Hugging Face's logo

mlfoundations-dev
/
llama3-1_8b_physics_500000_samples

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
gsmyrnis commited on
Commit
cd8b574
·
verified ·
1 Parent(s): c0bbdba

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 +39 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6c5857dd8d7bf751a51ed832110e144c05d1252501eb3c516edd411e0e880da
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bf0f04311e4d3974130d0591220488128c5f90383ca33aaac3bf2128c793df1
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:10ce8bcabaa7c5d3d48e7527852f2cd42e57c92af3b1e34043cfe5b2af29d03a
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e7f8e190bf9d64c804b1cf91219d91006770bedc3dadc66058d344ddeaa3738
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8bd8615d3e81eaf46656f678ae4d9564af7bb3df87edacbad8367720d07bb409
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4f5f930ee976374da88ab1f4343736994ff757e63003a2d136c9f1b125ca1fe
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:a1436cafb42c114e82eae1e28fc1e9494069b4b291756f9c9fadbddbf6d48e4a
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4aeb230c99414c987ee577f00ba221b06a9b7df6885210d8b7511ceaf42ab659
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -67,3 +67,42 @@
67
  {"current_steps": 660, "total_steps": 1134, "loss": 0.7488, "lr": 5e-06, "epoch": 1.746031746031746, "percentage": 58.2, "elapsed_time": "1:06:25", "remaining_time": "0:47:42"}
68
  {"current_steps": 670, "total_steps": 1134, "loss": 0.7484, "lr": 5e-06, "epoch": 1.7724867724867726, "percentage": 59.08, "elapsed_time": "1:07:24", "remaining_time": "0:46:40"}
69
  {"current_steps": 680, "total_steps": 1134, "loss": 0.7425, "lr": 5e-06, "epoch": 1.798941798941799, "percentage": 59.96, "elapsed_time": "1:08:22", "remaining_time": "0:45:39"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
67
  {"current_steps": 660, "total_steps": 1134, "loss": 0.7488, "lr": 5e-06, "epoch": 1.746031746031746, "percentage": 58.2, "elapsed_time": "1:06:25", "remaining_time": "0:47:42"}
68
  {"current_steps": 670, "total_steps": 1134, "loss": 0.7484, "lr": 5e-06, "epoch": 1.7724867724867726, "percentage": 59.08, "elapsed_time": "1:07:24", "remaining_time": "0:46:40"}
69
  {"current_steps": 680, "total_steps": 1134, "loss": 0.7425, "lr": 5e-06, "epoch": 1.798941798941799, "percentage": 59.96, "elapsed_time": "1:08:22", "remaining_time": "0:45:39"}
70
+ {"current_steps": 690, "total_steps": 1134, "loss": 0.7481, "lr": 5e-06, "epoch": 1.8253968253968254, "percentage": 60.85, "elapsed_time": "1:09:20", "remaining_time": "0:44:37"}
71
+ {"current_steps": 700, "total_steps": 1134, "loss": 0.7427, "lr": 5e-06, "epoch": 1.8518518518518519, "percentage": 61.73, "elapsed_time": "1:10:19", "remaining_time": "0:43:35"}
72
+ {"current_steps": 710, "total_steps": 1134, "loss": 0.7468, "lr": 5e-06, "epoch": 1.8783068783068781, "percentage": 62.61, "elapsed_time": "1:11:17", "remaining_time": "0:42:34"}
73
+ {"current_steps": 720, "total_steps": 1134, "loss": 0.7411, "lr": 5e-06, "epoch": 1.9047619047619047, "percentage": 63.49, "elapsed_time": "1:12:15", "remaining_time": "0:41:33"}
74
