imdatta0 commited on
Commit
6871817
·
verified ·
1 Parent(s): 11e8c58

Training in progress, step 16

Browse files
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
1
  {
2
+ "_name_or_path": "/home/ubuntu/llama_r1math_grpo_deepspeed/",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e482bc8112bba891e44b882eb20bb40d37800f98d799ca378eb94ffd9399067c
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d64929c0e62be2b795c7ba10c247bfb5705b358f472ccd2cf29301efb3dea14
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:fb5246694556c8410b1e5f1d203fa09593d802258f69e0b1e7e45235509c7a2e
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1372bec1259c1fc9e500f0b902dcdd09941879f1c52edd2381da695786dd3f9c
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1918dfe9bfc85325cf8ffc5b2d4b0fe83ba881d62782c0be0e9a94751b3b8f38
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fefe3969ec00b21fb8637d489962a6d62496c2f4bae7353e3f56a48a2e89da9c
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b8718584ff8f6b9edecb63f204845f0570e395258314208e74a466b7c9eb113
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31225bf9b42ea76c70a02e26ab1bfcd210e0d77609849ebdee5fd089a809c820
3
  size 1168138808
tokenizer_config.json CHANGED
@@ -2054,11 +2054,15 @@
2054
  "clean_up_tokenization_spaces": true,
2055
  "eos_token": "<|eot_id|>",
2056
  "extra_special_tokens": {},
 
2057
  "model_input_names": [
2058
  "input_ids",
2059
  "attention_mask"
2060
  ],
2061
  "model_max_length": 131072,
 
2062
  "pad_token": "<|reserved_special_token_0|>",
 
 
2063
  "tokenizer_class": "PreTrainedTokenizerFast"
2064
  }
 
2054
  "clean_up_tokenization_spaces": true,
2055
  "eos_token": "<|eot_id|>",
2056
  "extra_special_tokens": {},
2057
+ "max_length": null,
2058
  "model_input_names": [
2059
  "input_ids",
2060
  "attention_mask"
2061
  ],
2062
  "model_max_length": 131072,
2063
+ "pad_to_multiple_of": null,
2064
  "pad_token": "<|reserved_special_token_0|>",
2065
+ "pad_token_type_id": 0,
2066
+ "padding_side": "left",
2067
  "tokenizer_class": "PreTrainedTokenizerFast"
2068
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a454ab36f976f70255ab7afa5520734206a990c323f43d55fe5e2e02f4821ed2
3
  size 7672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1af291767493af3eab35139a2601f95a2759a8336fbd5310a0ed5843bad536c7
3
  size 7672