sedrickkeh commited on
Commit
1e9ac63
·
verified ·
1 Parent(s): f1191ce

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:bbfff4de318472442602aaf608c44962197770d1dca3d9a58dc383ab96e6f064
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eea183f6b2dcc8c8fc79e826bcea2e87f09396b0b87f8f6e312bbbf21bf8380c
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:f3cd9e8817b2df86df505c063e32e13714bd50d438346c3544a52a4612c267a3
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0eadcdeed8ac66c8d877747bb676c749d272e295b07e488b7415d511be21cfb7
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:db36a24eb1cd82d8ded3055669f0c64f7f5772eadd98b9eceab56f7f6654a1d8
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e8c69650ffa09249ec90e6bc44fef9d97ad8dc9e5d824bca8d70d37439f94b4
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59f315349a8d8df45d9ccb268d2ede832629b0443becfbb25a72ba0a35113eee
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7ce8eda0c008414e0ce1cd9048599232fa1452f5a8a91651b3f19df744cb5dc
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -57,3 +57,32 @@
57
  {"current_steps": 560, "total_steps": 864, "loss": 0.6787, "lr": 5e-06, "epoch": 1.9415077989601386, "percentage": 64.81, "elapsed_time": "9:03:50", "remaining_time": "4:55:13"}
58
  {"current_steps": 570, "total_steps": 864, "loss": 0.6785, "lr": 5e-06, "epoch": 1.9761698440207973, "percentage": 65.97, "elapsed_time": "9:13:27", "remaining_time": "4:45:28"}
59
  {"current_steps": 576, "total_steps": 864, "eval_loss": 0.7195846438407898, "epoch": 1.9969670710571923, "percentage": 66.67, "elapsed_time": "9:25:00", "remaining_time": "4:42:30"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
57
  {"current_steps": 560, "total_steps": 864, "loss": 0.6787, "lr": 5e-06, "epoch": 1.9415077989601386, "percentage": 64.81, "elapsed_time": "9:03:50", "remaining_time": "4:55:13"}
58
  {"current_steps": 570, "total_steps": 864, "loss": 0.6785, "lr": 5e-06, "epoch": 1.9761698440207973, "percentage": 65.97, "elapsed_time": "9:13:27", "remaining_time": "4:45:28"}
59
  {"current_steps": 576, "total_steps": 864, "eval_loss": 0.7195846438407898, "epoch": 1.9969670710571923, "percentage": 66.67, "elapsed_time": "9:25:00", "remaining_time": "4:42:30"}
60
+ {"current_steps": 580, "total_steps": 864, "loss": 0.7064, "lr": 5e-06, "epoch": 2.011265164644714, "percentage": 67.13, "elapsed_time": "9:29:29", "remaining_time": "4:38:51"}
61
+ {"current_steps": 590, "total_steps": 864, "loss": 0.6269, "lr": 5e-06, "epoch": 2.0459272097053725, "percentage": 68.29, "elapsed_time": "9:39:06", "remaining_time": "4:28:56"}
62
+ {"current_steps": 600, "total_steps": 864, "loss": 0.6204, "lr": 5e-06, "epoch": 2.080589254766031, "percentage": 69.44, "elapsed_time": "9:48:42", "remaining_time": "4:19:01"}
63
+ {"current_steps": 610, "total_steps": 864, "loss": 0.6251, "lr": 5e-06, "epoch": 2.11525129982669, "percentage": 70.6, "elapsed_time": "9:58:18", "remaining_time": "4:09:07"}
64
+ {"current_steps": 620, "total_steps": 864, "loss": 0.6274, "lr": 5e-06, "epoch": 2.149913344887348, "percentage": 71.76, "elapsed_time": "10:07:53", "remaining_time": "3:59:14"}
65
+ {"current_steps": 630, "total_steps": 864, "loss": 0.6267, "lr": 5e-06, "epoch": 2.184575389948007, "percentage": 72.92, "elapsed_time": "10:17:29", "remaining_time": "3:49:21"}
66
+ {"current_steps": 640, "total_steps": 864, "loss": 0.6284, "lr": 5e-06, "epoch": 2.2192374350086657, "percentage": 74.07, "elapsed_time": "10:27:05", "remaining_time": "3:39:28"}
67
+ {"current_steps": 650, "total_steps": 864, "loss": 0.6334, "lr": 5e-06, "epoch": 2.253899480069324, "percentage": 75.23, "elapsed_time": "10:36:40", "remaining_time": "3:29:36"}
68
