sedrickkeh commited on
Commit
713e4f1
·
verified ·
1 Parent(s): 9831a38

Training in progress, epoch 1

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa3457647cc5f04e3234258879e6816843f19d25e25d1d8bd1fcf967d6156b4e
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5b4766707ae4c843486ebdfa033d4dd63c94cd06bd94c048adcb61bc9cafad6
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c30375716cf3bede22dd204c9a73b64474caa396672de0b4badb99241a10d0f
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e4b526cc5056003f4c96fb8435658a31238b79d4f872930cc77a90e129934ee
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:f1c5f0c33a5cf46eafbd9c82cc2616508c4346acd0a13e66ff4a9377f8a4d9c4
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d0bf4d4716a91b988e74f6c9e868fb03c4002dfdaeb74433e49680231b81ba0
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d4a8a22d3fd81f19902b8c099a4163f40013a6ea6cbb1ff7d2cc728ba224d16
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12c011c22f0bbf108b37de4cb012205f827ef59c613af48dab8da6f31bfa95c7
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -43,3 +43,46 @@
43
  {"current_steps": 430, "total_steps": 876, "loss": 0.6345, "lr": 5e-06, "epoch": 0.98005698005698, "percentage": 49.09, "elapsed_time": "6:15:46", "remaining_time": "6:29:45"}
44
  {"current_steps": 438, "total_steps": 876, "eval_loss": 0.6251205205917358, "epoch": 0.9982905982905983, "percentage": 50.0, "elapsed_time": "6:30:34", "remaining_time": "6:30:34"}
45
  {"current_steps": 440, "total_steps": 876, "loss": 0.6472, "lr": 5e-06, "epoch": 1.0034188034188034, "percentage": 50.23, "elapsed_time": "6:32:59", "remaining_time": "6:29:24"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
43
  {"current_steps": 430, "total_steps": 876, "loss": 0.6345, "lr": 5e-06, "epoch": 0.98005698005698, "percentage": 49.09, "elapsed_time": "6:15:46", "remaining_time": "6:29:45"}
44
  {"current_steps": 438, "total_steps": 876, "eval_loss": 0.6251205205917358, "epoch": 0.9982905982905983, "percentage": 50.0, "elapsed_time": "6:30:34", "remaining_time": "6:30:34"}
45
  {"current_steps": 440, "total_steps": 876, "loss": 0.6472, "lr": 5e-06, "epoch": 1.0034188034188034, "percentage": 50.23, "elapsed_time": "6:32:59", "remaining_time": "6:29:24"}
46
+ {"current_steps": 450, "total_steps": 876, "loss": 0.6017, "lr": 5e-06, "epoch": 1.0262108262108263, "percentage": 51.37, "elapsed_time": "6:41:44", "remaining_time": "6:20:18"}
47
+ {"current_steps": 460, "total_steps": 876, "loss": 0.5954, "lr": 5e-06, "epoch": 1.049002849002849, "percentage": 52.51, "elapsed_time": "6:50:28", "remaining_time": "6:11:12"}
48
+ {"current_steps": 470, "total_steps": 876, "loss": 0.5962, "lr": 5e-06, "epoch": 1.0717948717948718, "percentage": 53.65, "elapsed_time": "6:59:12", "remaining_time": "6:02:07"}
49
+ {"current_steps": 480, "total_steps": 876, "loss": 0.6039, "lr": 5e-06, "epoch": 1.0945868945868946, "percentage": 54.79, "elapsed_time": "7:07:56", "remaining_time": "5:53:03"}
50
+ {"current_steps": 490, "total_steps": 876, "loss": 0.6089, "lr": 5e-06, "epoch": 1.1173789173789175, "percentage": 55.94, "elapsed_time": "7:16:40", "remaining_time": "5:43:59"}
51
+ {"current_steps": 500, "total_steps": 876, "loss": 0.5988, "lr": 5e-06, "epoch": 1.1401709401709401, "percentage": 57.08, "elapsed_time": "7:25:24", "remaining_time": "5:34:57"}
52
