Hugging Face's logo

mlfoundations-dev
/
hp_ablations_qwen_adambeta1_0.92_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
4d3fa06
·
verified ·
1 Parent(s): 9740850

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 sha256:56878b1dc9bfb97127a7ce8cdf10e21aad850d4426fdbcc4bcd753531225e495
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65062fd780a03568a639b46278c51a6c6c25c4ffcaa844c075a16c8013e89bf5
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8bb99af0eef32beefbfda9195c0f08619e06fd8a01188150791f00f3ae3e5f2f
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3695d96b4714cb4f3cbce323d1af5380692e46efc9c82eadf8a1e08437d26c18
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:e415d807a1105a30dc63ef690c43744eb9723ce4bd3594b5fc352e6617fc1e2a
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bc6f9ba65562572483e19fb81afc8ef2c9d1c5817b0a176b15bde889baf516d
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a8dfd9a78143a04fd36016879f6cd7358ecfef26edb1e77f30f6e963a59f8a9
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70085b431332d270b4c2144a43b06d4029c4272492dcbe6208e599627cca1846
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -68,3 +68,37 @@
68
  {"current_steps": 670, "total_steps": 1023, "loss": 0.5953, "learning_rate": 5e-06, "epoch": 1.9615947329919532, "percentage": 65.49, "elapsed_time": "9:52:12", "remaining_time": "5:12:00"}
69
  {"current_steps": 680, "total_steps": 1023, "loss": 0.6097, "learning_rate": 5e-06, "epoch": 1.9908558888076078, "percentage": 66.47, "elapsed_time": "10:00:56", "remaining_time": "5:03:07"}
70
  {"current_steps": 682, "total_steps": 1023, "eval_loss": 0.6332425475120544, "epoch": 1.9967081199707388, "percentage": 66.67, "elapsed_time": "10:09:02", "remaining_time": "5:04:31"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  {"current_steps": 670, "total_steps": 1023, "loss": 0.5953, "learning_rate": 5e-06, "epoch": 1.9615947329919532, "percentage": 65.49, "elapsed_time": "9:52:12", "remaining_time": "5:12:00"}
69
  {"current_steps": 680, "total_steps": 1023, "loss": 0.6097, "learning_rate": 5e-06, "epoch": 1.9908558888076078, "percentage": 66.47, "elapsed_time": "10:00:56", "remaining_time": "5:03:07"}
70
  {"current_steps": 682, "total_steps": 1023, "eval_loss": 0.6332425475120544, "epoch": 1.9967081199707388, "percentage": 66.67, "elapsed_time": "10:09:02", "remaining_time": "5:04:31"}
71
+ {"current_steps": 690, "total_steps": 1023, "loss": 0.6198, "learning_rate": 5e-06, "epoch": 2.0212143379663496, "percentage": 67.45, "elapsed_time": "10:16:33", "remaining_time": "4:57:33"}
72
+ {"current_steps": 700, "total_steps": 1023, "loss": 0.5675, "learning_rate": 5e-06, "epoch": 2.050475493782004, "percentage": 68.43, "elapsed_time": "10:25:19", "remaining_time": "4:48:32"}
73
+ {"current_steps": 710, "total_steps": 1023, "loss": 0.5694, "learning_rate": 5e-06, "epoch": 2.0797366495976592, "percentage": 69.4, "elapsed_time": "10:34:04", "remaining_time": "4:39:31"}
74
+ {"current_steps": 720, "total_steps": 1023, "loss": 0.5705, "learning_rate": 5e-06, "epoch": 2.108997805413314, "percentage": 70.38, "elapsed_time": "10:42:49", "remaining_time": "4:30:31"}
75
+ {"current_steps": 730, "total_steps": 1023, "loss": 0.5722, "learning_rate": 5e-06, "epoch": 2.1382589612289684, "percentage": 71.36, "elapsed_time": "10:51:34", "remaining_time": "4:21:31"}
76
+ {"current_steps": 740, "total_steps": 1023, "loss": 0.5775, "learning_rate": 5e-06, "epoch": 2.1675201170446234, "percentage": 72.34, "elapsed_time": "11:00:19", "remaining_time": "4:12:31"}
77
+ {"current_steps": 750, "total_steps": 1023, "loss": 0.5762, "learning_rate": 5e-06, "epoch": 2.196781272860278, "percentage": 73.31, "elapsed_time": "11:09:04", "remaining_time": "4:03:32"}
78
+ {"current_steps": 760, "total_steps": 1023, "loss": 0.5736, "learning_rate": 5e-06, "epoch": 2.2260424286759326, "percentage": 74.29, "elapsed_time": "11:17:49", "remaining_time": "3:54:33"}
79
+ {"current_steps": 770, "total_steps": 1023, "loss": 0.5725, "learning_rate": 5e-06, "epoch": 2.255303584491587, "percentage": 75.27, "elapsed_time": "11:26:34", "remaining_time": "3:45:35"}
80
+ {"current_steps": 780, "total_steps": 1023, "loss": 0.5715, "learning_rate": 5e-06, "epoch": 2.284564740307242, "percentage": 76.25, "elapsed_time": "11:35:19", "remaining_time": "3:36:37"}
81
+ {"current_steps": 790, "total_steps": 1023, "loss": 0.5698, "learning_rate": 5e-06, "epoch": 2.313825896122897, "percentage": 77.22, "elapsed_time": "11:44:02", "remaining_time": "3:27:38"}