+ {"current_steps": 730, "total_steps": 1134, "loss": 0.7445, "lr": 5e-06, "epoch": 1.9312169312169312, "percentage": 64.37, "elapsed_time": "1:13:14", "remaining_time": "0:40:31"}
75
+ {"current_steps": 740, "total_steps": 1134, "loss": 0.746, "lr": 5e-06, "epoch": 1.9576719576719577, "percentage": 65.26, "elapsed_time": "1:14:13", "remaining_time": "0:39:31"}
76
+ {"current_steps": 750, "total_steps": 1134, "loss": 0.7439, "lr": 5e-06, "epoch": 1.9841269841269842, "percentage": 66.14, "elapsed_time": "1:15:12", "remaining_time": "0:38:30"}
77
+ {"current_steps": 756, "total_steps": 1134, "eval_loss": 0.7724016904830933, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:16:24", "remaining_time": "0:38:12"}
78
+ {"current_steps": 760, "total_steps": 1134, "loss": 0.7315, "lr": 5e-06, "epoch": 2.0105820105820107, "percentage": 67.02, "elapsed_time": "1:18:30", "remaining_time": "0:38:37"}
79
+ {"current_steps": 770, "total_steps": 1134, "loss": 0.7084, "lr": 5e-06, "epoch": 2.037037037037037, "percentage": 67.9, "elapsed_time": "1:19:28", "remaining_time": "0:37:34"}
80
+ {"current_steps": 780, "total_steps": 1134, "loss": 0.7103, "lr": 5e-06, "epoch": 2.0634920634920633, "percentage": 68.78, "elapsed_time": "1:20:26", "remaining_time": "0:36:30"}
81
+ {"current_steps": 790, "total_steps": 1134, "loss": 0.7106, "lr": 5e-06, "epoch": 2.0899470899470898, "percentage": 69.66, "elapsed_time": "1:21:25", "remaining_time": "0:35:27"}
82
+ {"current_steps": 800, "total_steps": 1134, "loss": 0.7103, "lr": 5e-06, "epoch": 2.1164021164021163, "percentage": 70.55, "elapsed_time": "1:22:23", "remaining_time": "0:34:23"}
83
+ {"current_steps": 810, "total_steps": 1134, "loss": 0.7118, "lr": 5e-06, "epoch": 2.142857142857143, "percentage": 71.43, "elapsed_time": "1:23:21", "remaining_time": "0:33:20"}
84
+ {"current_steps": 820, "total_steps": 1134, "loss": 0.7117, "lr": 5e-06, "epoch": 2.1693121693121693, "percentage": 72.31, "elapsed_time": "1:24:19", "remaining_time": "0:32:17"}
85
+ {"current_steps": 830, "total_steps": 1134, "loss": 0.7115, "lr": 5e-06, "epoch": 2.195767195767196, "percentage": 73.19, "elapsed_time": "1:25:17", "remaining_time": "0:31:14"}
86
+ {"current_steps": 840, "total_steps": 1134, "loss": 0.7116, "lr": 5e-06, "epoch": 2.2222222222222223, "percentage": 74.07, "elapsed_time": "1:26:16", "remaining_time": "0:30:11"}
87
+ {"current_steps": 850, "total_steps": 1134, "loss": 0.7132, "lr": 5e-06, "epoch": 2.248677248677249, "percentage": 74.96, "elapsed_time": "1:27:15", "remaining_time": "0:29:09"}
88
+ {"current_steps": 860, "total_steps": 1134, "loss": 0.7156, "lr": 5e-06, "epoch": 2.2751322751322753, "percentage": 75.84, "elapsed_time": "1:28:13", "remaining_time": "0:28:06"}
89
+ {"current_steps": 870, "total_steps": 1134, "loss": 0.7134, "lr": 5e-06, "epoch": 2.3015873015873014, "percentage": 76.72, "elapsed_time": "1:29:11", "remaining_time": "0:27:03"}
90
+ {"current_steps": 880, "total_steps": 1134, "loss": 0.7182, "lr": 5e-06, "epoch": 2.328042328042328, "percentage": 77.6, "elapsed_time": "1:30:09", "remaining_time": "0:26:01"}
91
+ {"current_steps": 890, "total_steps": 1134, "loss": 0.7152, "lr": 5e-06, "epoch": 2.3544973544973544, "percentage": 78.48, "elapsed_time": "1:31:08", "remaining_time": "0:24:59"}
