Hugging Face's logo

mlfoundations-dev
/
llama2_oh_teknium_scaling_down_random_0.1

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
 Community
sedrickkeh commited on
Commit
4feaf88
·
verified ·
1 Parent(s): c7b256f

Training in progress, epoch 2

Browse files
Files changed (4) hide show
  1. model-00001-of-00003.safetensors +1 -1
  2. model-00002-of-00003.safetensors +1 -1
  3. model-00003-of-00003.safetensors +1 -1
  4. trainer_log.jsonl +6 -0
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38f4d97b123f3c2dae75e910c7affd0d671fade69ad90b62bd9bc1b776802c6b
3
  size 4938985352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:647dc8c1c9830aba790c957b605e25dc1f6d49a88165fe62e0a427dd22f1ab1b
3
  size 4938985352
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dea9bcf67293726b3d0b36faf716aa504156bf6ffad434c30b3e78e8e513eef9
3
  size 4947390880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a7bb3403227ca0e1f48b6519e24c0483f475eb9c2cfe9356a70424f294e3906
3
  size 4947390880
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c7a1b6d1d45e72f7a15129918fb23cfbc328045063b920b9c0fc8219256f9d7
3
  size 3590488816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0deffb4fb2734d400ca6bc4651469c8bd0f8619e74127c4853c4a547799807a
3
  size 3590488816
trainer_log.jsonl CHANGED
@@ -9,3 +9,9 @@
9
  {"current_steps": 80, "total_steps": 135, "loss": 0.4344, "lr": 5e-06, "epoch": 1.7728531855955678, "percentage": 59.26, "elapsed_time": "1:14:28", "remaining_time": "0:51:12"}
10
  {"current_steps": 90, "total_steps": 135, "loss": 0.4264, "lr": 5e-06, "epoch": 1.994459833795014, "percentage": 66.67, "elapsed_time": "1:23:34", "remaining_time": "0:41:47"}
11
  {"current_steps": 90, "total_steps": 135, "eval_loss": 0.44181302189826965, "epoch": 1.994459833795014, "percentage": 66.67, "elapsed_time": "1:24:32", "remaining_time": "0:42:16"}
 
 
 
 
 
 
 
9
  {"current_steps": 80, "total_steps": 135, "loss": 0.4344, "lr": 5e-06, "epoch": 1.7728531855955678, "percentage": 59.26, "elapsed_time": "1:14:28", "remaining_time": "0:51:12"}
10
  {"current_steps": 90, "total_steps": 135, "loss": 0.4264, "lr": 5e-06, "epoch": 1.994459833795014, "percentage": 66.67, "elapsed_time": "1:23:34", "remaining_time": "0:41:47"}
11
  {"current_steps": 90, "total_steps": 135, "eval_loss": 0.44181302189826965, "epoch": 1.994459833795014, "percentage": 66.67, "elapsed_time": "1:24:32", "remaining_time": "0:42:16"}
12
+ {"current_steps": 100, "total_steps": 135, "loss": 0.4405, "lr": 5e-06, "epoch": 2.21606648199446, "percentage": 74.07, "elapsed_time": "1:34:27", "remaining_time": "0:33:03"}
13
+ {"current_steps": 110, "total_steps": 135, "loss": 0.401, "lr": 5e-06, "epoch": 2.4376731301939056, "percentage": 81.48, "elapsed_time": "1:43:32", "remaining_time": "0:23:31"}
14
+ {"current_steps": 120, "total_steps": 135, "loss": 0.3954, "lr": 5e-06, "epoch": 2.6592797783933517, "percentage": 88.89, "elapsed_time": "1:52:37", "remaining_time": "0:14:04"}
15
+ {"current_steps": 130, "total_steps": 135, "loss": 0.3849, "lr": 5e-06, "epoch": 2.880886426592798, "percentage": 96.3, "elapsed_time": "2:01:42", "remaining_time": "0:04:40"}
16
+ {"current_steps": 135, "total_steps": 135, "eval_loss": 0.4231138229370117, "epoch": 2.9916897506925206, "percentage": 100.0, "elapsed_time": "2:08:03", "remaining_time": "0:00:00"}
17
+ {"current_steps": 135, "total_steps": 135, "epoch": 2.9916897506925206, "percentage": 100.0, "elapsed_time": "2:09:06", "remaining_time": "0:00:00"}