odats commited on
Commit
ce04d36
·
verified ·
1 Parent(s): 38d0952

Training in progress, step 6100

Browse files
README.md CHANGED
@@ -27,7 +27,7 @@ print(output["generated_text"])
27
 
28
  ## Training procedure
29
 
30
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/oleg-dats/nmt/runs/yn1sslos)
31
 
32
 
33
  This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
@@ -35,7 +35,7 @@ This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing
35
  ### Framework versions
36
 
37
  - TRL: 0.23.1
38
- - Transformers: 4.57.0
39
  - Pytorch: 2.5.1+cu124
40
  - Datasets: 4.1.1
41
  - Tokenizers: 0.22.1
 
27
 
28
  ## Training procedure
29
 
30
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/oleg-dats/nmt/runs/syf13vuv)
31
 
32
 
33
  This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
 
35
  ### Framework versions
36
 
37
  - TRL: 0.23.1
38
+ - Transformers: 4.56.2
39
  - Pytorch: 2.5.1+cu124
40
  - Datasets: 4.1.1
41
  - Tokenizers: 0.22.1
config.json CHANGED
@@ -73,11 +73,10 @@
73
  },
74
  "rope_theta": 1000000.0,
75
  "sliding_window": 1024,
76
- "use_bidirectional_attention": false,
77
  "use_cache": true,
78
  "vocab_size": 262208
79
  },
80
- "transformers_version": "4.57.0",
81
  "vision_config": {
82
  "attention_dropout": 0.0,
83
  "hidden_act": "gelu_pytorch_tanh",
 
73
  },
74
  "rope_theta": 1000000.0,
75
  "sliding_window": 1024,
 
76
  "use_cache": true,
77
  "vocab_size": 262208
78
  },
79
+ "transformers_version": "4.56.2",
80
  "vision_config": {
81
  "attention_dropout": 0.0,
82
  "hidden_act": "gelu_pytorch_tanh",
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a653ce67ccca35b508e079bb5328530c791b3e71f267b172865041b6b04e88e
3
  size 4961251752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef73b40167933e937d4a83f4f03717856fcf4a1e853b03ee8ff3f82eb7c62ee7
3
  size 4961251752
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24d395bd995ee0eb269aab4db2c4197c2515af165dc9f1c94bbc3314f2dace51
3
  size 3639026128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:409583ebe05c45beb3cfc21c3c7a6eb810ecf46d500b5ef108188174edcf2060
3
  size 3639026128
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54eac288f57ef58be29ddb0e8adea9bc712650afeaf8d7d4f42255c44a942cbb
3
- size 6840
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1962c6464b1c9286492998d5209bebd4b71eaeb55518cd47e972fb26d1807131
3
+ size 6776