Hugging Face's logo

mlfoundations-dev
/
hp_ablations_qwen_scheduler_cosine_warmup0.05_minlr1e-6_dcftv1.2

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
803cd43
·
verified ·
1 Parent(s): d190f31

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 sha256:37b0e9850b1c9e1ba9a527fc1cad6c4371c418254d8d7c55a9e1a080fcdf9fb3
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8316ba8e1e4687694003d1f7cee02815c7099e2cdd7f5f2c24572fc8ffd3bee5
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63d875c37214ce5ecea9f85a0d7decdb6cb9dba38c43eee5b6a85ee67bb90631
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a64c8235e235959761373f9a024b483645cb37352147619311539ebaf114fa4
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7981efa6daf7e51bbd098ae1e595e5971e087ab5f0f055a1fe92d75cf9bc01e4
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e05d5750ec31dce31191899b7c4eb2417264487576e50d9de4048210038b6bf0
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05dddbe36c26f8324f741914454d71c573fed0d71e3b240f8a707cc31263baa4
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb29b9a17b7be3ada83a5570da02ad2ef9c0d86240ab249cc31561e258485aae
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -68,3 +68,37 @@
68
  {"current_steps": 670, "total_steps": 1023, "loss": 0.5979, "learning_rate": 2.1686349115069234e-06, "epoch": 1.9615947329919532, "percentage": 65.49, "elapsed_time": "9:52:13", "remaining_time": "5:12:01"}
69
  {"current_steps": 680, "total_steps": 1023, "loss": 0.6124, "learning_rate": 2.1102273559743233e-06, "epoch": 1.9908558888076078, "percentage": 66.47, "elapsed_time": "10:00:57", "remaining_time": "5:03:07"}
70
  {"current_steps": 682, "total_steps": 1023, "eval_loss": 0.6345736980438232, "epoch": 1.9967081199707388, "percentage": 66.67, "elapsed_time": "10:09:04", "remaining_time": "5:04:32"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  {"current_steps": 670, "total_steps": 1023, "loss": 0.5979, "learning_rate": 2.1686349115069234e-06, "epoch": 1.9615947329919532, "percentage": 65.49, "elapsed_time": "9:52:13", "remaining_time": "5:12:01"}
69
  {"current_steps": 680, "total_steps": 1023, "loss": 0.6124, "learning_rate": 2.1102273559743233e-06, "epoch": 1.9908558888076078, "percentage": 66.47, "elapsed_time": "10:00:57", "remaining_time": "5:03:07"}
70
  {"current_steps": 682, "total_steps": 1023, "eval_loss": 0.6345736980438232, "epoch": 1.9967081199707388, "percentage": 66.67, "elapsed_time": "10:09:04", "remaining_time": "5:04:32"}
71
+ {"current_steps": 690, "total_steps": 1023, "loss": 0.6304, "learning_rate": 2.052751127990816e-06, "epoch": 2.0212143379663496, "percentage": 67.45, "elapsed_time": "10:16:37", "remaining_time": "4:57:35"}
72
+ {"current_steps": 700, "total_steps": 1023, "loss": 0.581, "learning_rate": 1.996266388087183e-06, "epoch": 2.050475493782004, "percentage": 68.43, "elapsed_time": "10:25:22", "remaining_time": "4:48:34"}
73
+ {"current_steps": 710, "total_steps": 1023, "loss": 0.5831, "learning_rate": 1.9408322590008207e-06, "epoch": 2.0797366495976592, "percentage": 69.4, "elapsed_time": "10:34:07", "remaining_time": "4:39:33"}
74
