Hugging Face's logo

mlfoundations-dev
/
hp_ablations_qwen_adambeta2_0.995_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
6ae404d
·
verified ·
1 Parent(s): 009ef3d

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 sha256:7f023c6de2fe3cd0110908a2cf9b5e647a971a8e0114e8b9aa9e5a0bcdb71001
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f98f983319ce01be4bc04d4570eca4aff5123e304459575891c5ad228cba99a1
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:122088d26573eacc29d17e83d00f04e16a13c0c24579f1788ec88caf44e306bb
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c75c9cd4cad6b6e0b19c9981a1e94b98845496e957ec4a1e09edb33a109f8c15
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03279e69e5e7394dd6c742dda6c3498eba86f7605476e68f6c22ba50cbd02b02
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44e758ea52cea0268ed3acde8e03e5cae6192ac8a35776d8a966bc9c9dfd5785
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88aeff413bfdc02cbaf5e6c41367249bf2458199e9e0312f9b033bc3cdae10f2
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f3065d497bc72a2df4dbefa260d02c2f7ffcf42d5b57ed81f8b4b57ae89eb44
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -68,3 +68,37 @@
68
  {"current_steps": 670, "total_steps": 1023, "loss": 0.5955, "learning_rate": 5e-06, "epoch": 1.9615947329919532, "percentage": 65.49, "elapsed_time": "9:52:20", "remaining_time": "5:12:04"}
69
  {"current_steps": 680, "total_steps": 1023, "loss": 0.61, "learning_rate": 5e-06, "epoch": 1.9908558888076078, "percentage": 66.47, "elapsed_time": "10:01:04", "remaining_time": "5:03:11"}
70
  {"current_steps": 682, "total_steps": 1023, "eval_loss": 0.633293867111206, "epoch": 1.9967081199707388, "percentage": 66.67, "elapsed_time": "10:09:09", "remaining_time": "5:04:34"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  {"current_steps": 670, "total_steps": 1023, "loss": 0.5955, "learning_rate": 5e-06, "epoch": 1.9615947329919532, "percentage": 65.49, "elapsed_time": "9:52:20", "remaining_time": "5:12:04"}
69
  {"current_steps": 680, "total_steps": 1023, "loss": 0.61, "learning_rate": 5e-06, "epoch": 1.9908558888076078, "percentage": 66.47, "elapsed_time": "10:01:04", "remaining_time": "5:03:11"}
70
  {"current_steps": 682, "total_steps": 1023, "eval_loss": 0.633293867111206, "epoch": 1.9967081199707388, "percentage": 66.67, "elapsed_time": "10:09:09", "remaining_time": "5:04:34"}
71
+ {"current_steps": 690, "total_steps": 1023, "loss": 0.6203, "learning_rate": 5e-06, "epoch": 2.0212143379663496, "percentage": 67.45, "elapsed_time": "10:16:41", "remaining_time": "4:57:37"}
72
+ {"current_steps": 700, "total_steps": 1023, "loss": 0.568, "learning_rate": 5e-06, "epoch": 2.050475493782004, "percentage": 68.43, "elapsed_time": "10:25:25", "remaining_time": "4:48:35"}
73
+ {"current_steps": 710, "total_steps": 1023, "loss": 0.5701, "learning_rate": 5e-06, "epoch": 2.0797366495976592, "percentage": 69.4, "elapsed_time": "10:34:10", "remaining_time": "4:39:34"}
74
+ {"current_steps": 720, "total_steps": 1023, "loss": 0.5711, "learning_rate": 5e-06, "epoch": 2.108997805413314, "percentage": 70.38, "elapsed_time": "10:42:54", "remaining_time": "4:30:33"}
75
+ {"current_steps": 730, "total_steps": 1023, "loss": 0.573, "learning_rate": 5e-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": 0.5782, "learning_rate": 5e-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": 0.5769, "learning_rate": 5e-06, "epoch": 2.196781272860278, "percentage": 73.31, "elapsed_time": "11:09:07", "remaining_time": "4:03:33"}
78
+ {"current_steps": 760, "total_steps": 1023, "loss": 0.5744, "learning_rate": 5e-06, "epoch": 2.2260424286759326, "percentage": 74.29, "elapsed_time": "11:17:52", "remaining_time": "3:54:34"}
79
+ {"current_steps": 770, "total_steps": 1023, "loss": 0.5732, "learning_rate": 5e-06, "epoch": 2.255303584491587, "percentage": 75.27, "elapsed_time": "11:26:37", "remaining_time": "3:45:36"}
80
+ {"current_steps": 780, "total_steps": 1023, "loss": 0.5722, "learning_rate": 5e-06, "epoch": 2.284564740307242, "percentage": 76.25, "elapsed_time": "11:35:23", "remaining_time": "3:36:38"}
81
+ {"current_steps": 790, "total_steps": 1023, "loss": 0.5705, "learning_rate": 5e-06, "epoch": 2.313825896122897, "percentage": 77.22, "elapsed_time": "11:44:08", "remaining_time": "3:27:40"}
82
