Hugging Face's logo

mlfoundations-dev
/
hp_ablations_qwen_adambeta1_0.95_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
6e82ff8
·
verified ·
1 Parent(s): 53132fd

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:e77a030722e822954228415c1617deccd8843841bed950ebfd889f4390099878
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c796492eea5b22f8139ecb990338525ca3e496b885b37ca96e54c8c139f89372
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:a87e91ac482d9edb69269a5779e712b54e7fc738d3485d304544f137f9f9d59a
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:831cb6ab84c4f8c155dc956aca44ba2e62247e7f4e83fb308f0510304ebca550
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a7d9ca3047790bb777293115c3b717d30a7464bbe34037a460d0c41ebc06a8d
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eebc9f99eefab3f8713a225936eb838050894d4ae0ec126fb1b6ec53bdb0f9a2
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d2daef47ddbb31db66799d65c5a9fd2eb19b5a07b03de504c02156c345d3e87
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f68b50dd8b4e6c9f4f6f84615bac6458cc4add18570b61e43313934a3b3dcdaa
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -68,3 +68,37 @@
68
  {"current_steps": 670, "total_steps": 1023, "loss": 0.595, "learning_rate": 5e-06, "epoch": 1.9615947329919532, "percentage": 65.49, "elapsed_time": "9:53:11", "remaining_time": "5:12:32"}
69
  {"current_steps": 680, "total_steps": 1023, "loss": 0.6094, "learning_rate": 5e-06, "epoch": 1.9908558888076078, "percentage": 66.47, "elapsed_time": "10:01:57", "remaining_time": "5:03:38"}
70
  {"current_steps": 682, "total_steps": 1023, "eval_loss": 0.6333937644958496, "epoch": 1.9967081199707388, "percentage": 66.67, "elapsed_time": "10:10:05", "remaining_time": "5:05:02"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  {"current_steps": 670, "total_steps": 1023, "loss": 0.595, "learning_rate": 5e-06, "epoch": 1.9615947329919532, "percentage": 65.49, "elapsed_time": "9:53:11", "remaining_time": "5:12:32"}
69
  {"current_steps": 680, "total_steps": 1023, "loss": 0.6094, "learning_rate": 5e-06, "epoch": 1.9908558888076078, "percentage": 66.47, "elapsed_time": "10:01:57", "remaining_time": "5:03:38"}
70
  {"current_steps": 682, "total_steps": 1023, "eval_loss": 0.6333937644958496, "epoch": 1.9967081199707388, "percentage": 66.67, "elapsed_time": "10:10:05", "remaining_time": "5:05:02"}
71
+ {"current_steps": 690, "total_steps": 1023, "loss": 0.6198, "learning_rate": 5e-06, "epoch": 2.0212143379663496, "percentage": 67.45, "elapsed_time": "10:17:37", "remaining_time": "4:58:04"}
72
+ {"current_steps": 700, "total_steps": 1023, "loss": 0.5674, "learning_rate": 5e-06, "epoch": 2.050475493782004, "percentage": 68.43, "elapsed_time": "10:26:21", "remaining_time": "4:49:01"}
73
+ {"current_steps": 710, "total_steps": 1023, "loss": 0.5693, "learning_rate": 5e-06, "epoch": 2.0797366495976592, "percentage": 69.4, "elapsed_time": "10:35:07", "remaining_time": "4:39:59"}
74
+ {"current_steps": 720, "total_steps": 1023, "loss": 0.5701, "learning_rate": 5e-06, "epoch": 2.108997805413314, "percentage": 70.38, "elapsed_time": "10:43:52", "remaining_time": "4:30:57"}
75
+ {"current_steps": 730, "total_steps": 1023, "loss": 0.5718, "learning_rate": 5e-06, "epoch": 2.1382589612289684, "percentage": 71.36, "elapsed_time": "10:52:37", "remaining_time": "4:21:56"}
76
+ {"current_steps": 740, "total_steps": 1023, "loss": 0.5769, "learning_rate": 5e-06, "epoch": 2.1675201170446234, "percentage": 72.34, "elapsed_time": "11:01:22", "remaining_time": "4:12:55"}
77
+ {"current_steps": 750, "total_steps": 1023, "loss": 0.5755, "learning_rate": 5e-06, "epoch": 2.196781272860278, "percentage": 73.31, "elapsed_time": "11:10:07", "remaining_time": "4:03:55"}
78
+ {"current_steps": 760, "total_steps": 1023, "loss": 0.573, "learning_rate": 5e-06, "epoch": 2.2260424286759326, "percentage": 74.29, "elapsed_time": "11:18:52", "remaining_time": "3:54:55"}
79
+ {"current_steps": 770, "total_steps": 1023, "loss": 0.5718, "learning_rate": 5e-06, "epoch": 2.255303584491587, "percentage": 75.27, "elapsed_time": "11:27:38", "remaining_time": "3:45:56"}
80
+ {"current_steps": 780, "total_steps": 1023, "loss": 0.5709, "learning_rate": 5e-06, "epoch": 2.284564740307242, "percentage": 76.25, "elapsed_time": "11:36:23", "remaining_time": "3:36:57"}
81
+ {"current_steps": 790, "total_steps": 1023, "loss": 0.5691, "learning_rate": 5e-06, "epoch": 2.313825896122897, "percentage": 77.22, "elapsed_time": "11:45:08", "remaining_time": "3:27:58"}