+ {"current_steps": 510, "total_steps": 876, "loss": 0.5966, "lr": 5e-06, "epoch": 1.162962962962963, "percentage": 58.22, "elapsed_time": "7:34:08", "remaining_time": "5:25:55"}
53
+ {"current_steps": 520, "total_steps": 876, "loss": 0.6023, "lr": 5e-06, "epoch": 1.1857549857549858, "percentage": 59.36, "elapsed_time": "7:42:53", "remaining_time": "5:16:54"}
54
+ {"current_steps": 530, "total_steps": 876, "loss": 0.5953, "lr": 5e-06, "epoch": 1.2085470085470085, "percentage": 60.5, "elapsed_time": "7:51:38", "remaining_time": "5:07:53"}
55
+ {"current_steps": 540, "total_steps": 876, "loss": 0.6055, "lr": 5e-06, "epoch": 1.2313390313390313, "percentage": 61.64, "elapsed_time": "8:00:22", "remaining_time": "4:58:54"}
56
+ {"current_steps": 550, "total_steps": 876, "loss": 0.6022, "lr": 5e-06, "epoch": 1.2541310541310542, "percentage": 62.79, "elapsed_time": "8:09:06", "remaining_time": "4:49:54"}
57
+ {"current_steps": 560, "total_steps": 876, "loss": 0.6037, "lr": 5e-06, "epoch": 1.2769230769230768, "percentage": 63.93, "elapsed_time": "8:17:51", "remaining_time": "4:40:56"}
58
+ {"current_steps": 570, "total_steps": 876, "loss": 0.5977, "lr": 5e-06, "epoch": 1.2997150997150997, "percentage": 65.07, "elapsed_time": "8:26:36", "remaining_time": "4:31:58"}
59
+ {"current_steps": 580, "total_steps": 876, "loss": 0.5962, "lr": 5e-06, "epoch": 1.3225071225071225, "percentage": 66.21, "elapsed_time": "8:35:21", "remaining_time": "4:23:00"}
60
+ {"current_steps": 590, "total_steps": 876, "loss": 0.5958, "lr": 5e-06, "epoch": 1.3452991452991454, "percentage": 67.35, "elapsed_time": "8:44:06", "remaining_time": "4:14:03"}
61
+ {"current_steps": 600, "total_steps": 876, "loss": 0.6015, "lr": 5e-06, "epoch": 1.368091168091168, "percentage": 68.49, "elapsed_time": "8:52:51", "remaining_time": "4:05:06"}
62
+ {"current_steps": 610, "total_steps": 876, "loss": 0.6015, "lr": 5e-06, "epoch": 1.390883190883191, "percentage": 69.63, "elapsed_time": "9:01:35", "remaining_time": "3:56:10"}
63
+ {"current_steps": 620, "total_steps": 876, "loss": 0.6041, "lr": 5e-06, "epoch": 1.4136752136752135, "percentage": 70.78, "elapsed_time": "9:10:20", "remaining_time": "3:47:14"}
64
+ {"current_steps": 630, "total_steps": 876, "loss": 0.6021, "lr": 5e-06, "epoch": 1.4364672364672364, "percentage": 71.92, "elapsed_time": "9:19:05", "remaining_time": "3:38:18"}
65
+ {"current_steps": 640, "total_steps": 876, "loss": 0.597, "lr": 5e-06, "epoch": 1.4592592592592593, "percentage": 73.06, "elapsed_time": "9:27:49", "remaining_time": "3:29:23"}
66
+ {"current_steps": 650, "total_steps": 876, "loss": 0.5949, "lr": 5e-06, "epoch": 1.4820512820512821, "percentage": 74.2, "elapsed_time": "9:36:34", "remaining_time": "3:20:28"}
67
+ {"current_steps": 660, "total_steps": 876, "loss": 0.5946, "lr": 5e-06, "epoch": 1.504843304843305, "percentage": 75.34, "elapsed_time": "9:45:18", "remaining_time": "3:11:33"}
68
+ {"current_steps": 670, "total_steps": 876, "loss": 0.6022, "lr": 5e-06, "epoch": 1.5276353276353276, "percentage": 76.48, "elapsed_time": "9:54:03", "remaining_time": "3:02:38"}
69
+ {"current_steps": 680, "total_steps": 876, "loss": 0.5908, "lr": 5e-06, "epoch": 1.5504273504273505, "percentage": 77.63, "elapsed_time": "10:02:47", "remaining_time": "2:53:44"}
70
+ {"current_steps": 690, "total_steps": 876, "loss": 0.5947, "lr": 5e-06, "epoch": 1.573219373219373, "percentage": 78.77, "elapsed_time": "10:11:31", "remaining_time": "2:44:50"}