+ {"current_steps": 660, "total_steps": 864, "loss": 0.6292, "lr": 5e-06, "epoch": 2.2885615251299827, "percentage": 76.39, "elapsed_time": "10:46:17", "remaining_time": "3:19:45"}
69
+ {"current_steps": 670, "total_steps": 864, "loss": 0.6299, "lr": 5e-06, "epoch": 2.3232235701906414, "percentage": 77.55, "elapsed_time": "10:55:53", "remaining_time": "3:09:54"}
70
+ {"current_steps": 680, "total_steps": 864, "loss": 0.6342, "lr": 5e-06, "epoch": 2.3578856152512997, "percentage": 78.7, "elapsed_time": "11:05:29", "remaining_time": "3:00:04"}
71
+ {"current_steps": 690, "total_steps": 864, "loss": 0.6315, "lr": 5e-06, "epoch": 2.3925476603119584, "percentage": 79.86, "elapsed_time": "11:15:06", "remaining_time": "2:50:14"}
72
+ {"current_steps": 700, "total_steps": 864, "loss": 0.631, "lr": 5e-06, "epoch": 2.427209705372617, "percentage": 81.02, "elapsed_time": "11:24:43", "remaining_time": "2:40:25"}
73
+ {"current_steps": 710, "total_steps": 864, "loss": 0.6295, "lr": 5e-06, "epoch": 2.4618717504332754, "percentage": 82.18, "elapsed_time": "11:34:18", "remaining_time": "2:30:35"}
74
+ {"current_steps": 720, "total_steps": 864, "loss": 0.6315, "lr": 5e-06, "epoch": 2.496533795493934, "percentage": 83.33, "elapsed_time": "11:43:54", "remaining_time": "2:20:46"}
75
+ {"current_steps": 730, "total_steps": 864, "loss": 0.6362, "lr": 5e-06, "epoch": 2.5311958405545925, "percentage": 84.49, "elapsed_time": "11:53:29", "remaining_time": "2:10:58"}
76
+ {"current_steps": 740, "total_steps": 864, "loss": 0.6303, "lr": 5e-06, "epoch": 2.565857885615251, "percentage": 85.65, "elapsed_time": "12:03:04", "remaining_time": "2:01:09"}
77
+ {"current_steps": 750, "total_steps": 864, "loss": 0.6285, "lr": 5e-06, "epoch": 2.60051993067591, "percentage": 86.81, "elapsed_time": "12:12:39", "remaining_time": "1:51:21"}
78
+ {"current_steps": 760, "total_steps": 864, "loss": 0.6339, "lr": 5e-06, "epoch": 2.635181975736568, "percentage": 87.96, "elapsed_time": "12:22:15", "remaining_time": "1:41:34"}
79
+ {"current_steps": 770, "total_steps": 864, "loss": 0.6326, "lr": 5e-06, "epoch": 2.669844020797227, "percentage": 89.12, "elapsed_time": "12:31:52", "remaining_time": "1:31:47"}
80
+ {"current_steps": 780, "total_steps": 864, "loss": 0.6295, "lr": 5e-06, "epoch": 2.7045060658578857, "percentage": 90.28, "elapsed_time": "12:41:27", "remaining_time": "1:22:00"}
81
+ {"current_steps": 790, "total_steps": 864, "loss": 0.6253, "lr": 5e-06, "epoch": 2.739168110918544, "percentage": 91.44, "elapsed_time": "12:51:02", "remaining_time": "1:12:13"}
82
+ {"current_steps": 800, "total_steps": 864, "loss": 0.6328, "lr": 5e-06, "epoch": 2.7738301559792027, "percentage": 92.59, "elapsed_time": "13:00:38", "remaining_time": "1:02:27"}
83
+ {"current_steps": 810, "total_steps": 864, "loss": 0.6346, "lr": 5e-06, "epoch": 2.8084922010398614, "percentage": 93.75, "elapsed_time": "13:10:14", "remaining_time": "0:52:40"}
84
+ {"current_steps": 820, "total_steps": 864, "loss": 0.6331, "lr": 5e-06, "epoch": 2.8431542461005197, "percentage": 94.91, "elapsed_time": "13:19:50", "remaining_time": "0:42:55"}
85
+ {"current_steps": 830, "total_steps": 864, "loss": 0.6274, "lr": 5e-06, "epoch": 2.8778162911611784, "percentage": 96.06, "elapsed_time": "13:29:26", "remaining_time": "0:33:09"}
86
+ {"current_steps": 840, "total_steps": 864, "loss": 0.632, "lr": 5e-06, "epoch": 2.912478336221837, "percentage": 97.22, "elapsed_time": "13:39:02", "remaining_time": "0:23:24"}
87
+ {"current_steps": 850, "total_steps": 864, "loss": 0.6307, "lr": 5e-06, "epoch": 2.9471403812824954, "percentage": 98.38, "elapsed_time": "13:48:39", "remaining_time": "0:13:38"}
88
+ {"current_steps": 860, "total_steps": 864, "loss": 0.6293, "lr": 5e-06, "epoch": 2.981802426343154, "percentage": 99.54, "elapsed_time": "13:58:15", "remaining_time": "0:03:53"}