Hugging Face's logo

mlfoundations-dev
/
hp_ablations_qwen_adambeta1_0.9_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
83a8075
·
verified ·
1 Parent(s): 12160e3

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:f148e76f768197377f64ed31e0db0a76ce1ba2d09f8531b29e71a0284a4c93f4
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f653f9728bd831fd1fe7ef98b8ad98a23d8bd9bf491186cf990e771573fc3dd
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:b6c9dc3c762eb4432ec428007f26ac048a97322f2b9e406ff8b1bf21a2d7be61
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db29c9b9ad88b8e7299bf38ea82708898678de5089481c7d5a1234a7ee1f1822
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f20f5f8105ee238556c8b6452009bcf01cc26b981edb6794e0238c6b80d2ffd
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc6542d14534c84214c06987b01fed299a5418fe88941138915c6accb8736822
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:f672dff938d795fff4001ea74d9f94ab3082d6462dd7f94ca457678391e53994
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cec063848df2b12c7fe43390ba62e52076775e44e70635e4bbd097af68c4243b
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -68,3 +68,37 @@
68
  {"current_steps": 670, "total_steps": 1023, "loss": 0.5952, "learning_rate": 5e-06, "epoch": 1.9615947329919532, "percentage": 65.49, "elapsed_time": "9:56:30", "remaining_time": "5:14:16"}
69
  {"current_steps": 680, "total_steps": 1023, "loss": 0.6096, "learning_rate": 5e-06, "epoch": 1.9908558888076078, "percentage": 66.47, "elapsed_time": "10:05:18", "remaining_time": "5:05:19"}
70
  {"current_steps": 682, "total_steps": 1023, "eval_loss": 0.6332002878189087, "epoch": 1.9967081199707388, "percentage": 66.67, "elapsed_time": "10:13:27", "remaining_time": "5:06:43"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  {"current_steps": 670, "total_steps": 1023, "loss": 0.5952, "learning_rate": 5e-06, "epoch": 1.9615947329919532, "percentage": 65.49, "elapsed_time": "9:56:30", "remaining_time": "5:14:16"}
69
  {"current_steps": 680, "total_steps": 1023, "loss": 0.6096, "learning_rate": 5e-06, "epoch": 1.9908558888076078, "percentage": 66.47, "elapsed_time": "10:05:18", "remaining_time": "5:05:19"}
70
  {"current_steps": 682, "total_steps": 1023, "eval_loss": 0.6332002878189087, "epoch": 1.9967081199707388, "percentage": 66.67, "elapsed_time": "10:13:27", "remaining_time": "5:06:43"}
71
+ {"current_steps": 690, "total_steps": 1023, "loss": 0.6196, "learning_rate": 5e-06, "epoch": 2.0212143379663496, "percentage": 67.45, "elapsed_time": "10:21:02", "remaining_time": "4:59:43"}
72
+ {"current_steps": 700, "total_steps": 1023, "loss": 0.5673, "learning_rate": 5e-06, "epoch": 2.050475493782004, "percentage": 68.43, "elapsed_time": "10:29:52", "remaining_time": "4:50:38"}
73
+ {"current_steps": 710, "total_steps": 1023, "loss": 0.5693, "learning_rate": 5e-06, "epoch": 2.0797366495976592, "percentage": 69.4, "elapsed_time": "10:38:41", "remaining_time": "4:41:34"}
74
+ {"current_steps": 720, "total_steps": 1023, "loss": 0.5704, "learning_rate": 5e-06, "epoch": 2.108997805413314, "percentage": 70.38, "elapsed_time": "10:47:30", "remaining_time": "4:32:29"}
75
+ {"current_steps": 730, "total_steps": 1023, "loss": 0.5722, "learning_rate": 5e-06, "epoch": 2.1382589612289684, "percentage": 71.36, "elapsed_time": "10:56:20", "remaining_time": "4:23:26"}
76
+ {"current_steps": 740, "total_steps": 1023, "loss": 0.5775, "learning_rate": 5e-06, "epoch": 2.1675201170446234, "percentage": 72.34, "elapsed_time": "11:05:08", "remaining_time": "4:14:22"}
77
+ {"current_steps": 750, "total_steps": 1023, "loss": 0.5761, "learning_rate": 5e-06, "epoch": 2.196781272860278, "percentage": 73.31, "elapsed_time": "11:13:57", "remaining_time": "4:05:19"}
78
+ {"current_steps": 760, "total_steps": 1023, "loss": 0.5736, "learning_rate": 5e-06, "epoch": 2.2260424286759326, "percentage": 74.29, "elapsed_time": "11:22:48", "remaining_time": "3:56:17"}
79
+ {"current_steps": 770, "total_steps": 1023, "loss": 0.5724, "learning_rate": 5e-06, "epoch": 2.255303584491587, "percentage": 75.27, "elapsed_time": "11:31:37", "remaining_time": "3:47:15"}
80
+ {"current_steps": 780, "total_steps": 1023, "loss": 0.5715, "learning_rate": 5e-06, "epoch": 2.284564740307242, "percentage": 76.25, "elapsed_time": "11:40:27", "remaining_time": "3:38:13"}
81
+ {"current_steps": 790, "total_steps": 1023, "loss": 0.5698, "learning_rate": 5e-06, "epoch": 2.313825896122897, "percentage": 77.22, "elapsed_time": "11:49:17", "remaining_time": "3:29:11"}
