Hugging Face's logo

mlfoundations-dev
/
llama3-1_8b_math_375000_samples

Safetensors
llama
Model card Files Community
gsmyrnis commited on
Commit
6fc80c7
·
verified ·
1 Parent(s): e4d6341

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 +4 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a40c7999c1a87223cfd7f4c5ce50c8202233918bc1aaae8853b83f606edb6bab
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:deccc8e2f7e261725817ab9129566691cd8db2bd7efcdc9d22feafc7daa3c24e
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:635343d24e89e376722ac2bd2bb8759d6fdabb7e216e277a5de3f68245a5f697
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6c5849e535f2ff5ea1025f2900d7114b04b326f4507018512348c0cfd747270
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41a46523a75364ad875f3fe6e6ec7a3feb0a910d9384b0130a19c98acc9c2466
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75a1c48669d043d08290afb5665453c66be2fb7ff69b4af5da5b92584541605d
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c37ed02ad04e3aa9b43b38787562d997a7d8f0967ed7737647bacdbeb8f4b45
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d658c5b858c7392707b92b0df36ed14999a32a2e274a924dd49a3677def856c8
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -94,3 +94,7 @@
94
  {"current_steps": 920, "total_steps": 960, "loss": 0.471, "lr": 5e-06, "epoch": 2.875, "percentage": 95.83, "elapsed_time": "1:34:50", "remaining_time": "0:04:07"}
95
  {"current_steps": 930, "total_steps": 960, "loss": 0.4706, "lr": 5e-06, "epoch": 2.90625, "percentage": 96.88, "elapsed_time": "1:35:50", "remaining_time": "0:03:05"}
96
  {"current_steps": 940, "total_steps": 960, "loss": 0.4756, "lr": 5e-06, "epoch": 2.9375, "percentage": 97.92, "elapsed_time": "1:36:49", "remaining_time": "0:02:03"}
 
 
 
 
 
94
  {"current_steps": 920, "total_steps": 960, "loss": 0.471, "lr": 5e-06, "epoch": 2.875, "percentage": 95.83, "elapsed_time": "1:34:50", "remaining_time": "0:04:07"}
95
  {"current_steps": 930, "total_steps": 960, "loss": 0.4706, "lr": 5e-06, "epoch": 2.90625, "percentage": 96.88, "elapsed_time": "1:35:50", "remaining_time": "0:03:05"}
96
  {"current_steps": 940, "total_steps": 960, "loss": 0.4756, "lr": 5e-06, "epoch": 2.9375, "percentage": 97.92, "elapsed_time": "1:36:49", "remaining_time": "0:02:03"}
97
+ {"current_steps": 950, "total_steps": 960, "loss": 0.4745, "lr": 5e-06, "epoch": 2.96875, "percentage": 98.96, "elapsed_time": "1:37:49", "remaining_time": "0:01:01"}
98
+ {"current_steps": 960, "total_steps": 960, "loss": 0.473, "lr": 5e-06, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:38:48", "remaining_time": "0:00:00"}
99
+ {"current_steps": 960, "total_steps": 960, "eval_loss": 0.5187644362449646, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:40:45", "remaining_time": "0:00:00"}
100
+ {"current_steps": 960, "total_steps": 960, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:42:02", "remaining_time": "0:00:00"}