71
+ {"current_steps": 700, "total_steps": 876, "loss": 0.6102, "lr": 5e-06, "epoch": 1.596011396011396, "percentage": 79.91, "elapsed_time": "10:20:15", "remaining_time": "2:35:57"}
72
+ {"current_steps": 710, "total_steps": 876, "loss": 0.5973, "lr": 5e-06, "epoch": 1.6188034188034188, "percentage": 81.05, "elapsed_time": "10:29:00", "remaining_time": "2:27:03"}
73
+ {"current_steps": 720, "total_steps": 876, "loss": 0.6019, "lr": 5e-06, "epoch": 1.6415954415954417, "percentage": 82.19, "elapsed_time": "10:37:44", "remaining_time": "2:18:10"}
74
+ {"current_steps": 730, "total_steps": 876, "loss": 0.595, "lr": 5e-06, "epoch": 1.6643874643874645, "percentage": 83.33, "elapsed_time": "10:46:29", "remaining_time": "2:09:17"}
75
+ {"current_steps": 740, "total_steps": 876, "loss": 0.5961, "lr": 5e-06, "epoch": 1.6871794871794872, "percentage": 84.47, "elapsed_time": "10:55:13", "remaining_time": "2:00:25"}
76
+ {"current_steps": 750, "total_steps": 876, "loss": 0.5935, "lr": 5e-06, "epoch": 1.7099715099715098, "percentage": 85.62, "elapsed_time": "11:03:58", "remaining_time": "1:51:32"}
77
+ {"current_steps": 760, "total_steps": 876, "loss": 0.5974, "lr": 5e-06, "epoch": 1.7327635327635327, "percentage": 86.76, "elapsed_time": "11:12:42", "remaining_time": "1:42:40"}
78
+ {"current_steps": 770, "total_steps": 876, "loss": 0.5938, "lr": 5e-06, "epoch": 1.7555555555555555, "percentage": 87.9, "elapsed_time": "11:21:27", "remaining_time": "1:33:48"}
79
+ {"current_steps": 780, "total_steps": 876, "loss": 0.6009, "lr": 5e-06, "epoch": 1.7783475783475784, "percentage": 89.04, "elapsed_time": "11:30:12", "remaining_time": "1:24:56"}
80
+ {"current_steps": 790, "total_steps": 876, "loss": 0.5985, "lr": 5e-06, "epoch": 1.8011396011396013, "percentage": 90.18, "elapsed_time": "11:38:56", "remaining_time": "1:16:05"}
81
+ {"current_steps": 800, "total_steps": 876, "loss": 0.5853, "lr": 5e-06, "epoch": 1.823931623931624, "percentage": 91.32, "elapsed_time": "11:47:40", "remaining_time": "1:07:13"}
82
+ {"current_steps": 810, "total_steps": 876, "loss": 0.5932, "lr": 5e-06, "epoch": 1.8467236467236468, "percentage": 92.47, "elapsed_time": "11:56:24", "remaining_time": "0:58:22"}
83
+ {"current_steps": 820, "total_steps": 876, "loss": 0.5909, "lr": 5e-06, "epoch": 1.8695156695156694, "percentage": 93.61, "elapsed_time": "12:05:08", "remaining_time": "0:49:31"}
84
+ {"current_steps": 830, "total_steps": 876, "loss": 0.5947, "lr": 5e-06, "epoch": 1.8923076923076922, "percentage": 94.75, "elapsed_time": "12:13:53", "remaining_time": "0:40:40"}
85
+ {"current_steps": 840, "total_steps": 876, "loss": 0.5992, "lr": 5e-06, "epoch": 1.915099715099715, "percentage": 95.89, "elapsed_time": "12:22:37", "remaining_time": "0:31:49"}
86
+ {"current_steps": 850, "total_steps": 876, "loss": 0.5973, "lr": 5e-06, "epoch": 1.937891737891738, "percentage": 97.03, "elapsed_time": "12:31:22", "remaining_time": "0:22:59"}
87
+ {"current_steps": 860, "total_steps": 876, "loss": 0.5986, "lr": 5e-06, "epoch": 1.9606837606837608, "percentage": 98.17, "elapsed_time": "12:40:07", "remaining_time": "0:14:08"}
88
+ {"current_steps": 870, "total_steps": 876, "loss": 0.5961, "lr": 5e-06, "epoch": 1.9834757834757835, "percentage": 99.32, "elapsed_time": "12:48:52", "remaining_time": "0:05:18"}