Hugging Face's logo

mlfoundations-dev
/
top_8_ranking_stackexchange

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
7cf0923
·
verified ·
1 Parent(s): 5d0aaa0

Training in progress, epoch 2

Browse files
Files changed (5) hide show
  1. model-00001-of-00004.safetensors +1 -1
  2. model-00002-of-00004.safetensors +1 -1
  3. model-00003-of-00004.safetensors +1 -1
  4. model-00004-of-00004.safetensors +1 -1
  5. trainer_log.jsonl +31 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11c5747be4034596bcf5942dbd9ebad80d720e47121bf4dffbab4b062305b049
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9d9c67959bcc3f755bc2f18d5ec98878c4ae91e8badb87369712d753c806121
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8200deb16bd284ee66962ef05fbec5caa149c806fec01eec45b3f55dc1b55051
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d575f364f0a1afa678d4724cea0a0be66e4fabff8b185b15382b4f0348cc63b2
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:b872b9c17b5ed7998a69c31be8f411ab64d8d99058497fc3922cda8d8da62d04
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb2cb17dab95eb3bb9bd4a031d4c69e503bad212fdb6428957cba4c9379b4ded
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9cc9afc40ae76f2f926b71c9da93898c6c2dbabda4799eb06bafee0e79ecf534
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7939d63ae15dcda8a4554e22420e531df53536bad19c7f5c07022e8fb576181
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -28,3 +28,34 @@
28
  {"current_steps": 280, "total_steps": 882, "loss": 0.7883, "lr": 5e-06, "epoch": 0.9523809523809523, "percentage": 31.75, "elapsed_time": "4:29:42", "remaining_time": "9:39:51"}
29
  {"current_steps": 290, "total_steps": 882, "loss": 0.7865, "lr": 5e-06, "epoch": 0.9863945578231292, "percentage": 32.88, "elapsed_time": "4:39:20", "remaining_time": "9:30:13"}
30
  {"current_steps": 294, "total_steps": 882, "eval_loss": 0.787599503993988, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "4:48:22", "remaining_time": "9:36:44"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28
  {"current_steps": 280, "total_steps": 882, "loss": 0.7883, "lr": 5e-06, "epoch": 0.9523809523809523, "percentage": 31.75, "elapsed_time": "4:29:42", "remaining_time": "9:39:51"}
29
  {"current_steps": 290, "total_steps": 882, "loss": 0.7865, "lr": 5e-06, "epoch": 0.9863945578231292, "percentage": 32.88, "elapsed_time": "4:39:20", "remaining_time": "9:30:13"}
30
  {"current_steps": 294, "total_steps": 882, "eval_loss": 0.787599503993988, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "4:48:22", "remaining_time": "9:36:44"}
31
+ {"current_steps": 300, "total_steps": 882, "loss": 0.7746, "lr": 5e-06, "epoch": 1.0204081632653061, "percentage": 34.01, "elapsed_time": "4:55:18", "remaining_time": "9:32:53"}
32
+ {"current_steps": 310, "total_steps": 882, "loss": 0.7488, "lr": 5e-06, "epoch": 1.054421768707483, "percentage": 35.15, "elapsed_time": "5:04:57", "remaining_time": "9:22:41"}
33
+ {"current_steps": 320, "total_steps": 882, "loss": 0.7475, "lr": 5e-06, "epoch": 1.08843537414966, "percentage": 36.28, "elapsed_time": "5:14:36", "remaining_time": "9:12:31"}
34
+ {"current_steps": 330, "total_steps": 882, "loss": 0.7431, "lr": 5e-06, "epoch": 1.1224489795918366, "percentage": 37.41, "elapsed_time": "5:24:15", "remaining_time": "9:02:23"}
35
+ {"current_steps": 340, "total_steps": 882, "loss": 0.7462, "lr": 5e-06, "epoch": 1.1564625850340136, "percentage": 38.55, "elapsed_time": "5:33:54", "remaining_time": "8:52:17"}
36
+ {"current_steps": 350, "total_steps": 882, "loss": 0.747, "lr": 5e-06, "epoch": 1.1904761904761905, "percentage": 39.68, "elapsed_time": "5:43:33", "remaining_time": "8:42:12"}
37
+ {"current_steps": 360, "total_steps": 882, "loss": 0.7455, "lr": 5e-06, "epoch": 1.2244897959183674, "percentage": 40.82, "elapsed_time": "5:53:11", "remaining_time": "8:32:07"}
38
+ {"current_steps": 370, "total_steps": 882, "loss": 0.7406, "lr": 5e-06, "epoch": 1.2585034013605443, "percentage": 41.95, "elapsed_time": "6:02:49", "remaining_time": "8:22:03"}
39
