Hugging Face's logo

mlfoundations-dev
/
hp_ablations_qwen_adambeta2_0.999_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
2454481
·
verified ·
1 Parent(s): ed27ef4

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:fc353c4eebdb2b4a2f9fc885deb363bf06eb4568e4e22bd02362b83ae16a7a4d
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7922ebc30399eb9bfdd641e8ac6f31251cc9868afb657ee40a78fa8f778f9862
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:d6a54fe114690478c32eee22793954cae10f9b74971eeedfb6bcf0c0b4ffff3a
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f50b070c9c1f71b6ef18111b808c63fc964704f4a72da67e4384e25c538736c2
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:a08165934ba590ca10ee3423a2f0e7bf831c5d3abb14e3b7e3d8f71ce40c2b27
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33c54939b86adb60cf7ef312770c1188784b820ae4db1cb847c0baf9020daf96
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:e47ffdca08244c77085c9ad6d3ef3715083bea83f4d3f0b48fa4b485bfe32061
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3732a129e3dddde51340442dbf4bc92e94d8efa4863460b8ca8fa3abe050a530
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": "9:51:05", "remaining_time": "5:11:25"}
69
  {"current_steps": 680, "total_steps": 1023, "loss": 0.6098, "learning_rate": 5e-06, "epoch": 1.9908558888076078, "percentage": 66.47, "elapsed_time": "9:59:49", "remaining_time": "5:02:33"}
70
  {"current_steps": 682, "total_steps": 1023, "eval_loss": 0.6332319378852844, "epoch": 1.9967081199707388, "percentage": 66.67, "elapsed_time": "10:07:54", "remaining_time": "5:03:57"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  {"current_steps": 670, "total_steps": 1023, "loss": 0.5953, "learning_rate": 5e-06, "epoch": 1.9615947329919532, "percentage": 65.49, "elapsed_time": "9:51:05", "remaining_time": "5:11:25"}
69
  {"current_steps": 680, "total_steps": 1023, "loss": 0.6098, "learning_rate": 5e-06, "epoch": 1.9908558888076078, "percentage": 66.47, "elapsed_time": "9:59:49", "remaining_time": "5:02:33"}
70
  {"current_steps": 682, "total_steps": 1023, "eval_loss": 0.6332319378852844, "epoch": 1.9967081199707388, "percentage": 66.67, "elapsed_time": "10:07:54", "remaining_time": "5:03:57"}
71
+ {"current_steps": 690, "total_steps": 1023, "loss": 0.6197, "learning_rate": 5e-06, "epoch": 2.0212143379663496, "percentage": 67.45, "elapsed_time": "10:15:24", "remaining_time": "4:57:00"}
72
+ {"current_steps": 700, "total_steps": 1023, "loss": 0.5674, "learning_rate": 5e-06, "epoch": 2.050475493782004, "percentage": 68.43, "elapsed_time": "10:24:09", "remaining_time": "4:48:00"}
73
+ {"current_steps": 710, "total_steps": 1023, "loss": 0.5695, "learning_rate": 5e-06, "epoch": 2.0797366495976592, "percentage": 69.4, "elapsed_time": "10:32:53", "remaining_time": "4:39:00"}
74
+ {"current_steps": 720, "total_steps": 1023, "loss": 0.5705, "learning_rate": 5e-06, "epoch": 2.108997805413314, "percentage": 70.38, "elapsed_time": "10:41:36", "remaining_time": "4:30:00"}
75
+ {"current_steps": 730, "total_steps": 1023, "loss": 0.5724, "learning_rate": 5e-06, "epoch": 2.1382589612289684, "percentage": 71.36, "elapsed_time": "10:50:17", "remaining_time": "4:21:00"}
76
+ {"current_steps": 740, "total_steps": 1023, "loss": 0.5776, "learning_rate": 5e-06, "epoch": 2.1675201170446234, "percentage": 72.34, "elapsed_time": "10:59:01", "remaining_time": "4:12:02"}
77
+ {"current_steps": 750, "total_steps": 1023, "loss": 0.5763, "learning_rate": 5e-06, "epoch": 2.196781272860278, "percentage": 73.31, "elapsed_time": "11:07:43", "remaining_time": "4:03:03"}
78
+ {"current_steps": 760, "total_steps": 1023, "loss": 0.5738, "learning_rate": 5e-06, "epoch": 2.2260424286759326, "percentage": 74.29, "elapsed_time": "11:16:27", "remaining_time": "3:54:05"}
79
+ {"current_steps": 770, "total_steps": 1023, "loss": 0.5726, "learning_rate": 5e-06, "epoch": 2.255303584491587, "percentage": 75.27, "elapsed_time": "11:25:09", "remaining_time": "3:45:07"}
80
+ {"current_steps": 780, "total_steps": 1023, "loss": 0.5716, "learning_rate": 5e-06, "epoch": 2.284564740307242, "percentage": 76.25, "elapsed_time": "11:33:52", "remaining_time": "3:36:10"}
81
+ {"current_steps": 790, "total_steps": 1023, "loss": 0.57, "learning_rate": 5e-06, "epoch": 2.313825896122897, "percentage": 77.22, "elapsed_time": "11:42:35", "remaining_time": "3:27:13"}
82
