sedrickkeh commited on
Commit
512ff31
·
verified ·
1 Parent(s): 25dc355

Training in progress, epoch 2

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:942a6aabb2739dd624b0afd1e5c4245c5fb5230d51b294bbb363d549cc735b83
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ec8a5759a7651bf81ff1ac40361a51128c94c55bd613a22eb764632b51258f9
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca39d99a0ed094672c67fc987dd39ea57f9de75fac860d351618e7118df60653
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acb82f14f2c468aee1998fa48ba5162e73e4c06f78e7e1f2a59e42b4ab9e4a68
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a2f2b93f8ea74be948a732eef86b4aff4d1e812615547d973b02c3c203a00f9
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9abb16c61991c4969b08ed2e83f47de2c2a589b4abbd4a00ba88b9fc82edec
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5dbfe2f75425b62fb6a902946f58cd8151699f92ab0d768fb7835ecb58a449a
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c23c7a02197e796555e28efc6d9caeddd812e56ae2080cda249e8b76eba03f0
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -69,3 +69,37 @@
69
  {"current_steps": 680, "total_steps": 1035, "loss": 0.7277, "lr": 5e-06, "epoch": 1.9695872556118754, "percentage": 65.7, "elapsed_time": "6:09:51", "remaining_time": "3:13:05"}
70
  {"current_steps": 690, "total_steps": 1035, "loss": 0.72, "lr": 5e-06, "epoch": 1.998551774076756, "percentage": 66.67, "elapsed_time": "6:15:14", "remaining_time": "3:07:37"}
71
  {"current_steps": 690, "total_steps": 1035, "eval_loss": 0.7591201663017273, "epoch": 1.998551774076756, "percentage": 66.67, "elapsed_time": "6:19:27", "remaining_time": "3:09:43"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  {"current_steps": 680, "total_steps": 1035, "loss": 0.7277, "lr": 5e-06, "epoch": 1.9695872556118754, "percentage": 65.7, "elapsed_time": "6:09:51", "remaining_time": "3:13:05"}
70
  {"current_steps": 690, "total_steps": 1035, "loss": 0.72, "lr": 5e-06, "epoch": 1.998551774076756, "percentage": 66.67, "elapsed_time": "6:15:14", "remaining_time": "3:07:37"}
71
  {"current_steps": 690, "total_steps": 1035, "eval_loss": 0.7591201663017273, "epoch": 1.998551774076756, "percentage": 66.67, "elapsed_time": "6:19:27", "remaining_time": "3:09:43"}
72
+ {"current_steps": 700, "total_steps": 1035, "loss": 0.7321, "lr": 5e-06, "epoch": 2.0275162925416366, "percentage": 67.63, "elapsed_time": "6:25:54", "remaining_time": "3:04:41"}
73
+ {"current_steps": 710, "total_steps": 1035, "loss": 0.6723, "lr": 5e-06, "epoch": 2.056480811006517, "percentage": 68.6, "elapsed_time": "6:31:14", "remaining_time": "2:59:05"}
74
+ {"current_steps": 720, "total_steps": 1035, "loss": 0.6804, "lr": 5e-06, "epoch": 2.0854453294713977, "percentage": 69.57, "elapsed_time": "6:36:36", "remaining_time": "2:53:30"}
75
+ {"current_steps": 730, "total_steps": 1035, "loss": 0.6797, "lr": 5e-06, "epoch": 2.114409847936278, "percentage": 70.53, "elapsed_time": "6:41:58", "remaining_time": "2:47:56"}
76
+ {"current_steps": 740, "total_steps": 1035, "loss": 0.6733, "lr": 5e-06, "epoch": 2.1433743664011584, "percentage": 71.5, "elapsed_time": "6:47:19", "remaining_time": "2:42:22"}
77
+ {"current_steps": 750, "total_steps": 1035, "loss": 0.6807, "lr": 5e-06, "epoch": 2.172338884866039, "percentage": 72.46, "elapsed_time": "6:52:37", "remaining_time": "2:36:48"}
78
+ {"current_steps": 760, "total_steps": 1035, "loss": 0.6836, "lr": 5e-06, "epoch": 2.2013034033309196, "percentage": 73.43, "elapsed_time": "6:57:57", "remaining_time": "2:31:13"}
79
+ {"current_steps": 770, "total_steps": 1035, "loss": 0.6782, "lr": 5e-06, "epoch": 2.2302679217958, "percentage": 74.4, "elapsed_time": "7:03:18", "remaining_time": "2:25:41"}
80
+ {"current_steps": 780, "total_steps": 1035, "loss": 0.6792, "lr": 5e-06, "epoch": 2.2592324402606807, "percentage": 75.36, "elapsed_time": "7:08:41", "remaining_time": "2:20:08"}
81
+ {"current_steps": 790, "total_steps": 1035, "loss": 0.6839, "lr": 5e-06, "epoch": 2.2881969587255613, "percentage": 76.33, "elapsed_time": "7:14:03", "remaining_time": "2:14:36"}
82
+ {"current_steps": 800, "total_steps": 1035, "loss": 0.6793, "lr": 5e-06, "epoch": 2.317161477190442, "percentage": 77.29, "elapsed_time": "7:19:24", "remaining_time": "2:09:04"}
