neginr commited on
Commit
9223a0d
·
verified ·
1 Parent(s): 7b9e227

Training in progress, epoch 4

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d8e7f96a8540e0a3c779cc9672ef984f249c88a74bbb937631f1c577919120f
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bc918f9d513794d256a27dddb9e84a9b7d6a27cd51bc2daf6d0b9d60a6cf8a5
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:e9bcd39d368e16580de9852684bb0279634415e1ee0a5aa812e8a950fa1ab26e
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fe70bc2fe80d5327ab34208c9d3416dc8d61acd5a3d01093d9232980b3446d4
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ec66c7db36cbae91674832c561e589ecac97f55cb5e2f2d74adf7aea1ae2ff5
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47cec3f27639824f0365cf284921afd611117afe0bd538194c758c43787d6898
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:555b6809a8a067de1b241ec99a4594e325833e96fa2a932cdac6ec2f3121ff43
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7db0b4d05d1a6d7a122b4264bde486ea4eb8da47b46e3c98e7d31bdecea76fd
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -104,3 +104,36 @@
104
  {"current_steps": 104, "total_steps": 231, "loss": 0.3505, "lr": 1.3491409798123687e-05, "epoch": 3.1515151515151514, "percentage": 45.02, "elapsed_time": "0:47:17", "remaining_time": "0:57:44"}
105
  {"current_steps": 105, "total_steps": 231, "loss": 0.3767, "lr": 1.3348796121709862e-05, "epoch": 3.1818181818181817, "percentage": 45.45, "elapsed_time": "0:47:40", "remaining_time": "0:57:12"}
106
  {"current_steps": 106, "total_steps": 231, "loss": 0.2797, "lr": 1.3205411116710973e-05, "epoch": 3.212121212121212, "percentage": 45.89, "elapsed_time": "0:48:02", "remaining_time": "0:56:39"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
104
  {"current_steps": 104, "total_steps": 231, "loss": 0.3505, "lr": 1.3491409798123687e-05, "epoch": 3.1515151515151514, "percentage": 45.02, "elapsed_time": "0:47:17", "remaining_time": "0:57:44"}
105
  {"current_steps": 105, "total_steps": 231, "loss": 0.3767, "lr": 1.3348796121709862e-05, "epoch": 3.1818181818181817, "percentage": 45.45, "elapsed_time": "0:47:40", "remaining_time": "0:57:12"}
106
  {"current_steps": 106, "total_steps": 231, "loss": 0.2797, "lr": 1.3205411116710973e-05, "epoch": 3.212121212121212, "percentage": 45.89, "elapsed_time": "0:48:02", "remaining_time": "0:56:39"}
107
+ {"current_steps": 107, "total_steps": 231, "loss": 0.3354, "lr": 1.3061287809011243e-05, "epoch": 3.242424242424242, "percentage": 46.32, "elapsed_time": "0:48:25", "remaining_time": "0:56:06"}
108
+ {"current_steps": 108, "total_steps": 231, "loss": 0.3346, "lr": 1.291645939454825e-05, "epoch": 3.2727272727272725, "percentage": 46.75, "elapsed_time": "0:48:47", "remaining_time": "0:55:34"}
109
+ {"current_steps": 109, "total_steps": 231, "loss": 0.4063, "lr": 1.277095923166689e-05, "epoch": 3.303030303030303, "percentage": 47.19, "elapsed_time": "0:49:09", "remaining_time": "0:55:01"}
110
+ {"current_steps": 110, "total_steps": 231, "loss": 0.3517, "lr": 1.2624820833435939e-05, "epoch": 3.3333333333333335, "percentage": 47.62, "elapsed_time": "0:49:34", "remaining_time": "0:54:31"}
111
+ {"current_steps": 111, "total_steps": 231, "loss": 0.3517, "lr": 1.2478077859929e-05, "epoch": 3.3636363636363638, "percentage": 48.05, "elapsed_time": "0:50:00", "remaining_time": "0:54:03"}
112
+ {"current_steps": 112, "total_steps": 231, "loss": 0.3057, "lr": 1.2330764110471567e-05, "epoch": 3.393939393939394, "percentage": 48.48, "elapsed_time": "0:50:21", "remaining_time": "0:53:30"}
113
+ {"current_steps": 113, "total_steps": 231, "loss": 0.4122, "lr": 1.2182913515856016e-05, "epoch": 3.4242424242424243, "percentage": 48.92, "elapsed_time": "0:50:50", "remaining_time": "0:53:05"}
114
+ {"current_steps": 114, "total_steps": 231, "loss": 0.3289, "lr": 1.2034560130526341e-05, "epoch": 3.4545454545454546, "percentage": 49.35, "elapsed_time": "0:51:09", "remaining_time": "0:52:30"}
115
+ {"current_steps": 115, "total_steps": 231, "loss": 0.3524, "lr": 1.1885738124734359e-05, "epoch": 3.484848484848485, "percentage": 49.78, "elapsed_time": "0:51:37", "remaining_time": "0:52:03"}
116
+ {"current_steps": 116, "total_steps": 231, "loss": 0.3106, "lr": 1.1736481776669307e-05, "epoch": 3.515151515151515, "percentage": 50.22, "elapsed_time": "0:51:57", "remaining_time": "0:51:30"}
117
+ {"current_steps": 117, "total_steps": 231, "loss": 0.3574, "lr": 1.1586825464562515e-05, "epoch": 3.5454545454545454, "percentage": 50.65, "elapsed_time": "0:52:15", "remaining_time": "0:50:55"}
