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
abea050
·
verified ·
1 Parent(s): cd8b574

Training in progress, epoch 3

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 +9 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bf0f04311e4d3974130d0591220488128c5f90383ca33aaac3bf2128c793df1
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daf2ad38cf675d0b1ea5b9c24fc26407670262b8bca00d6d050862ba80ec0aa6
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e7f8e190bf9d64c804b1cf91219d91006770bedc3dadc66058d344ddeaa3738
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2953d86cae5c49554dcca69b46d4a5359d98baa34c7c499b1adf03b3e2fb37b9
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:f4f5f930ee976374da88ab1f4343736994ff757e63003a2d136c9f1b125ca1fe
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e711bdb3d723651515e18332ccebec4d2e20d35cc70ddad7896888a2a47b947d
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4aeb230c99414c987ee577f00ba221b06a9b7df6885210d8b7511ceaf42ab659
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a43af810e2d62288f10e2840a2f83d2252fe18b17f4c63315b59b23a9249b909
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -106,3 +106,12 @@
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"}
 
 
 
 
 
 
 
 
 
 
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"}
109
+ {"current_steps": 1070, "total_steps": 1134, "loss": 0.7165, "lr": 5e-06, "epoch": 2.8306878306878307, "percentage": 94.36, "elapsed_time": "1:48:41", "remaining_time": "0:06:30"}
110
+ {"current_steps": 1080, "total_steps": 1134, "loss": 0.7147, "lr": 5e-06, "epoch": 2.857142857142857, "percentage": 95.24, "elapsed_time": "1:49:39", "remaining_time": "0:05:28"}
111
+ {"current_steps": 1090, "total_steps": 1134, "loss": 0.7146, "lr": 5e-06, "epoch": 2.8835978835978837, "percentage": 96.12, "elapsed_time": "1:50:37", "remaining_time": "0:04:27"}
112
+ {"current_steps": 1100, "total_steps": 1134, "loss": 0.7175, "lr": 5e-06, "epoch": 2.91005291005291, "percentage": 97.0, "elapsed_time": "1:51:36", "remaining_time": "0:03:26"}
113
+ {"current_steps": 1110, "total_steps": 1134, "loss": 0.7162, "lr": 5e-06, "epoch": 2.9365079365079367, "percentage": 97.88, "elapsed_time": "1:52:34", "remaining_time": "0:02:26"}
114
+ {"current_steps": 1120, "total_steps": 1134, "loss": 0.714, "lr": 5e-06, "epoch": 2.962962962962963, "percentage": 98.77, "elapsed_time": "1:53:33", "remaining_time": "0:01:25"}
115
+ {"current_steps": 1130, "total_steps": 1134, "loss": 0.7146, "lr": 5e-06, "epoch": 2.9894179894179893, "percentage": 99.65, "elapsed_time": "1:54:32", "remaining_time": "0:00:24"}
116
+ {"current_steps": 1134, "total_steps": 1134, "eval_loss": 0.7703806757926941, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:57:06", "remaining_time": "0:00:00"}
117
+ {"current_steps": 1134, "total_steps": 1134, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:58:37", "remaining_time": "0:00:00"}