83
+ {"current_steps": 810, "total_steps": 1035, "loss": 0.6771, "lr": 5e-06, "epoch": 2.3461259956553224, "percentage": 78.26, "elapsed_time": "7:24:44", "remaining_time": "2:03:32"}
84
+ {"current_steps": 820, "total_steps": 1035, "loss": 0.6834, "lr": 5e-06, "epoch": 2.3750905141202026, "percentage": 79.23, "elapsed_time": "7:30:06", "remaining_time": "1:58:01"}
85
+ {"current_steps": 830, "total_steps": 1035, "loss": 0.6828, "lr": 5e-06, "epoch": 2.404055032585083, "percentage": 80.19, "elapsed_time": "7:35:28", "remaining_time": "1:52:29"}
86
+ {"current_steps": 840, "total_steps": 1035, "loss": 0.6835, "lr": 5e-06, "epoch": 2.4330195510499637, "percentage": 81.16, "elapsed_time": "7:40:47", "remaining_time": "1:46:58"}
87
+ {"current_steps": 850, "total_steps": 1035, "loss": 0.6852, "lr": 5e-06, "epoch": 2.4619840695148443, "percentage": 82.13, "elapsed_time": "7:46:09", "remaining_time": "1:41:27"}
88
+ {"current_steps": 860, "total_steps": 1035, "loss": 0.6813, "lr": 5e-06, "epoch": 2.490948587979725, "percentage": 83.09, "elapsed_time": "7:51:29", "remaining_time": "1:35:56"}
89
+ {"current_steps": 870, "total_steps": 1035, "loss": 0.6846, "lr": 5e-06, "epoch": 2.5199131064446054, "percentage": 84.06, "elapsed_time": "7:56:51", "remaining_time": "1:30:26"}
90
+ {"current_steps": 880, "total_steps": 1035, "loss": 0.6806, "lr": 5e-06, "epoch": 2.548877624909486, "percentage": 85.02, "elapsed_time": "8:02:12", "remaining_time": "1:24:56"}
91
+ {"current_steps": 890, "total_steps": 1035, "loss": 0.6818, "lr": 5e-06, "epoch": 2.577842143374366, "percentage": 85.99, "elapsed_time": "8:07:32", "remaining_time": "1:19:25"}
92
+ {"current_steps": 900, "total_steps": 1035, "loss": 0.6825, "lr": 5e-06, "epoch": 2.606806661839247, "percentage": 86.96, "elapsed_time": "8:12:49", "remaining_time": "1:13:55"}
93
+ {"current_steps": 910, "total_steps": 1035, "loss": 0.6825, "lr": 5e-06, "epoch": 2.6357711803041273, "percentage": 87.92, "elapsed_time": "8:18:10", "remaining_time": "1:08:25"}
94
+ {"current_steps": 920, "total_steps": 1035, "loss": 0.6834, "lr": 5e-06, "epoch": 2.664735698769008, "percentage": 88.89, "elapsed_time": "8:23:32", "remaining_time": "1:02:56"}
95
+ {"current_steps": 930, "total_steps": 1035, "loss": 0.6808, "lr": 5e-06, "epoch": 2.6937002172338884, "percentage": 89.86, "elapsed_time": "8:28:55", "remaining_time": "0:57:27"}
96
+ {"current_steps": 940, "total_steps": 1035, "loss": 0.6844, "lr": 5e-06, "epoch": 2.722664735698769, "percentage": 90.82, "elapsed_time": "8:34:16", "remaining_time": "0:51:58"}
97
+ {"current_steps": 950, "total_steps": 1035, "loss": 0.6841, "lr": 5e-06, "epoch": 2.7516292541636496, "percentage": 91.79, "elapsed_time": "8:39:38", "remaining_time": "0:46:29"}
98
+ {"current_steps": 960, "total_steps": 1035, "loss": 0.6805, "lr": 5e-06, "epoch": 2.78059377262853, "percentage": 92.75, "elapsed_time": "8:44:59", "remaining_time": "0:41:00"}
99
+ {"current_steps": 970, "total_steps": 1035, "loss": 0.6836, "lr": 5e-06, "epoch": 2.8095582910934107, "percentage": 93.72, "elapsed_time": "8:50:20", "remaining_time": "0:35:32"}
100
+ {"current_steps": 980, "total_steps": 1035, "loss": 0.6802, "lr": 5e-06, "epoch": 2.838522809558291, "percentage": 94.69, "elapsed_time": "8:55:42", "remaining_time": "0:30:03"}
101
+ {"current_steps": 990, "total_steps": 1035, "loss": 0.6779, "lr": 5e-06, "epoch": 2.867487328023172, "percentage": 95.65, "elapsed_time": "9:01:04", "remaining_time": "0:24:35"}
102
+ {"current_steps": 1000, "total_steps": 1035, "loss": 0.6815, "lr": 5e-06, "epoch": 2.896451846488052, "percentage": 96.62, "elapsed_time": "9:06:26", "remaining_time": "0:19:07"}
103
+ {"current_steps": 1010, "total_steps": 1035, "loss": 0.6828, "lr": 5e-06, "epoch": 2.9254163649529326, "percentage": 97.58, "elapsed_time": "9:11:49", "remaining_time": "0:13:39"}
104
+ {"current_steps": 1020, "total_steps": 1035, "loss": 0.6884, "lr": 5e-06, "epoch": 2.954380883417813, "percentage": 98.55, "elapsed_time": "9:17:12", "remaining_time": "0:08:11"}
105
+ {"current_steps": 1030, "total_steps": 1035, "loss": 0.685, "lr": 5e-06, "epoch": 2.9833454018826937, "percentage": 99.52, "elapsed_time": "9:22:34", "remaining_time": "0:02:43"}