+ {"current_steps": 380, "total_steps": 882, "loss": 0.7538, "lr": 5e-06, "epoch": 1.2925170068027212, "percentage": 43.08, "elapsed_time": "6:12:26", "remaining_time": "8:12:01"}
40
+ {"current_steps": 390, "total_steps": 882, "loss": 0.7458, "lr": 5e-06, "epoch": 1.3265306122448979, "percentage": 44.22, "elapsed_time": "6:22:05", "remaining_time": "8:02:01"}
41
+ {"current_steps": 400, "total_steps": 882, "loss": 0.7446, "lr": 5e-06, "epoch": 1.3605442176870748, "percentage": 45.35, "elapsed_time": "6:31:44", "remaining_time": "7:52:02"}
42
+ {"current_steps": 410, "total_steps": 882, "loss": 0.7497, "lr": 5e-06, "epoch": 1.3945578231292517, "percentage": 46.49, "elapsed_time": "6:41:22", "remaining_time": "7:42:04"}
43
+ {"current_steps": 420, "total_steps": 882, "loss": 0.7469, "lr": 5e-06, "epoch": 1.4285714285714286, "percentage": 47.62, "elapsed_time": "6:51:01", "remaining_time": "7:32:08"}
44
+ {"current_steps": 430, "total_steps": 882, "loss": 0.7424, "lr": 5e-06, "epoch": 1.4625850340136055, "percentage": 48.75, "elapsed_time": "7:00:40", "remaining_time": "7:22:11"}
45
+ {"current_steps": 440, "total_steps": 882, "loss": 0.7445, "lr": 5e-06, "epoch": 1.4965986394557822, "percentage": 49.89, "elapsed_time": "7:10:19", "remaining_time": "7:12:16"}
46
+ {"current_steps": 450, "total_steps": 882, "loss": 0.7492, "lr": 5e-06, "epoch": 1.5306122448979593, "percentage": 51.02, "elapsed_time": "7:19:58", "remaining_time": "7:02:22"}
47
+ {"current_steps": 460, "total_steps": 882, "loss": 0.7423, "lr": 5e-06, "epoch": 1.564625850340136, "percentage": 52.15, "elapsed_time": "7:29:36", "remaining_time": "6:52:28"}
48
+ {"current_steps": 470, "total_steps": 882, "loss": 0.7434, "lr": 5e-06, "epoch": 1.598639455782313, "percentage": 53.29, "elapsed_time": "7:39:14", "remaining_time": "6:42:34"}
49
+ {"current_steps": 480, "total_steps": 882, "loss": 0.7365, "lr": 5e-06, "epoch": 1.6326530612244898, "percentage": 54.42, "elapsed_time": "7:48:54", "remaining_time": "6:32:42"}
50
+ {"current_steps": 490, "total_steps": 882, "loss": 0.7421, "lr": 5e-06, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "7:58:33", "remaining_time": "6:22:50"}
51
+ {"current_steps": 500, "total_steps": 882, "loss": 0.7463, "lr": 5e-06, "epoch": 1.7006802721088436, "percentage": 56.69, "elapsed_time": "8:08:12", "remaining_time": "6:12:59"}
52
+ {"current_steps": 510, "total_steps": 882, "loss": 0.7376, "lr": 5e-06, "epoch": 1.7346938775510203, "percentage": 57.82, "elapsed_time": "8:17:51", "remaining_time": "6:03:08"}
53
+ {"current_steps": 520, "total_steps": 882, "loss": 0.7441, "lr": 5e-06, "epoch": 1.7687074829931972, "percentage": 58.96, "elapsed_time": "8:27:30", "remaining_time": "5:53:18"}
54
+ {"current_steps": 530, "total_steps": 882, "loss": 0.7431, "lr": 5e-06, "epoch": 1.8027210884353742, "percentage": 60.09, "elapsed_time": "8:37:08", "remaining_time": "5:43:27"}
55
+ {"current_steps": 540, "total_steps": 882, "loss": 0.7438, "lr": 5e-06, "epoch": 1.836734693877551, "percentage": 61.22, "elapsed_time": "8:46:47", "remaining_time": "5:33:37"}
56
+ {"current_steps": 550, "total_steps": 882, "loss": 0.7393, "lr": 5e-06, "epoch": 1.870748299319728, "percentage": 62.36, "elapsed_time": "8:56:26", "remaining_time": "5:23:49"}
57
+ {"current_steps": 560, "total_steps": 882, "loss": 0.7397, "lr": 5e-06, "epoch": 1.9047619047619047, "percentage": 63.49, "elapsed_time": "9:06:05", "remaining_time": "5:14:00"}
58
+ {"current_steps": 570, "total_steps": 882, "loss": 0.7397, "lr": 5e-06, "epoch": 1.9387755102040818, "percentage": 64.63, "elapsed_time": "9:15:45", "remaining_time": "5:04:12"}
59
+ {"current_steps": 580, "total_steps": 882, "loss": 0.7399, "lr": 5e-06, "epoch": 1.9727891156462585, "percentage": 65.76, "elapsed_time": "9:25:25", "remaining_time": "4:54:24"}
60
+ {"current_steps": 588, "total_steps": 882, "eval_loss": 0.7747776508331299, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "9:38:24", "remaining_time": "4:49:12"}
61
+ {"current_steps": 590, "total_steps": 882, "loss": 0.7322, "lr": 5e-06, "epoch": 2.006802721088435, "percentage": 66.89, "elapsed_time": "9:41:32", "remaining_time": "4:47:48"}