 66.21, "elapsed_time": "12:58:38", "remaining_time": "6:37:22"}
89
  {"current_steps": 877, "total_steps": 1314, "eval_loss": 0.618757426738739, "epoch": 1.9994301994301993, "percentage": 66.74, "elapsed_time": "13:12:11", "remaining_time": "6:34:44"}
90
+ {"current_steps": 880, "total_steps": 1314, "loss": 0.6152, "learning_rate": 5e-06, "epoch": 2.006837606837607, "percentage": 66.97, "elapsed_time": "13:15:57", "remaining_time": "6:32:32"}
91
+ {"current_steps": 890, "total_steps": 1314, "loss": 0.5547, "learning_rate": 5e-06, "epoch": 2.0296296296296297, "percentage": 67.73, "elapsed_time": "13:24:48", "remaining_time": "6:23:24"}
92
+ {"current_steps": 900, "total_steps": 1314, "loss": 0.5696, "learning_rate": 5e-06, "epoch": 2.0524216524216525, "percentage": 68.49, "elapsed_time": "13:33:40", "remaining_time": "6:14:17"}
93
+ {"current_steps": 910, "total_steps": 1314, "loss": 0.5676, "learning_rate": 5e-06, "epoch": 2.0752136752136754, "percentage": 69.25, "elapsed_time": "13:42:30", "remaining_time": "6:05:09"}
94
+ {"current_steps": 920, "total_steps": 1314, "loss": 0.5706, "learning_rate": 5e-06, "epoch": 2.098005698005698, "percentage": 70.02, "elapsed_time": "13:51:20", "remaining_time": "5:56:01"}
95
+ {"current_steps": 930, "total_steps": 1314, "loss": 0.5685, "learning_rate": 5e-06, "epoch": 2.1207977207977207, "percentage": 70.78, "elapsed_time": "14:00:11", "remaining_time": "5:46:55"}
96
+ {"current_steps": 940, "total_steps": 1314, "loss": 0.5632, "learning_rate": 5e-06, "epoch": 2.1435897435897435, "percentage": 71.54, "elapsed_time": "14:09:03", "remaining_time": "5:37:49"}
97
+ {"current_steps": 950, "total_steps": 1314, "loss": 0.5641, "learning_rate": 5e-06, "epoch": 2.1663817663817664, "percentage": 72.3, "elapsed_time": "14:17:54", "remaining_time": "5:28:42"}
98
+ {"current_steps": 960, "total_steps": 1314, "loss": 0.5691, "learning_rate": 5e-06, "epoch": 2.1891737891737892, "percentage": 73.06, "elapsed_time": "14:26:44", "remaining_time": "5:19:36"}
99
+ {"current_steps": 970, "total_steps": 1314, "loss": 0.5686, "learning_rate": 5e-06, "epoch": 2.211965811965812, "percentage": 73.82, "elapsed_time": "14:35:35", "remaining_time": "5:10:31"}
100
+ {"current_steps": 980, "total_steps": 1314, "loss": 0.5583, "learning_rate": 5e-06, "epoch": 2.234757834757835, "percentage": 74.58, "elapsed_time": "14:44:27", "remaining_time": "5:01:26"}
101
+ {"current_steps": 990, "total_steps": 1314, "loss": 0.5673, "learning_rate": 5e-06, "epoch": 2.2575498575498574, "percentage": 75.34, "elapsed_time": "14:53:18", "remaining_time": "4:52:21"}
102
+ {"current_steps": 1000, "total_steps": 1314, "loss": 0.5676, "learning_rate": 5e-06, "epoch": 2.2803418803418802, "percentage": 76.1, "elapsed_time": "15:02:08", "remaining_time": "4:43:16"}
103
+ {"current_steps": 1010, "total_steps": 1314, "loss": 0.565, "learning_rate": 5e-06, "epoch": 2.303133903133903, "percentage": 76.86, "elapsed_time": "15:10:58", "remaining_time": "4:34:11"}