+ {"current_steps": 800, "total_steps": 1023, "loss": 0.5782, "learning_rate": 5e-06, "epoch": 2.3430870519385514, "percentage": 78.2, "elapsed_time": "11:52:53", "remaining_time": "3:18:43"}
83
+ {"current_steps": 810, "total_steps": 1023, "loss": 0.5735, "learning_rate": 5e-06, "epoch": 2.3723482077542064, "percentage": 79.18, "elapsed_time": "12:01:39", "remaining_time": "3:09:46"}
84
+ {"current_steps": 820, "total_steps": 1023, "loss": 0.5798, "learning_rate": 5e-06, "epoch": 2.401609363569861, "percentage": 80.16, "elapsed_time": "12:10:24", "remaining_time": "3:00:49"}
85
+ {"current_steps": 830, "total_steps": 1023, "loss": 0.5721, "learning_rate": 5e-06, "epoch": 2.4308705193855156, "percentage": 81.13, "elapsed_time": "12:19:09", "remaining_time": "2:51:52"}
86
+ {"current_steps": 840, "total_steps": 1023, "loss": 0.5725, "learning_rate": 5e-06, "epoch": 2.4601316752011706, "percentage": 82.11, "elapsed_time": "12:27:54", "remaining_time": "2:42:56"}
87
+ {"current_steps": 850, "total_steps": 1023, "loss": 0.5747, "learning_rate": 5e-06, "epoch": 2.489392831016825, "percentage": 83.09, "elapsed_time": "12:36:38", "remaining_time": "2:34:00"}
88
+ {"current_steps": 860, "total_steps": 1023, "loss": 0.5677, "learning_rate": 5e-06, "epoch": 2.5186539868324798, "percentage": 84.07, "elapsed_time": "12:45:22", "remaining_time": "2:25:04"}
89
+ {"current_steps": 870, "total_steps": 1023, "loss": 0.5702, "learning_rate": 5e-06, "epoch": 2.547915142648135, "percentage": 85.04, "elapsed_time": "12:54:08", "remaining_time": "2:16:08"}
90
+ {"current_steps": 880, "total_steps": 1023, "loss": 0.5744, "learning_rate": 5e-06, "epoch": 2.5771762984637894, "percentage": 86.02, "elapsed_time": "13:02:53", "remaining_time": "2:07:13"}
91
+ {"current_steps": 890, "total_steps": 1023, "loss": 0.5737, "learning_rate": 5e-06, "epoch": 2.606437454279444, "percentage": 87.0, "elapsed_time": "13:11:38", "remaining_time": "1:58:18"}
92
+ {"current_steps": 900, "total_steps": 1023, "loss": 0.5783, "learning_rate": 5e-06, "epoch": 2.6356986100950985, "percentage": 87.98, "elapsed_time": "13:20:24", "remaining_time": "1:49:23"}
93
+ {"current_steps": 910, "total_steps": 1023, "loss": 0.5784, "learning_rate": 5e-06, "epoch": 2.6649597659107536, "percentage": 88.95, "elapsed_time": "13:29:09", "remaining_time": "1:40:28"}
94
+ {"current_steps": 920, "total_steps": 1023, "loss": 0.5728, "learning_rate": 5e-06, "epoch": 2.694220921726408, "percentage": 89.93, "elapsed_time": "13:37:55", "remaining_time": "1:31:34"}
95
+ {"current_steps": 930, "total_steps": 1023, "loss": 0.5764, "learning_rate": 5e-06, "epoch": 2.723482077542063, "percentage": 90.91, "elapsed_time": "13:46:40", "remaining_time": "1:22:40"}
96
+ {"current_steps": 940, "total_steps": 1023, "loss": 0.5754, "learning_rate": 5e-06, "epoch": 2.7527432333577178, "percentage": 91.89, "elapsed_time": "13:55:25", "remaining_time": "1:13:45"}
97
+ {"current_steps": 950, "total_steps": 1023, "loss": 0.5741, "learning_rate": 5e-06, "epoch": 2.7820043891733723, "percentage": 92.86, "elapsed_time": "14:04:10", "remaining_time": "1:04:52"}
98
+ {"current_steps": 960, "total_steps": 1023, "loss": 0.5779, "learning_rate": 5e-06, "epoch": 2.811265544989027, "percentage": 93.84, "elapsed_time": "14:12:56", "remaining_time": "0:55:58"}
99
+ {"current_steps": 970, "total_steps": 1023, "loss": 0.5736, "learning_rate": 5e-06, "epoch": 2.840526700804682, "percentage": 94.82, "elapsed_time": "14:21:40", "remaining_time": "0:47:04"}
100
+ {"current_steps": 980, "total_steps": 1023, "loss": 0.5735, "learning_rate": 5e-06, "epoch": 2.8697878566203365, "percentage": 95.8, "elapsed_time": "14:30:26", "remaining_time": "0:38:11"}
101
+ {"current_steps": 990, "total_steps": 1023, "loss": 0.5665, "learning_rate": 5e-06, "epoch": 2.899049012435991, "percentage": 96.77, "elapsed_time": "14:39:11", "remaining_time": "0:29:18"}
102
+ {"current_steps": 1000, "total_steps": 1023, "loss": 0.5743, "learning_rate": 5e-06, "epoch": 2.928310168251646, "percentage": 97.75, "elapsed_time": "14:47:57", "remaining_time": "0:20:25"}
103
+ {"current_steps": 1010, "total_steps": 1023, "loss": 0.5661, "learning_rate": 5e-06, "epoch": 2.9575713240673007, "percentage": 98.73, "elapsed_time": "14:56:42", "remaining_time": "0:11:32"}
104
+ {"current_steps": 1020, "total_steps": 1023, "loss": 0.5777, "learning_rate": 5e-06, "epoch": 2.9868324798829553, "percentage": 99.71, "elapsed_time": "15:05:27", "remaining_time": "0:02:39"}