Safetensors
llama
vananh0905 commited on
Commit
df20e41
1 Parent(s): 7f07a02

Upload 10 files

Browse files
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_loss": 1.0952651500701904,
4
+ "eval_runtime": 163.6144,
5
+ "eval_samples": 40979,
6
+ "eval_samples_per_second": 24.491,
7
+ "eval_steps_per_second": 0.513,
8
+ "train_loss": 0.34447823324152127,
9
+ "train_runtime": 12106.1256,
10
+ "train_samples": 368811,
11
+ "train_samples_per_second": 14.719,
12
+ "train_steps_per_second": 0.46
13
+ }
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "./deepseek-7b-ft-full/checkpoint-5425",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
1
  {
2
+ "_name_or_path": "/cm/shared/anhdtv7/mainframe_gpt/data/deepseek-7b-ft-full/checkpoint-5425",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_loss": 1.0952651500701904,
4
+ "eval_runtime": 163.6144,
5
+ "eval_samples": 40979,
6
+ "eval_samples_per_second": 24.491,
7
+ "eval_steps_per_second": 0.513
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_loss": 0.34447823324152127,
4
+ "train_runtime": 12106.1256,
5
+ "train_samples": 368811,
6
+ "train_samples_per_second": 14.719,
7
+ "train_steps_per_second": 0.46
8
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3653101cf90e5c42348d4a07963a73cc9b42f82845e5a4ad7d931487eaad4f3a
3
+ size 5880