Training in progress, step 16
Browse files- config.json +1 -1
- model-00001-of-00004.safetensors +1 -1
- model-00002-of-00004.safetensors +1 -1
- model-00003-of-00004.safetensors +1 -1
- model-00004-of-00004.safetensors +1 -1
- tokenizer_config.json +4 -0
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
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:
|
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:
|
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:
|
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:
|
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:
|
3 |
size 7672
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1af291767493af3eab35139a2601f95a2759a8336fbd5310a0ed5843bad536c7
|
3 |
size 7672
|