Hugging Face's logo

mlfoundations-dev
/
hp_ablations_qwen_lr5e-6_dcftv1.2

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
b100ad7
•
1 Parent(s): d76e989

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 +34 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5090b4b6e9f28597f8e76574081fd1f90c398d9d8e41eb30bf6227f2b6b94169
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:693c9a91321eaa4aa718507364d880b7bb3244d01c4506fb315325bf5b1d7dd6
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:f21e48ab38a8dd94e9c05873267b612eb9d488d00f8fbe56b60baf2b3b517e59
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85bb6dee48139081fef849a4967c5e04786a24d6f9e1a01f38796188fa37f415
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24f7b720a360e8d5faddc664787cb026370fc5bf465d640968403b40dd0fff29
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27a86a8e04915ba523fae3cc6a3de42383dea8ec612cec290daa06db5b1cc3c5
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:dde392298209c940108e47a516c9cb631825f27f211da8b0764f836c8145e3cf
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c82079187fdb4c295553bd57568e50274dd0f9abdb07ccbf91c067a437695a42
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -68,3 +68,37 @@
68
  {"current_steps": 670, "total_steps": 1023, "loss": 0.5952, "learning_rate": 5e-06, "epoch": 1.9615947329919532, "percentage": 65.49, "elapsed_time": "9:54:23", "remaining_time": "5:13:09"}
69
  {"current_steps": 680, "total_steps": 1023, "loss": 0.6097, "learning_rate": 5e-06, "epoch": 1.9908558888076078, "percentage": 66.47, "elapsed_time": "10:03:09", "remaining_time": "5:04:14"}
70
  {"current_steps": 682, "total_steps": 1023, "eval_loss": 0.6332100629806519, "epoch": 1.9967081199707388, "percentage": 66.67, "elapsed_time": "10:11:19", "remaining_time": "5:05:39"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  {"current_steps": 670, "total_steps": 1023, "loss": 0.5952, "learning_rate": 5e-06, "epoch": 1.9615947329919532, "percentage": 65.49, "elapsed_time": "9:54:23", "remaining_time": "5:13:09"}
69
  {"current_steps": 680, "total_steps": 1023, "loss": 0.6097, "learning_rate": 5e-06, "epoch": 1.9908558888076078, "percentage": 66.47, "elapsed_time": "10:03:09", "remaining_time": "5:04:14"}
70
  {"current_steps": 682, "total_steps": 1023, "eval_loss": 0.6332100629806519, "epoch": 1.9967081199707388, "percentage": 66.67, "elapsed_time": "10:11:19", "remaining_time": "5:05:39"}
71
+ {"current_steps": 690, "total_steps": 1023, "loss": 0.6197, "learning_rate": 5e-06, "epoch": 2.0212143379663496, "percentage": 67.45, "elapsed_time": "10:18:55", "remaining_time": "4:58:41"}
72
+ {"current_steps": 700, "total_steps": 1023, "loss": 0.5673, "learning_rate": 5e-06, "epoch": 2.050475493782004, "percentage": 68.43, "elapsed_time": "10:27:43", "remaining_time": "4:49:38"}
73
+ {"current_steps": 710, "total_steps": 1023, "loss": 0.5694, "learning_rate": 5e-06, "epoch": 2.0797366495976592, "percentage": 69.4, "elapsed_time": "10:36:30", "remaining_time": "4:40:36"}
74
+ {"current_steps": 720, "total_steps": 1023, "loss": 0.5704, "learning_rate": 5e-06, "epoch": 2.108997805413314, "percentage": 70.38, "elapsed_time": "10:45:18", "remaining_time": "4:31:33"}
75
+ {"current_steps": 730, "total_steps": 1023, "loss": 0.5723, "learning_rate": 5e-06, "epoch": 2.1382589612289684, "percentage": 71.36, "elapsed_time": "10:54:06", "remaining_time": "4:22:32"}
76
+ {"current_steps": 740, "total_steps": 1023, "loss": 0.5775, "learning_rate": 5e-06, "epoch": 2.1675201170446234, "percentage": 72.34, "elapsed_time": "11:02:54", "remaining_time": "4:13:30"}
77
+ {"current_steps": 750, "total_steps": 1023, "loss": 0.5763, "learning_rate": 5e-06, "epoch": 2.196781272860278, "percentage": 73.31, "elapsed_time": "11:11:41", "remaining_time": "4:04:29"}
78
+ {"current_steps": 760, "total_steps": 1023, "loss": 0.5737, "learning_rate": 5e-06, "epoch": 2.2260424286759326, "percentage": 74.29, "elapsed_time": "11:20:29", "remaining_time": "3:55:28"}
79
+ {"current_steps": 770, "total_steps": 1023, "loss": 0.5725, "learning_rate": 5e-06, "epoch": 2.255303584491587, "percentage": 75.27, "elapsed_time": "11:29:16", "remaining_time": "3:46:28"}
80
+ {"current_steps": 780, "total_steps": 1023, "loss": 0.5716, "learning_rate": 5e-06, "epoch": 2.284564740307242, "percentage": 76.25, "elapsed_time": "11:38:04", "remaining_time": "3:37:28"}
81
+ {"current_steps": 790, "total_steps": 1023, "loss": 0.5699, "learning_rate": 5e-06, "epoch": 2.313825896122897, "percentage": 77.22, "elapsed_time": "11:46:52", "remaining_time": "3:28:28"}