+ {"current_steps": 720, "total_steps": 1023, "loss": 0.5841, "learning_rate": 1.8865067637918055e-06, "epoch": 2.108997805413314, "percentage": 70.38, "elapsed_time": "10:42:52", "remaining_time": "4:30:32"}
75
+ {"current_steps": 730, "total_steps": 1023, "loss": 0.5857, "learning_rate": 1.8333467651099898e-06, "epoch": 2.1382589612289684, "percentage": 71.36, "elapsed_time": "10:51:38", "remaining_time": "4:21:32"}
76
+ {"current_steps": 740, "total_steps": 1023, "loss": 0.5906, "learning_rate": 1.7814079056767086e-06, "epoch": 2.1675201170446234, "percentage": 72.34, "elapsed_time": "11:00:23", "remaining_time": "4:12:33"}
77
+ {"current_steps": 750, "total_steps": 1023, "loss": 0.5893, "learning_rate": 1.7307445500433817e-06, "epoch": 2.196781272860278, "percentage": 73.31, "elapsed_time": "11:09:08", "remaining_time": "4:03:34"}
78
+ {"current_steps": 760, "total_steps": 1023, "loss": 0.5865, "learning_rate": 1.681409727687987e-06, "epoch": 2.2260424286759326, "percentage": 74.29, "elapsed_time": "11:17:53", "remaining_time": "3:54:35"}
79
+ {"current_steps": 770, "total_steps": 1023, "loss": 0.5848, "learning_rate": 1.6334550775089513e-06, "epoch": 2.255303584491587, "percentage": 75.27, "elapsed_time": "11:26:39", "remaining_time": "3:45:36"}
80
+ {"current_steps": 780, "total_steps": 1023, "loss": 0.5842, "learning_rate": 1.5869307937745748e-06, "epoch": 2.284564740307242, "percentage": 76.25, "elapsed_time": "11:35:24", "remaining_time": "3:36:38"}
81
+ {"current_steps": 790, "total_steps": 1023, "loss": 0.5822, "learning_rate": 1.5418855735845411e-06, "epoch": 2.313825896122897, "percentage": 77.22, "elapsed_time": "11:44:10", "remaining_time": "3:27:41"}
82
+ {"current_steps": 800, "total_steps": 1023, "loss": 0.5899, "learning_rate": 1.498366565898533e-06, "epoch": 2.3430870519385514, "percentage": 78.2, "elapsed_time": "11:52:55", "remaining_time": "3:18:43"}
83
+ {"current_steps": 810, "total_steps": 1023, "loss": 0.5849, "learning_rate": 1.456419322185274e-06, "epoch": 2.3723482077542064, "percentage": 79.18, "elapsed_time": "12:01:40", "remaining_time": "3:09:46"}
84
+ {"current_steps": 820, "total_steps": 1023, "loss": 0.5911, "learning_rate": 1.4160877487436847e-06, "epoch": 2.401609363569861, "percentage": 80.16, "elapsed_time": "12:10:25", "remaining_time": "3:00:49"}
85
+ {"current_steps": 830, "total_steps": 1023, "loss": 0.5834, "learning_rate": 1.377414060746029e-06, "epoch": 2.4308705193855156, "percentage": 81.13, "elapsed_time": "12:19:10", "remaining_time": "2:51:52"}
86
+ {"current_steps": 840, "total_steps": 1023, "loss": 0.5837, "learning_rate": 1.340438738051179e-06, "epoch": 2.4601316752011706, "percentage": 82.11, "elapsed_time": "12:27:55", "remaining_time": "2:42:56"}
87
+ {"current_steps": 850, "total_steps": 1023, "loss": 0.5855, "learning_rate": 1.305200482834227e-06, "epoch": 2.489392831016825, "percentage": 83.09, "elapsed_time": "12:36:39", "remaining_time": "2:34:00"}
88
+ {"current_steps": 860, "total_steps": 1023, "loss": 0.5787, "learning_rate": 1.2717361790768135e-06, "epoch": 2.5186539868324798, "percentage": 84.07, "elapsed_time": "12:45:24", "remaining_time": "2:25:04"}
89
+ {"current_steps": 870, "total_steps": 1023, "loss": 0.581, "learning_rate": 1.2400808539605547e-06, "epoch": 2.547915142648135, "percentage": 85.04, "elapsed_time": "12:54:09", "remaining_time": "2:16:08"}