82
+ {"current_steps": 800, "total_steps": 1023, "loss": 0.5776, "learning_rate": 5e-06, "epoch": 2.3430870519385514, "percentage": 78.2, "elapsed_time": "11:52:47", "remaining_time": "3:18:41"}
83
+ {"current_steps": 810, "total_steps": 1023, "loss": 0.5728, "learning_rate": 5e-06, "epoch": 2.3723482077542064, "percentage": 79.18, "elapsed_time": "12:01:32", "remaining_time": "3:09:44"}
84
+ {"current_steps": 820, "total_steps": 1023, "loss": 0.5791, "learning_rate": 5e-06, "epoch": 2.401609363569861, "percentage": 80.16, "elapsed_time": "12:10:17", "remaining_time": "3:00:47"}
85
+ {"current_steps": 830, "total_steps": 1023, "loss": 0.5714, "learning_rate": 5e-06, "epoch": 2.4308705193855156, "percentage": 81.13, "elapsed_time": "12:19:02", "remaining_time": "2:51:51"}
86
+ {"current_steps": 840, "total_steps": 1023, "loss": 0.5718, "learning_rate": 5e-06, "epoch": 2.4601316752011706, "percentage": 82.11, "elapsed_time": "12:27:47", "remaining_time": "2:42:54"}
87
+ {"current_steps": 850, "total_steps": 1023, "loss": 0.574, "learning_rate": 5e-06, "epoch": 2.489392831016825, "percentage": 83.09, "elapsed_time": "12:36:32", "remaining_time": "2:33:58"}
88
+ {"current_steps": 860, "total_steps": 1023, "loss": 0.5671, "learning_rate": 5e-06, "epoch": 2.5186539868324798, "percentage": 84.07, "elapsed_time": "12:45:17", "remaining_time": "2:25:03"}
89
+ {"current_steps": 870, "total_steps": 1023, "loss": 0.5695, "learning_rate": 5e-06, "epoch": 2.547915142648135, "percentage": 85.04, "elapsed_time": "12:54:01", "remaining_time": "2:16:07"}
90
+ {"current_steps": 880, "total_steps": 1023, "loss": 0.5738, "learning_rate": 5e-06, "epoch": 2.5771762984637894, "percentage": 86.02, "elapsed_time": "13:02:44", "remaining_time": "2:07:11"}
91
+ {"current_steps": 890, "total_steps": 1023, "loss": 0.5731, "learning_rate": 5e-06, "epoch": 2.606437454279444, "percentage": 87.0, "elapsed_time": "13:11:29", "remaining_time": "1:58:16"}
92
+ {"current_steps": 900, "total_steps": 1023, "loss": 0.5777, "learning_rate": 5e-06, "epoch": 2.6356986100950985, "percentage": 87.98, "elapsed_time": "13:20:14", "remaining_time": "1:49:21"}
93
+ {"current_steps": 910, "total_steps": 1023, "loss": 0.5778, "learning_rate": 5e-06, "epoch": 2.6649597659107536, "percentage": 88.95, "elapsed_time": "13:28:59", "remaining_time": "1:40:27"}
94
+ {"current_steps": 920, "total_steps": 1023, "loss": 0.5722, "learning_rate": 5e-06, "epoch": 2.694220921726408, "percentage": 89.93, "elapsed_time": "13:37:44", "remaining_time": "1:31:33"}
95
+ {"current_steps": 930, "total_steps": 1023, "loss": 0.5758, "learning_rate": 5e-06, "epoch": 2.723482077542063, "percentage": 90.91, "elapsed_time": "13:46:28", "remaining_time": "1:22:38"}
96
+ {"current_steps": 940, "total_steps": 1023, "loss": 0.5747, "learning_rate": 5e-06, "epoch": 2.7527432333577178, "percentage": 91.89, "elapsed_time": "13:55:14", "remaining_time": "1:13:44"}
97
+ {"current_steps": 950, "total_steps": 1023, "loss": 0.5734, "learning_rate": 5e-06, "epoch": 2.7820043891733723, "percentage": 92.86, "elapsed_time": "14:03:58", "remaining_time": "1:04:51"}
98
+ {"current_steps": 960, "total_steps": 1023, "loss": 0.5774, "learning_rate": 5e-06, "epoch": 2.811265544989027, "percentage": 93.84, "elapsed_time": "14:12:42", "remaining_time": "0:55:57"}
99
+ {"current_steps": 970, "total_steps": 1023, "loss": 0.5731, "learning_rate": 5e-06, "epoch": 2.840526700804682, "percentage": 94.82, "elapsed_time": "14:21:26", "remaining_time": "0:47:04"}
100
+ {"current_steps": 980, "total_steps": 1023, "loss": 0.5729, "learning_rate": 5e-06, "epoch": 2.8697878566203365, "percentage": 95.8, "elapsed_time": "14:30:09", "remaining_time": "0:38:10"}
101
+ {"current_steps": 990, "total_steps": 1023, "loss": 0.5659, "learning_rate": 5e-06, "epoch": 2.899049012435991, "percentage": 96.77, "elapsed_time": "14:38:54", "remaining_time": "0:29:17"}
102
+ {"current_steps": 1000, "total_steps": 1023, "loss": 0.5736, "learning_rate": 5e-06, "epoch": 2.928310168251646, "percentage": 97.75, "elapsed_time": "14:47:38", "remaining_time": "0:20:24"}
103
+ {"current_steps": 1010, "total_steps": 1023, "loss": 0.5654, "learning_rate": 5e-06, "epoch": 2.9575713240673007, "percentage": 98.73, "elapsed_time": "14:56:23", "remaining_time": "0:11:32"}
104
+ {"current_steps": 1020, "total_steps": 1023, "loss": 0.5772, "learning_rate": 5e-06, "epoch": 2.9868324798829553, "percentage": 99.71, "elapsed_time": "15:05:07", "remaining_time": "0:02:39"}