Hugging Face's logo

nileshmalpeddi
/
ppo

Text Generation
Transformers
TensorBoard
Safetensors
exaone
Generated from Trainer
conversational
custom_code
Model card Files
xet
Metrics Community
nileshmalpeddi commited on
Commit
db1ff91
·
verified ·
1 Parent(s): 69de038

Training in progress, step 500

Browse files
Files changed (5) hide show
  1. config.json +3 -3
  2. model.safetensors +2 -2
  3. runs/Mar06_16-46-00_bizon3/events.out.tfevents.1741308444.bizon3.2149916.0 +3 -0
  4. tokenizer.json +6 -1
  5. training_args.bin +1 -1
config.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
- "_name_or_path": "/home/edgeai/DeepSpeedExamples/training/autotuning/hf/gpt2-large/saved_based_exaone_block1024_Batch1_Rank28_last_layer_save/",
3
  "activation_function": "silu",
4
  "architectures": [
5
  "ExaoneTDForCausalLM"
6
  ],
7
  "attention_dropout": 0.0,
8
  "auto_map": {
9
- "AutoConfig": "configuration_exaone.ExaoneConfig",
10
  "AutoModelForCausalLM": "LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct--modeling_exaone.ExaoneForCausalLM",
11
  "AutoModelForSequenceClassification": "LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct--modeling_exaone.ExaoneForSequenceClassification"
12
  },
@@ -32,7 +32,7 @@
32
  "rope_type": "llama3"
33
  },
34
  "rope_theta": 1000000,
35
- "torch_dtype": "bfloat16",
36
  "transformers_version": "4.48.2",
37
  "use_cache": true,
38
  "vocab_size": 102400
 
1
  {
2
+ "_name_or_path": "/home/edgeai/rlhf/EXAONE_Decomposition/saved_based_exaone_block1024_Batch1_Rank28_last_layer_save",
3
  "activation_function": "silu",
4
  "architectures": [
5
  "ExaoneTDForCausalLM"
6
  ],
7
  "attention_dropout": 0.0,
8
  "auto_map": {
9
+ "AutoConfig": "LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct--configuration_exaone.ExaoneConfig",
10
  "AutoModelForCausalLM": "LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct--modeling_exaone.ExaoneForCausalLM",
11
  "AutoModelForSequenceClassification": "LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct--modeling_exaone.ExaoneForSequenceClassification"
12
  },
 
32
  "rope_type": "llama3"
33
  },
34
  "rope_theta": 1000000,
35
+ "torch_dtype": "float16",
36
  "transformers_version": "4.48.2",
37
  "use_cache": true,
38
  "vocab_size": 102400
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25648d41b9c4841adda4184fcc5469ff03a925525b5b09785894013cab8629ae
3
- size 634692008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2923be8ed2dbeefaa47b41012388622f63d58024e3e609fbe71e5563ebfb763b
3
+ size 634690960
runs/Mar06_16-46-00_bizon3/events.out.tfevents.1741308444.bizon3.2149916.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a9ee2cf25e5d42545e722811d698e93c27239ed09c2e82c026fd8bdd7132d1f
3
+ size 534292
tokenizer.json CHANGED
@@ -1,6 +1,11 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 256,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
  "padding": null,
10
  "added_tokens": [
11
  {
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:356ad0a2f4757b2366d7565d0d097a2fbe122abbb7914bbd6acf189a1bd315b1
3
  size 7480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00aec0357b99ec54ee52e47674ca67ee2873f77aa26885becdd6728a1c140625
3
  size 7480