92
+ {"current_steps": 900, "total_steps": 1134, "loss": 0.7164, "lr": 5e-06, "epoch": 2.380952380952381, "percentage": 79.37, "elapsed_time": "1:32:06", "remaining_time": "0:23:56"}
93
+ {"current_steps": 910, "total_steps": 1134, "loss": 0.7169, "lr": 5e-06, "epoch": 2.4074074074074074, "percentage": 80.25, "elapsed_time": "1:33:05", "remaining_time": "0:22:54"}
94
+ {"current_steps": 920, "total_steps": 1134, "loss": 0.7134, "lr": 5e-06, "epoch": 2.433862433862434, "percentage": 81.13, "elapsed_time": "1:34:03", "remaining_time": "0:21:52"}
95
+ {"current_steps": 930, "total_steps": 1134, "loss": 0.714, "lr": 5e-06, "epoch": 2.4603174603174605, "percentage": 82.01, "elapsed_time": "1:35:02", "remaining_time": "0:20:50"}
96
+ {"current_steps": 940, "total_steps": 1134, "loss": 0.7119, "lr": 5e-06, "epoch": 2.4867724867724865, "percentage": 82.89, "elapsed_time": "1:36:00", "remaining_time": "0:19:48"}
97
+ {"current_steps": 950, "total_steps": 1134, "loss": 0.7164, "lr": 5e-06, "epoch": 2.5132275132275135, "percentage": 83.77, "elapsed_time": "1:36:58", "remaining_time": "0:18:46"}
98
+ {"current_steps": 960, "total_steps": 1134, "loss": 0.7176, "lr": 5e-06, "epoch": 2.5396825396825395, "percentage": 84.66, "elapsed_time": "1:37:56", "remaining_time": "0:17:45"}
99
+ {"current_steps": 970, "total_steps": 1134, "loss": 0.718, "lr": 5e-06, "epoch": 2.566137566137566, "percentage": 85.54, "elapsed_time": "1:38:56", "remaining_time": "0:16:43"}
100
+ {"current_steps": 980, "total_steps": 1134, "loss": 0.7158, "lr": 5e-06, "epoch": 2.5925925925925926, "percentage": 86.42, "elapsed_time": "1:39:55", "remaining_time": "0:15:42"}
101
+ {"current_steps": 990, "total_steps": 1134, "loss": 0.7152, "lr": 5e-06, "epoch": 2.619047619047619, "percentage": 87.3, "elapsed_time": "1:40:54", "remaining_time": "0:14:40"}
102
+ {"current_steps": 1000, "total_steps": 1134, "loss": 0.7167, "lr": 5e-06, "epoch": 2.6455026455026456, "percentage": 88.18, "elapsed_time": "1:41:52", "remaining_time": "0:13:39"}
103
+ {"current_steps": 1010, "total_steps": 1134, "loss": 0.7143, "lr": 5e-06, "epoch": 2.671957671957672, "percentage": 89.07, "elapsed_time": "1:42:50", "remaining_time": "0:12:37"}
104
+ {"current_steps": 1020, "total_steps": 1134, "loss": 0.7201, "lr": 5e-06, "epoch": 2.6984126984126986, "percentage": 89.95, "elapsed_time": "1:43:49", "remaining_time": "0:11:36"}
105
+ {"current_steps": 1030, "total_steps": 1134, "loss": 0.7151, "lr": 5e-06, "epoch": 2.7248677248677247, "percentage": 90.83, "elapsed_time": "1:44:47", "remaining_time": "0:10:34"}
106
+ {"current_steps": 1040, "total_steps": 1134, "loss": 0.7113, "lr": 5e-06, "epoch": 2.751322751322751, "percentage": 91.71, "elapsed_time": "1:45:45", "remaining_time": "0:09:33"}
107
+ {"current_steps": 1050, "total_steps": 1134, "loss": 0.7153, "lr": 5e-06, "epoch": 2.7777777777777777, "percentage": 92.59, "elapsed_time": "1:46:44", "remaining_time": "0:08:32"}
108
+ {"current_steps": 1060, "total_steps": 1134, "loss": 0.7147, "lr": 5e-06, "epoch": 2.804232804232804, "percentage": 93.47, "elapsed_time": "1:47:43", "remaining_time": "0:07:31"}