82
+ {"current_steps": 800, "total_steps": 1023, "loss": 0.5776, "learning_rate": 5e-06, "epoch": 2.3430870519385514, "percentage": 78.2, "elapsed_time": "11:58:06", "remaining_time": "3:20:10"}
83
+ {"current_steps": 810, "total_steps": 1023, "loss": 0.5728, "learning_rate": 5e-06, "epoch": 2.3723482077542064, "percentage": 79.18, "elapsed_time": "12:06:56", "remaining_time": "3:11:09"}
84
+ {"current_steps": 820, "total_steps": 1023, "loss": 0.5791, "learning_rate": 5e-06, "epoch": 2.401609363569861, "percentage": 80.16, "elapsed_time": "12:15:46", "remaining_time": "3:02:08"}
85
+ {"current_steps": 830, "total_steps": 1023, "loss": 0.5713, "learning_rate": 5e-06, "epoch": 2.4308705193855156, "percentage": 81.13, "elapsed_time": "12:24:35", "remaining_time": "2:53:08"}
86
+ {"current_steps": 840, "total_steps": 1023, "loss": 0.5718, "learning_rate": 5e-06, "epoch": 2.4601316752011706, "percentage": 82.11, "elapsed_time": "12:33:25", "remaining_time": "2:44:08"}
87
+ {"current_steps": 850, "total_steps": 1023, "loss": 0.574, "learning_rate": 5e-06, "epoch": 2.489392831016825, "percentage": 83.09, "elapsed_time": "12:42:14", "remaining_time": "2:35:08"}
88
+ {"current_steps": 860, "total_steps": 1023, "loss": 0.5671, "learning_rate": 5e-06, "epoch": 2.5186539868324798, "percentage": 84.07, "elapsed_time": "12:51:04", "remaining_time": "2:26:08"}
89
+ {"current_steps": 870, "total_steps": 1023, "loss": 0.5695, "learning_rate": 5e-06, "epoch": 2.547915142648135, "percentage": 85.04, "elapsed_time": "12:59:52", "remaining_time": "2:17:09"}
90
+ {"current_steps": 880, "total_steps": 1023, "loss": 0.5737, "learning_rate": 5e-06, "epoch": 2.5771762984637894, "percentage": 86.02, "elapsed_time": "13:08:41", "remaining_time": "2:08:09"}
91
+ {"current_steps": 890, "total_steps": 1023, "loss": 0.573, "learning_rate": 5e-06, "epoch": 2.606437454279444, "percentage": 87.0, "elapsed_time": "13:17:28", "remaining_time": "1:59:10"}
92
+ {"current_steps": 900, "total_steps": 1023, "loss": 0.5776, "learning_rate": 5e-06, "epoch": 2.6356986100950985, "percentage": 87.98, "elapsed_time": "13:26:17", "remaining_time": "1:50:11"}
93
+ {"current_steps": 910, "total_steps": 1023, "loss": 0.5778, "learning_rate": 5e-06, "epoch": 2.6649597659107536, "percentage": 88.95, "elapsed_time": "13:35:05", "remaining_time": "1:41:12"}
94
+ {"current_steps": 920, "total_steps": 1023, "loss": 0.5721, "learning_rate": 5e-06, "epoch": 2.694220921726408, "percentage": 89.93, "elapsed_time": "13:43:52", "remaining_time": "1:32:14"}
95
+ {"current_steps": 930, "total_steps": 1023, "loss": 0.5758, "learning_rate": 5e-06, "epoch": 2.723482077542063, "percentage": 90.91, "elapsed_time": "13:52:41", "remaining_time": "1:23:16"}
96
+ {"current_steps": 940, "total_steps": 1023, "loss": 0.5747, "learning_rate": 5e-06, "epoch": 2.7527432333577178, "percentage": 91.89, "elapsed_time": "14:01:31", "remaining_time": "1:14:18"}
97
+ {"current_steps": 950, "total_steps": 1023, "loss": 0.5735, "learning_rate": 5e-06, "epoch": 2.7820043891733723, "percentage": 92.86, "elapsed_time": "14:10:19", "remaining_time": "1:05:20"}
98
+ {"current_steps": 960, "total_steps": 1023, "loss": 0.5773, "learning_rate": 5e-06, "epoch": 2.811265544989027, "percentage": 93.84, "elapsed_time": "14:19:09", "remaining_time": "0:56:22"}
99
+ {"current_steps": 970, "total_steps": 1023, "loss": 0.573, "learning_rate": 5e-06, "epoch": 2.840526700804682, "percentage": 94.82, "elapsed_time": "14:27:58", "remaining_time": "0:47:25"}
100
+ {"current_steps": 980, "total_steps": 1023, "loss": 0.5729, "learning_rate": 5e-06, "epoch": 2.8697878566203365, "percentage": 95.8, "elapsed_time": "14:36:46", "remaining_time": "0:38:28"}
101
+ {"current_steps": 990, "total_steps": 1023, "loss": 0.5658, "learning_rate": 5e-06, "epoch": 2.899049012435991, "percentage": 96.77, "elapsed_time": "14:45:32", "remaining_time": "0:29:31"}
102
+ {"current_steps": 1000, "total_steps": 1023, "loss": 0.5736, "learning_rate": 5e-06, "epoch": 2.928310168251646, "percentage": 97.75, "elapsed_time": "14:54:21", "remaining_time": "0:20:34"}
103
+ {"current_steps": 1010, "total_steps": 1023, "loss": 0.5654, "learning_rate": 5e-06, "epoch": 2.9575713240673007, "percentage": 98.73, "elapsed_time": "15:03:08", "remaining_time": "0:11:37"}
104
+ {"current_steps": 1020, "total_steps": 1023, "loss": 0.5771, "learning_rate": 5e-06, "epoch": 2.9868324798829553, "percentage": 99.71, "elapsed_time": "15:11:55", "remaining_time": "0:02:40"}