118
+ {"current_steps": 118, "total_steps": 231, "loss": 0.3211, "lr": 1.1436803658769082e-05, "epoch": 3.5757575757575757, "percentage": 51.08, "elapsed_time": "0:52:40", "remaining_time": "0:50:26"}
119
+ {"current_steps": 119, "total_steps": 231, "loss": 0.3699, "lr": 1.1286450913828313e-05, "epoch": 3.606060606060606, "percentage": 51.52, "elapsed_time": "0:53:00", "remaining_time": "0:49:52"}
120
+ {"current_steps": 120, "total_steps": 231, "loss": 0.3578, "lr": 1.113580186050475e-05, "epoch": 3.6363636363636362, "percentage": 51.95, "elapsed_time": "0:53:26", "remaining_time": "0:49:25"}
121
+ {"current_steps": 121, "total_steps": 231, "loss": 0.3672, "lr": 1.0984891197811686e-05, "epoch": 3.6666666666666665, "percentage": 52.38, "elapsed_time": "0:53:52", "remaining_time": "0:48:58"}
122
+ {"current_steps": 122, "total_steps": 231, "loss": 0.3302, "lr": 1.0833753685018935e-05, "epoch": 3.6969696969696972, "percentage": 52.81, "elapsed_time": "0:54:13", "remaining_time": "0:48:26"}
123
+ {"current_steps": 123, "total_steps": 231, "loss": 0.3288, "lr": 1.0682424133646712e-05, "epoch": 3.7272727272727275, "percentage": 53.25, "elapsed_time": "0:54:34", "remaining_time": "0:47:55"}
124
+ {"current_steps": 124, "total_steps": 231, "loss": 0.3259, "lr": 1.0530937399447496e-05, "epoch": 3.757575757575758, "percentage": 53.68, "elapsed_time": "0:54:54", "remaining_time": "0:47:23"}
125
+ {"current_steps": 125, "total_steps": 231, "loss": 0.3499, "lr": 1.0379328374377715e-05, "epoch": 3.787878787878788, "percentage": 54.11, "elapsed_time": "0:55:16", "remaining_time": "0:46:52"}
126
+ {"current_steps": 126, "total_steps": 231, "loss": 0.3506, "lr": 1.0227631978561057e-05, "epoch": 3.8181818181818183, "percentage": 54.55, "elapsed_time": "0:55:43", "remaining_time": "0:46:25"}
127
+ {"current_steps": 127, "total_steps": 231, "loss": 0.3475, "lr": 1.0075883152245334e-05, "epoch": 3.8484848484848486, "percentage": 54.98, "elapsed_time": "0:55:59", "remaining_time": "0:45:51"}
128
+ {"current_steps": 128, "total_steps": 231, "loss": 0.3409, "lr": 9.92411684775467e-06, "epoch": 3.878787878787879, "percentage": 55.41, "elapsed_time": "0:56:23", "remaining_time": "0:45:22"}
129
+ {"current_steps": 129, "total_steps": 231, "loss": 0.3095, "lr": 9.772368021438943e-06, "epoch": 3.909090909090909, "percentage": 55.84, "elapsed_time": "0:56:47", "remaining_time": "0:44:54"}
130
+ {"current_steps": 130, "total_steps": 231, "loss": 0.3741, "lr": 9.620671625622287e-06, "epoch": 3.9393939393939394, "percentage": 56.28, "elapsed_time": "0:57:15", "remaining_time": "0:44:29"}
131
+ {"current_steps": 131, "total_steps": 231, "loss": 0.3234, "lr": 9.469062600552509e-06, "epoch": 3.9696969696969697, "percentage": 56.71, "elapsed_time": "0:57:38", "remaining_time": "0:44:00"}
132
+ {"current_steps": 132, "total_steps": 231, "loss": 0.3493, "lr": 9.317575866353293e-06, "epoch": 4.0, "percentage": 57.14, "elapsed_time": "0:58:02", "remaining_time": "0:43:32"}
133
+ {"current_steps": 133, "total_steps": 231, "loss": 0.2961, "lr": 9.166246314981066e-06, "epoch": 4.03030303030303, "percentage": 57.58, "elapsed_time": "1:00:25", "remaining_time": "0:44:31"}
134
+ {"current_steps": 134, "total_steps": 231, "loss": 0.2719, "lr": 9.015108802188314e-06, "epoch": 4.0606060606060606, "percentage": 58.01, "elapsed_time": "1:00:53", "remaining_time": "0:44:04"}
135
+ {"current_steps": 135, "total_steps": 231, "loss": 0.2593, "lr": 8.86419813949525e-06, "epoch": 4.090909090909091, "percentage": 58.44, "elapsed_time": "1:01:11", "remaining_time": "0:43:30"}
136
+ {"current_steps": 136, "total_steps": 231, "loss": 0.2303, "lr": 8.71354908617169e-06, "epoch": 4.121212121212121, "percentage": 58.87, "elapsed_time": "1:01:34", "remaining_time": "0:43:00"}
137
+ {"current_steps": 137, "total_steps": 231, "loss": 0.3083, "lr": 8.56319634123092e-06, "epoch": 4.151515151515151, "percentage": 59.31, "elapsed_time": "1:01:56", "remaining_time": "0:42:29"}
138
+ {"current_steps": 138, "total_steps": 231, "loss": 0.2441, "lr": 8.413174535437486e-06, "epoch": 4.181818181818182, "percentage": 59.74, "elapsed_time": "1:02:19", "remaining_time": "0:41:59"}
139
+ {"current_steps": 139, "total_steps": 231, "loss": 0.3123, "lr": 8.263518223330698e-06, "epoch": 4.212121212121212, "percentage": 60.17, "elapsed_time": "1:02:47", "remaining_time": "0:41:33"}