+ {"current_steps": 800, "total_steps": 1023, "loss": 0.5777, "learning_rate": 5e-06, "epoch": 2.3430870519385514, "percentage": 78.2, "elapsed_time": "11:51:19", "remaining_time": "3:18:17"}
83
+ {"current_steps": 810, "total_steps": 1023, "loss": 0.5729, "learning_rate": 5e-06, "epoch": 2.3723482077542064, "percentage": 79.18, "elapsed_time": "12:00:03", "remaining_time": "3:09:20"}
84
+ {"current_steps": 820, "total_steps": 1023, "loss": 0.5792, "learning_rate": 5e-06, "epoch": 2.401609363569861, "percentage": 80.16, "elapsed_time": "12:08:45", "remaining_time": "3:00:24"}
85
+ {"current_steps": 830, "total_steps": 1023, "loss": 0.5715, "learning_rate": 5e-06, "epoch": 2.4308705193855156, "percentage": 81.13, "elapsed_time": "12:17:28", "remaining_time": "2:51:29"}
86
+ {"current_steps": 840, "total_steps": 1023, "loss": 0.5719, "learning_rate": 5e-06, "epoch": 2.4601316752011706, "percentage": 82.11, "elapsed_time": "12:26:11", "remaining_time": "2:42:33"}
87
+ {"current_steps": 850, "total_steps": 1023, "loss": 0.5742, "learning_rate": 5e-06, "epoch": 2.489392831016825, "percentage": 83.09, "elapsed_time": "12:34:55", "remaining_time": "2:33:38"}
88
+ {"current_steps": 860, "total_steps": 1023, "loss": 0.5672, "learning_rate": 5e-06, "epoch": 2.5186539868324798, "percentage": 84.07, "elapsed_time": "12:43:39", "remaining_time": "2:24:44"}
89
+ {"current_steps": 870, "total_steps": 1023, "loss": 0.5697, "learning_rate": 5e-06, "epoch": 2.547915142648135, "percentage": 85.04, "elapsed_time": "12:52:22", "remaining_time": "2:15:49"}
90
+ {"current_steps": 880, "total_steps": 1023, "loss": 0.5739, "learning_rate": 5e-06, "epoch": 2.5771762984637894, "percentage": 86.02, "elapsed_time": "13:01:05", "remaining_time": "2:06:55"}
91
+ {"current_steps": 890, "total_steps": 1023, "loss": 0.5732, "learning_rate": 5e-06, "epoch": 2.606437454279444, "percentage": 87.0, "elapsed_time": "13:09:49", "remaining_time": "1:58:01"}
92
+ {"current_steps": 900, "total_steps": 1023, "loss": 0.5778, "learning_rate": 5e-06, "epoch": 2.6356986100950985, "percentage": 87.98, "elapsed_time": "13:18:32", "remaining_time": "1:49:08"}
93
+ {"current_steps": 910, "total_steps": 1023, "loss": 0.5779, "learning_rate": 5e-06, "epoch": 2.6649597659107536, "percentage": 88.95, "elapsed_time": "13:27:14", "remaining_time": "1:40:14"}
94
+ {"current_steps": 920, "total_steps": 1023, "loss": 0.5723, "learning_rate": 5e-06, "epoch": 2.694220921726408, "percentage": 89.93, "elapsed_time": "13:35:58", "remaining_time": "1:31:21"}
95
+ {"current_steps": 930, "total_steps": 1023, "loss": 0.5759, "learning_rate": 5e-06, "epoch": 2.723482077542063, "percentage": 90.91, "elapsed_time": "13:44:42", "remaining_time": "1:22:28"}
96
+ {"current_steps": 940, "total_steps": 1023, "loss": 0.5749, "learning_rate": 5e-06, "epoch": 2.7527432333577178, "percentage": 91.89, "elapsed_time": "13:53:24", "remaining_time": "1:13:35"}
97
+ {"current_steps": 950, "total_steps": 1023, "loss": 0.5736, "learning_rate": 5e-06, "epoch": 2.7820043891733723, "percentage": 92.86, "elapsed_time": "14:02:08", "remaining_time": "1:04:42"}
98
+ {"current_steps": 960, "total_steps": 1023, "loss": 0.5775, "learning_rate": 5e-06, "epoch": 2.811265544989027, "percentage": 93.84, "elapsed_time": "14:10:52", "remaining_time": "0:55:50"}
99
+ {"current_steps": 970, "total_steps": 1023, "loss": 0.5732, "learning_rate": 5e-06, "epoch": 2.840526700804682, "percentage": 94.82, "elapsed_time": "14:19:36", "remaining_time": "0:46:58"}
100
+ {"current_steps": 980, "total_steps": 1023, "loss": 0.573, "learning_rate": 5e-06, "epoch": 2.8697878566203365, "percentage": 95.8, "elapsed_time": "14:28:19", "remaining_time": "0:38:06"}
101
+ {"current_steps": 990, "total_steps": 1023, "loss": 0.566, "learning_rate": 5e-06, "epoch": 2.899049012435991, "percentage": 96.77, "elapsed_time": "14:37:02", "remaining_time": "0:29:14"}
102
+ {"current_steps": 1000, "total_steps": 1023, "loss": 0.5738, "learning_rate": 5e-06, "epoch": 2.928310168251646, "percentage": 97.75, "elapsed_time": "14:45:45", "remaining_time": "0:20:22"}
103
+ {"current_steps": 1010, "total_steps": 1023, "loss": 0.5655, "learning_rate": 5e-06, "epoch": 2.9575713240673007, "percentage": 98.73, "elapsed_time": "14:54:28", "remaining_time": "0:11:30"}
104
+ {"current_steps": 1020, "total_steps": 1023, "loss": 0.5772, "learning_rate": 5e-06, "epoch": 2.9868324798829553, "percentage": 99.71, "elapsed_time": "15:03:11", "remaining_time": "0:02:39"}