82
+ {"current_steps": 800, "total_steps": 1023, "loss": 0.5777, "learning_rate": 5e-06, "epoch": 2.3430870519385514, "percentage": 78.2, "elapsed_time": "11:55:40", "remaining_time": "3:19:29"}
83
+ {"current_steps": 810, "total_steps": 1023, "loss": 0.5728, "learning_rate": 5e-06, "epoch": 2.3723482077542064, "percentage": 79.18, "elapsed_time": "12:04:28", "remaining_time": "3:10:30"}
84
+ {"current_steps": 820, "total_steps": 1023, "loss": 0.5791, "learning_rate": 5e-06, "epoch": 2.401609363569861, "percentage": 80.16, "elapsed_time": "12:13:15", "remaining_time": "3:01:31"}
85
+ {"current_steps": 830, "total_steps": 1023, "loss": 0.5714, "learning_rate": 5e-06, "epoch": 2.4308705193855156, "percentage": 81.13, "elapsed_time": "12:22:03", "remaining_time": "2:52:33"}
86
+ {"current_steps": 840, "total_steps": 1023, "loss": 0.5719, "learning_rate": 5e-06, "epoch": 2.4601316752011706, "percentage": 82.11, "elapsed_time": "12:30:51", "remaining_time": "2:43:34"}
87
+ {"current_steps": 850, "total_steps": 1023, "loss": 0.5741, "learning_rate": 5e-06, "epoch": 2.489392831016825, "percentage": 83.09, "elapsed_time": "12:39:39", "remaining_time": "2:34:36"}
88
+ {"current_steps": 860, "total_steps": 1023, "loss": 0.5671, "learning_rate": 5e-06, "epoch": 2.5186539868324798, "percentage": 84.07, "elapsed_time": "12:48:26", "remaining_time": "2:25:38"}
89
+ {"current_steps": 870, "total_steps": 1023, "loss": 0.5696, "learning_rate": 5e-06, "epoch": 2.547915142648135, "percentage": 85.04, "elapsed_time": "12:57:14", "remaining_time": "2:16:41"}
90
+ {"current_steps": 880, "total_steps": 1023, "loss": 0.5738, "learning_rate": 5e-06, "epoch": 2.5771762984637894, "percentage": 86.02, "elapsed_time": "13:06:01", "remaining_time": "2:07:43"}
91
+ {"current_steps": 890, "total_steps": 1023, "loss": 0.5731, "learning_rate": 5e-06, "epoch": 2.606437454279444, "percentage": 87.0, "elapsed_time": "13:14:49", "remaining_time": "1:58:46"}
92
+ {"current_steps": 900, "total_steps": 1023, "loss": 0.5777, "learning_rate": 5e-06, "epoch": 2.6356986100950985, "percentage": 87.98, "elapsed_time": "13:23:36", "remaining_time": "1:49:49"}
93
+ {"current_steps": 910, "total_steps": 1023, "loss": 0.5778, "learning_rate": 5e-06, "epoch": 2.6649597659107536, "percentage": 88.95, "elapsed_time": "13:32:23", "remaining_time": "1:40:52"}
94
+ {"current_steps": 920, "total_steps": 1023, "loss": 0.5722, "learning_rate": 5e-06, "epoch": 2.694220921726408, "percentage": 89.93, "elapsed_time": "13:41:10", "remaining_time": "1:31:56"}
95
+ {"current_steps": 930, "total_steps": 1023, "loss": 0.5758, "learning_rate": 5e-06, "epoch": 2.723482077542063, "percentage": 90.91, "elapsed_time": "13:49:58", "remaining_time": "1:22:59"}
96
+ {"current_steps": 940, "total_steps": 1023, "loss": 0.5748, "learning_rate": 5e-06, "epoch": 2.7527432333577178, "percentage": 91.89, "elapsed_time": "13:58:46", "remaining_time": "1:14:03"}
97
+ {"current_steps": 950, "total_steps": 1023, "loss": 0.5735, "learning_rate": 5e-06, "epoch": 2.7820043891733723, "percentage": 92.86, "elapsed_time": "14:07:33", "remaining_time": "1:05:07"}
98
+ {"current_steps": 960, "total_steps": 1023, "loss": 0.5774, "learning_rate": 5e-06, "epoch": 2.811265544989027, "percentage": 93.84, "elapsed_time": "14:16:20", "remaining_time": "0:56:11"}
99
+ {"current_steps": 970, "total_steps": 1023, "loss": 0.5731, "learning_rate": 5e-06, "epoch": 2.840526700804682, "percentage": 94.82, "elapsed_time": "14:25:08", "remaining_time": "0:47:16"}
100
+ {"current_steps": 980, "total_steps": 1023, "loss": 0.5729, "learning_rate": 5e-06, "epoch": 2.8697878566203365, "percentage": 95.8, "elapsed_time": "14:33:56", "remaining_time": "0:38:20"}
101
+ {"current_steps": 990, "total_steps": 1023, "loss": 0.5659, "learning_rate": 5e-06, "epoch": 2.899049012435991, "percentage": 96.77, "elapsed_time": "14:42:43", "remaining_time": "0:29:25"}
102
+ {"current_steps": 1000, "total_steps": 1023, "loss": 0.5737, "learning_rate": 5e-06, "epoch": 2.928310168251646, "percentage": 97.75, "elapsed_time": "14:51:31", "remaining_time": "0:20:30"}
103
+ {"current_steps": 1010, "total_steps": 1023, "loss": 0.5654, "learning_rate": 5e-06, "epoch": 2.9575713240673007, "percentage": 98.73, "elapsed_time": "15:00:19", "remaining_time": "0:11:35"}
104
+ {"current_steps": 1020, "total_steps": 1023, "loss": 0.5771, "learning_rate": 5e-06, "epoch": 2.9868324798829553, "percentage": 99.71, "elapsed_time": "15:09:06", "remaining_time": "0:02:40"}