104
+ {"current_steps": 1020, "total_steps": 1314, "loss": 0.5682, "learning_rate": 5e-06, "epoch": 2.325925925925926, "percentage": 77.63, "elapsed_time": "15:19:48", "remaining_time": "4:25:07"}
105
+ {"current_steps": 1030, "total_steps": 1314, "loss": 0.5694, "learning_rate": 5e-06, "epoch": 2.348717948717949, "percentage": 78.39, "elapsed_time": "15:28:39", "remaining_time": "4:16:03"}
106
+ {"current_steps": 1040, "total_steps": 1314, "loss": 0.5674, "learning_rate": 5e-06, "epoch": 2.3715099715099717, "percentage": 79.15, "elapsed_time": "15:37:29", "remaining_time": "4:06:59"}
107
+ {"current_steps": 1050, "total_steps": 1314, "loss": 0.5668, "learning_rate": 5e-06, "epoch": 2.394301994301994, "percentage": 79.91, "elapsed_time": "15:46:19", "remaining_time": "3:57:56"}
108
+ {"current_steps": 1060, "total_steps": 1314, "loss": 0.5752, "learning_rate": 5e-06, "epoch": 2.417094017094017, "percentage": 80.67, "elapsed_time": "15:55:11", "remaining_time": "3:48:53"}
109
+ {"current_steps": 1070, "total_steps": 1314, "loss": 0.578, "learning_rate": 5e-06, "epoch": 2.43988603988604, "percentage": 81.43, "elapsed_time": "16:04:00", "remaining_time": "3:39:49"}
110
+ {"current_steps": 1080, "total_steps": 1314, "loss": 0.5732, "learning_rate": 5e-06, "epoch": 2.4626780626780627, "percentage": 82.19, "elapsed_time": "16:12:49", "remaining_time": "3:30:46"}
111
+ {"current_steps": 1090, "total_steps": 1314, "loss": 0.5709, "learning_rate": 5e-06, "epoch": 2.4854700854700855, "percentage": 82.95, "elapsed_time": "16:21:37", "remaining_time": "3:21:43"}
112
+ {"current_steps": 1100, "total_steps": 1314, "loss": 0.5773, "learning_rate": 5e-06, "epoch": 2.5082621082621084, "percentage": 83.71, "elapsed_time": "16:30:28", "remaining_time": "3:12:41"}
113
+ {"current_steps": 1110, "total_steps": 1314, "loss": 0.5709, "learning_rate": 5e-06, "epoch": 2.5310541310541312, "percentage": 84.47, "elapsed_time": "16:39:20", "remaining_time": "3:03:39"}
114
+ {"current_steps": 1120, "total_steps": 1314, "loss": 0.569, "learning_rate": 5e-06, "epoch": 2.5538461538461537, "percentage": 85.24, "elapsed_time": "16:48:11", "remaining_time": "2:54:37"}
115
+ {"current_steps": 1130, "total_steps": 1314, "loss": 0.5684, "learning_rate": 5e-06, "epoch": 2.5766381766381765, "percentage": 86.0, "elapsed_time": "16:57:01", "remaining_time": "2:45:36"}
116
+ {"current_steps": 1140, "total_steps": 1314, "loss": 0.5681, "learning_rate": 5e-06, "epoch": 2.5994301994301994, "percentage": 86.76, "elapsed_time": "17:05:52", "remaining_time": "2:36:34"}
117
+ {"current_steps": 1150, "total_steps": 1314, "loss": 0.5684, "learning_rate": 5e-06, "epoch": 2.6222222222222222, "percentage": 87.52, "elapsed_time": "17:14:42", "remaining_time": "2:27:33"}
118
+ {"current_steps": 1160, "total_steps": 1314, "loss": 0.5695, "learning_rate": 5e-06, "epoch": 2.645014245014245, "percentage": 88.28, "elapsed_time": "17:23:34", "remaining_time": "2:18:32"}
