sedrickkeh commited on
Commit
fb9aca0
·
verified ·
1 Parent(s): 22044af

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 sha256:5f986ae453a496481387a6021383b9aab71356256ca952db85a7446e0f8de722
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:645d45901ea21ad1db935bc1eb50b94f9aa2afc125769c8928233b29c012b54b
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:bb69f036064b5a5b88d72a49d14950e225c758b3e64ad50610b41dec03ba1c7f
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:364f3134428b4d6168a694bcf31f2c930451702db95f5f2e4ef61fb57885b455
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:ab4a51b39ab8a0a8403be253a3869e209ab73d2b3cf074c93286b92432239647
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4523c37e249d8232ddbd33ad4e72a59dedc8b870003dde81a3ba9f6de02c39d0
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:e9c9a52d6f1a492f887bd2c852daf4c9dd2800fb6cf19fd3c6747e0d9572a241
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:348d0de087666877efba47979c3cb029d8f83d4b90c4d9b97ad37aec0b3178ac
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -68,3 +68,37 @@
68
  {"current_steps": 670, "total_steps": 1023, "loss": 0.619, "learning_rate": 2e-06, "epoch": 1.9615947329919532, "percentage": 65.49, "elapsed_time": "9:53:08", "remaining_time": "5:12:30"}
69
  {"current_steps": 680, "total_steps": 1023, "loss": 0.6339, "learning_rate": 2e-06, "epoch": 1.9908558888076078, "percentage": 66.47, "elapsed_time": "10:01:52", "remaining_time": "5:03:35"}
70
  {"current_steps": 682, "total_steps": 1023, "eval_loss": 0.6420042514801025, "epoch": 1.9967081199707388, "percentage": 66.67, "elapsed_time": "10:09:58", "remaining_time": "5:04:59"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  {"current_steps": 670, "total_steps": 1023, "loss": 0.619, "learning_rate": 2e-06, "epoch": 1.9615947329919532, "percentage": 65.49, "elapsed_time": "9:53:08", "remaining_time": "5:12:30"}
69
  {"current_steps": 680, "total_steps": 1023, "loss": 0.6339, "learning_rate": 2e-06, "epoch": 1.9908558888076078, "percentage": 66.47, "elapsed_time": "10:01:52", "remaining_time": "5:03:35"}
70
  {"current_steps": 682, "total_steps": 1023, "eval_loss": 0.6420042514801025, "epoch": 1.9967081199707388, "percentage": 66.67, "elapsed_time": "10:09:58", "remaining_time": "5:04:59"}
71
+ {"current_steps": 690, "total_steps": 1023, "loss": 0.6582, "learning_rate": 2e-06, "epoch": 2.0212143379663496, "percentage": 67.45, "elapsed_time": "10:17:33", "remaining_time": "4:58:02"}
72
+ {"current_steps": 700, "total_steps": 1023, "loss": 0.6098, "learning_rate": 2e-06, "epoch": 2.050475493782004, "percentage": 68.43, "elapsed_time": "10:26:19", "remaining_time": "4:49:00"}
73
+ {"current_steps": 710, "total_steps": 1023, "loss": 0.6116, "learning_rate": 2e-06, "epoch": 2.0797366495976592, "percentage": 69.4, "elapsed_time": "10:35:05", "remaining_time": "4:39:58"}
74
+ {"current_steps": 720, "total_steps": 1023, "loss": 0.6126, "learning_rate": 2e-06, "epoch": 2.108997805413314, "percentage": 70.38, "elapsed_time": "10:43:50", "remaining_time": "4:30:57"}
75
+ {"current_steps": 730, "total_steps": 1023, "loss": 0.6141, "learning_rate": 2e-06, "epoch": 2.1382589612289684, "percentage": 71.36, "elapsed_time": "10:52:35", "remaining_time": "4:21:56"}
76
+ {"current_steps": 740, "total_steps": 1023, "loss": 0.619, "learning_rate": 2e-06, "epoch": 2.1675201170446234, "percentage": 72.34, "elapsed_time": "11:01:21", "remaining_time": "4:12:55"}
77
+ {"current_steps": 750, "total_steps": 1023, "loss": 0.6175, "learning_rate": 2e-06, "epoch": 2.196781272860278, "percentage": 73.31, "elapsed_time": "11:10:06", "remaining_time": "4:03:55"}
78
+ {"current_steps": 760, "total_steps": 1023, "loss": 0.6142, "learning_rate": 2e-06, "epoch": 2.2260424286759326, "percentage": 74.29, "elapsed_time": "11:18:53", "remaining_time": "3:54:55"}
79
+ {"current_steps": 770, "total_steps": 1023, "loss": 0.6128, "learning_rate": 2e-06, "epoch": 2.255303584491587, "percentage": 75.27, "elapsed_time": "11:27:40", "remaining_time": "3:45:56"}
80
+ {"current_steps": 780, "total_steps": 1023, "loss": 0.6121, "learning_rate": 2e-06, "epoch": 2.284564740307242, "percentage": 76.25, "elapsed_time": "11:36:27", "remaining_time": "3:36:58"}
81
+ {"current_steps": 790, "total_steps": 1023, "loss": 0.6096, "learning_rate": 2e-06, "epoch": 2.313825896122897, "percentage": 77.22, "elapsed_time": "11:45:13", "remaining_time": "3:27:59"}
82