90
+ {"current_steps": 880, "total_steps": 1023, "loss": 0.585, "learning_rate": 1.2102676412039964e-06, "epoch": 2.5771762984637894, "percentage": 86.02, "elapsed_time": "13:02:55", "remaining_time": "2:07:13"}
91
+ {"current_steps": 890, "total_steps": 1023, "loss": 0.5844, "learning_rate": 1.1823277463814542e-06, "epoch": 2.606437454279444, "percentage": 87.0, "elapsed_time": "13:11:39", "remaining_time": "1:58:18"}
92
+ {"current_steps": 900, "total_steps": 1023, "loss": 0.589, "learning_rate": 1.156290414260051e-06, "epoch": 2.6356986100950985, "percentage": 87.98, "elapsed_time": "13:20:25", "remaining_time": "1:49:23"}
93
+ {"current_steps": 910, "total_steps": 1023, "loss": 0.5892, "learning_rate": 1.1321828981891369e-06, "epoch": 2.6649597659107536, "percentage": 88.95, "elapsed_time": "13:29:10", "remaining_time": "1:40:28"}
94
+ {"current_steps": 920, "total_steps": 1023, "loss": 0.5833, "learning_rate": 1.1100304315741299e-06, "epoch": 2.694220921726408, "percentage": 89.93, "elapsed_time": "13:37:54", "remaining_time": "1:31:34"}
95
+ {"current_steps": 930, "total_steps": 1023, "loss": 0.5867, "learning_rate": 1.0898562014646412e-06, "epoch": 2.723482077542063, "percentage": 90.91, "elapsed_time": "13:46:39", "remaining_time": "1:22:39"}
96
+ {"current_steps": 940, "total_steps": 1023, "loss": 0.5857, "learning_rate": 1.0716813242845214e-06, "epoch": 2.7527432333577178, "percentage": 91.89, "elapsed_time": "13:55:22", "remaining_time": "1:13:45"}
97
+ {"current_steps": 950, "total_steps": 1023, "loss": 0.5844, "learning_rate": 1.0555248237292427e-06, "epoch": 2.7820043891733723, "percentage": 92.86, "elapsed_time": "14:04:06", "remaining_time": "1:04:51"}
98
+ {"current_steps": 960, "total_steps": 1023, "loss": 0.5882, "learning_rate": 1.041403610853742e-06, "epoch": 2.811265544989027, "percentage": 93.84, "elapsed_time": "14:12:50", "remaining_time": "0:55:58"}
99
+ {"current_steps": 970, "total_steps": 1023, "loss": 0.5839, "learning_rate": 1.0293324663715703e-06, "epoch": 2.840526700804682, "percentage": 94.82, "elapsed_time": "14:21:34", "remaining_time": "0:47:04"}
100
+ {"current_steps": 980, "total_steps": 1023, "loss": 0.5838, "learning_rate": 1.0193240251838808e-06, "epoch": 2.8697878566203365, "percentage": 95.8, "elapsed_time": "14:30:18", "remaining_time": "0:38:11"}
101
+ {"current_steps": 990, "total_steps": 1023, "loss": 0.5765, "learning_rate": 1.0113887631544393e-06, "epoch": 2.899049012435991, "percentage": 96.77, "elapsed_time": "14:39:03", "remaining_time": "0:29:18"}
102
+ {"current_steps": 1000, "total_steps": 1023, "loss": 0.5844, "learning_rate": 1.0055349861445087e-06, "epoch": 2.928310168251646, "percentage": 97.75, "elapsed_time": "14:47:47", "remaining_time": "0:20:25"}
103
+ {"current_steps": 1010, "total_steps": 1023, "loss": 0.5758, "learning_rate": 1.0017688213190817e-06, "epoch": 2.9575713240673007, "percentage": 98.73, "elapsed_time": "14:56:31", "remaining_time": "0:11:32"}
104
+ {"current_steps": 1020, "total_steps": 1023, "loss": 0.5878, "learning_rate": 1.000094210733559e-06, "epoch": 2.9868324798829553, "percentage": 99.71, "elapsed_time": "15:05:14", "remaining_time": "0:02:39"}