119
+ {"current_steps": 1170, "total_steps": 1314, "loss": 0.5723, "learning_rate": 5e-06, "epoch": 2.667806267806268, "percentage": 89.04, "elapsed_time": "17:32:25", "remaining_time": "2:09:31"}
120
+ {"current_steps": 1180, "total_steps": 1314, "loss": 0.5675, "learning_rate": 5e-06, "epoch": 2.690598290598291, "percentage": 89.8, "elapsed_time": "17:41:16", "remaining_time": "2:00:31"}
121
+ {"current_steps": 1190, "total_steps": 1314, "loss": 0.5686, "learning_rate": 5e-06, "epoch": 2.7133903133903132, "percentage": 90.56, "elapsed_time": "17:50:07", "remaining_time": "1:51:30"}
122
+ {"current_steps": 1200, "total_steps": 1314, "loss": 0.5718, "learning_rate": 5e-06, "epoch": 2.736182336182336, "percentage": 91.32, "elapsed_time": "17:58:59", "remaining_time": "1:42:30"}
123
+ {"current_steps": 1210, "total_steps": 1314, "loss": 0.5752, "learning_rate": 5e-06, "epoch": 2.758974358974359, "percentage": 92.09, "elapsed_time": "18:07:51", "remaining_time": "1:33:30"}
124
+ {"current_steps": 1220, "total_steps": 1314, "loss": 0.5651, "learning_rate": 5e-06, "epoch": 2.781766381766382, "percentage": 92.85, "elapsed_time": "18:16:43", "remaining_time": "1:24:30"}
125
+ {"current_steps": 1230, "total_steps": 1314, "loss": 0.5636, "learning_rate": 5e-06, "epoch": 2.8045584045584047, "percentage": 93.61, "elapsed_time": "18:25:36", "remaining_time": "1:15:30"}
126
+ {"current_steps": 1240, "total_steps": 1314, "loss": 0.5784, "learning_rate": 5e-06, "epoch": 2.827350427350427, "percentage": 94.37, "elapsed_time": "18:34:27", "remaining_time": "1:06:30"}
127
+ {"current_steps": 1250, "total_steps": 1314, "loss": 0.575, "learning_rate": 5e-06, "epoch": 2.8501424501424504, "percentage": 95.13, "elapsed_time": "18:43:20", "remaining_time": "0:57:30"}
128
+ {"current_steps": 1260, "total_steps": 1314, "loss": 0.5722, "learning_rate": 5e-06, "epoch": 2.872934472934473, "percentage": 95.89, "elapsed_time": "18:52:11", "remaining_time": "0:48:31"}
129
+ {"current_steps": 1270, "total_steps": 1314, "loss": 0.5731, "learning_rate": 5e-06, "epoch": 2.8957264957264957, "percentage": 96.65, "elapsed_time": "19:01:02", "remaining_time": "0:39:31"}
130
+ {"current_steps": 1280, "total_steps": 1314, "loss": 0.5633, "learning_rate": 5e-06, "epoch": 2.9185185185185185, "percentage": 97.41, "elapsed_time": "19:09:52", "remaining_time": "0:30:32"}
131
+ {"current_steps": 1290, "total_steps": 1314, "loss": 0.5635, "learning_rate": 5e-06, "epoch": 2.9413105413105414, "percentage": 98.17, "elapsed_time": "19:18:44", "remaining_time": "0:21:33"}
132
+ {"current_steps": 1300, "total_steps": 1314, "loss": 0.5646, "learning_rate": 5e-06, "epoch": 2.9641025641025642, "percentage": 98.93, "elapsed_time": "19:27:36", "remaining_time": "0:12:34"}
133
+ {"current_steps": 1310, "total_steps": 1314, "loss": 0.5744, "learning_rate": 5e-06, "epoch": 2.9868945868945866, "percentage": 99.7, "elapsed_time": "19:36:27", "remaining_time": "0:03:35"}