+ {"current_steps": 800, "total_steps": 1023, "loss": 0.6178, "learning_rate": 2e-06, "epoch": 2.3430870519385514, "percentage": 78.2, "elapsed_time": "11:53:58", "remaining_time": "3:19:01"}
83
+ {"current_steps": 810, "total_steps": 1023, "loss": 0.6127, "learning_rate": 2e-06, "epoch": 2.3723482077542064, "percentage": 79.18, "elapsed_time": "12:02:44", "remaining_time": "3:10:03"}
84
+ {"current_steps": 820, "total_steps": 1023, "loss": 0.6191, "learning_rate": 2e-06, "epoch": 2.401609363569861, "percentage": 80.16, "elapsed_time": "12:11:31", "remaining_time": "3:01:05"}
85
+ {"current_steps": 830, "total_steps": 1023, "loss": 0.6106, "learning_rate": 2e-06, "epoch": 2.4308705193855156, "percentage": 81.13, "elapsed_time": "12:20:17", "remaining_time": "2:52:08"}
86
+ {"current_steps": 840, "total_steps": 1023, "loss": 0.611, "learning_rate": 2e-06, "epoch": 2.4601316752011706, "percentage": 82.11, "elapsed_time": "12:29:03", "remaining_time": "2:43:11"}
87
+ {"current_steps": 850, "total_steps": 1023, "loss": 0.6127, "learning_rate": 2e-06, "epoch": 2.489392831016825, "percentage": 83.09, "elapsed_time": "12:37:50", "remaining_time": "2:34:14"}
88
+ {"current_steps": 860, "total_steps": 1023, "loss": 0.6057, "learning_rate": 2e-06, "epoch": 2.5186539868324798, "percentage": 84.07, "elapsed_time": "12:46:36", "remaining_time": "2:25:17"}
89
+ {"current_steps": 870, "total_steps": 1023, "loss": 0.6082, "learning_rate": 2e-06, "epoch": 2.547915142648135, "percentage": 85.04, "elapsed_time": "12:55:23", "remaining_time": "2:16:21"}
90
+ {"current_steps": 880, "total_steps": 1023, "loss": 0.6122, "learning_rate": 2e-06, "epoch": 2.5771762984637894, "percentage": 86.02, "elapsed_time": "13:04:09", "remaining_time": "2:07:25"}
91
+ {"current_steps": 890, "total_steps": 1023, "loss": 0.6116, "learning_rate": 2e-06, "epoch": 2.606437454279444, "percentage": 87.0, "elapsed_time": "13:12:57", "remaining_time": "1:58:29"}
92
+ {"current_steps": 900, "total_steps": 1023, "loss": 0.6163, "learning_rate": 2e-06, "epoch": 2.6356986100950985, "percentage": 87.98, "elapsed_time": "13:21:42", "remaining_time": "1:49:33"}
93
+ {"current_steps": 910, "total_steps": 1023, "loss": 0.6161, "learning_rate": 2e-06, "epoch": 2.6649597659107536, "percentage": 88.95, "elapsed_time": "13:30:29", "remaining_time": "1:40:38"}
94
+ {"current_steps": 920, "total_steps": 1023, "loss": 0.61, "learning_rate": 2e-06, "epoch": 2.694220921726408, "percentage": 89.93, "elapsed_time": "13:39:16", "remaining_time": "1:31:43"}
95
+ {"current_steps": 930, "total_steps": 1023, "loss": 0.6135, "learning_rate": 2e-06, "epoch": 2.723482077542063, "percentage": 90.91, "elapsed_time": "13:48:03", "remaining_time": "1:22:48"}
96
+ {"current_steps": 940, "total_steps": 1023, "loss": 0.6125, "learning_rate": 2e-06, "epoch": 2.7527432333577178, "percentage": 91.89, "elapsed_time": "13:56:51", "remaining_time": "1:13:53"}
97
+ {"current_steps": 950, "total_steps": 1023, "loss": 0.6111, "learning_rate": 2e-06, "epoch": 2.7820043891733723, "percentage": 92.86, "elapsed_time": "14:05:36", "remaining_time": "1:04:58"}
98
+ {"current_steps": 960, "total_steps": 1023, "loss": 0.6148, "learning_rate": 2e-06, "epoch": 2.811265544989027, "percentage": 93.84, "elapsed_time": "14:14:24", "remaining_time": "0:56:04"}
99
+ {"current_steps": 970, "total_steps": 1023, "loss": 0.6104, "learning_rate": 2e-06, "epoch": 2.840526700804682, "percentage": 94.82, "elapsed_time": "14:23:10", "remaining_time": "0:47:09"}
100
+ {"current_steps": 980, "total_steps": 1023, "loss": 0.61, "learning_rate": 2e-06, "epoch": 2.8697878566203365, "percentage": 95.8, "elapsed_time": "14:31:58", "remaining_time": "0:38:15"}
101
+ {"current_steps": 990, "total_steps": 1023, "loss": 0.6025, "learning_rate": 2e-06, "epoch": 2.899049012435991, "percentage": 96.77, "elapsed_time": "14:40:44", "remaining_time": "0:29:21"}
102
+ {"current_steps": 1000, "total_steps": 1023, "loss": 0.6107, "learning_rate": 2e-06, "epoch": 2.928310168251646, "percentage": 97.75, "elapsed_time": "14:49:31", "remaining_time": "0:20:27"}
103
+ {"current_steps": 1010, "total_steps": 1023, "loss": 0.6017, "learning_rate": 2e-06, "epoch": 2.9575713240673007, "percentage": 98.73, "elapsed_time": "14:58:15", "remaining_time": "0:11:33"}
104
+ {"current_steps": 1020, "total_steps": 1023, "loss": 0.6142, "learning_rate": 2e-06, "epoch": 2.9868324798829553, "percentage": 99.71, "elapsed_time": "15:07:02", "remaining_time": "0:02:40"}