82
+ {"current_steps": 800, "total_steps": 1023, "loss": 0.577, "learning_rate": 5e-06, "epoch": 2.3430870519385514, "percentage": 78.2, "elapsed_time": "11:53:53", "remaining_time": "3:18:59"}
83
+ {"current_steps": 810, "total_steps": 1023, "loss": 0.5722, "learning_rate": 5e-06, "epoch": 2.3723482077542064, "percentage": 79.18, "elapsed_time": "12:02:38", "remaining_time": "3:10:01"}
84
+ {"current_steps": 820, "total_steps": 1023, "loss": 0.5785, "learning_rate": 5e-06, "epoch": 2.401609363569861, "percentage": 80.16, "elapsed_time": "12:11:23", "remaining_time": "3:01:03"}
85
+ {"current_steps": 830, "total_steps": 1023, "loss": 0.5708, "learning_rate": 5e-06, "epoch": 2.4308705193855156, "percentage": 81.13, "elapsed_time": "12:20:07", "remaining_time": "2:52:06"}
86
+ {"current_steps": 840, "total_steps": 1023, "loss": 0.5713, "learning_rate": 5e-06, "epoch": 2.4601316752011706, "percentage": 82.11, "elapsed_time": "12:28:52", "remaining_time": "2:43:08"}
87
+ {"current_steps": 850, "total_steps": 1023, "loss": 0.5735, "learning_rate": 5e-06, "epoch": 2.489392831016825, "percentage": 83.09, "elapsed_time": "12:37:37", "remaining_time": "2:34:11"}
88
+ {"current_steps": 860, "total_steps": 1023, "loss": 0.5666, "learning_rate": 5e-06, "epoch": 2.5186539868324798, "percentage": 84.07, "elapsed_time": "12:46:23", "remaining_time": "2:25:15"}
89
+ {"current_steps": 870, "total_steps": 1023, "loss": 0.569, "learning_rate": 5e-06, "epoch": 2.547915142648135, "percentage": 85.04, "elapsed_time": "12:55:09", "remaining_time": "2:16:19"}
90
+ {"current_steps": 880, "total_steps": 1023, "loss": 0.5732, "learning_rate": 5e-06, "epoch": 2.5771762984637894, "percentage": 86.02, "elapsed_time": "13:03:55", "remaining_time": "2:07:23"}
91
+ {"current_steps": 890, "total_steps": 1023, "loss": 0.5725, "learning_rate": 5e-06, "epoch": 2.606437454279444, "percentage": 87.0, "elapsed_time": "13:12:41", "remaining_time": "1:58:27"}
92
+ {"current_steps": 900, "total_steps": 1023, "loss": 0.5772, "learning_rate": 5e-06, "epoch": 2.6356986100950985, "percentage": 87.98, "elapsed_time": "13:21:27", "remaining_time": "1:49:31"}
93
+ {"current_steps": 910, "total_steps": 1023, "loss": 0.5773, "learning_rate": 5e-06, "epoch": 2.6649597659107536, "percentage": 88.95, "elapsed_time": "13:30:12", "remaining_time": "1:40:36"}
94
+ {"current_steps": 920, "total_steps": 1023, "loss": 0.5717, "learning_rate": 5e-06, "epoch": 2.694220921726408, "percentage": 89.93, "elapsed_time": "13:38:58", "remaining_time": "1:31:41"}
95
+ {"current_steps": 930, "total_steps": 1023, "loss": 0.5753, "learning_rate": 5e-06, "epoch": 2.723482077542063, "percentage": 90.91, "elapsed_time": "13:47:44", "remaining_time": "1:22:46"}
96
+ {"current_steps": 940, "total_steps": 1023, "loss": 0.5744, "learning_rate": 5e-06, "epoch": 2.7527432333577178, "percentage": 91.89, "elapsed_time": "13:56:31", "remaining_time": "1:13:51"}
97
+ {"current_steps": 950, "total_steps": 1023, "loss": 0.5731, "learning_rate": 5e-06, "epoch": 2.7820043891733723, "percentage": 92.86, "elapsed_time": "14:05:17", "remaining_time": "1:04:57"}
98
+ {"current_steps": 960, "total_steps": 1023, "loss": 0.5769, "learning_rate": 5e-06, "epoch": 2.811265544989027, "percentage": 93.84, "elapsed_time": "14:14:04", "remaining_time": "0:56:02"}
99
+ {"current_steps": 970, "total_steps": 1023, "loss": 0.5726, "learning_rate": 5e-06, "epoch": 2.840526700804682, "percentage": 94.82, "elapsed_time": "14:22:50", "remaining_time": "0:47:08"}
100
+ {"current_steps": 980, "total_steps": 1023, "loss": 0.5724, "learning_rate": 5e-06, "epoch": 2.8697878566203365, "percentage": 95.8, "elapsed_time": "14:31:35", "remaining_time": "0:38:14"}
101
+ {"current_steps": 990, "total_steps": 1023, "loss": 0.5655, "learning_rate": 5e-06, "epoch": 2.899049012435991, "percentage": 96.77, "elapsed_time": "14:40:22", "remaining_time": "0:29:20"}
102
+ {"current_steps": 1000, "total_steps": 1023, "loss": 0.5732, "learning_rate": 5e-06, "epoch": 2.928310168251646, "percentage": 97.75, "elapsed_time": "14:49:09", "remaining_time": "0:20:27"}
103
+ {"current_steps": 1010, "total_steps": 1023, "loss": 0.565, "learning_rate": 5e-06, "epoch": 2.9575713240673007, "percentage": 98.73, "elapsed_time": "14:57:55", "remaining_time": "0:11:33"}
104
+ {"current_steps": 1020, "total_steps": 1023, "loss": 0.5767, "learning_rate": 5e-06, "epoch": 2.9868324798829553, "percentage": 99.71, "elapsed_time": "15:06:41", "remaining_time": "0:02:40"}