{
  "source": "artifacts/runs/feraoun-pro/best.pt",
  "source_contents": [
    "model",
    "optimizer",
    "rng",
    "state"
  ],
  "dropped_state": [
    "optimizer",
    "rng"
  ],
  "dropped_tied": [],
  "dropped_derived": [],
  "dropped_training_only": [
    "aux_decoder.decoder.layers.0.linear1.bias",
    "aux_decoder.decoder.layers.0.linear1.weight",
    "aux_decoder.decoder.layers.0.linear2.bias",
    "aux_decoder.decoder.layers.0.linear2.weight",
    "aux_decoder.decoder.layers.0.multihead_attn.in_proj_bias",
    "aux_decoder.decoder.layers.0.multihead_attn.in_proj_weight",
    "aux_decoder.decoder.layers.0.multihead_attn.out_proj.bias",
    "aux_decoder.decoder.layers.0.multihead_attn.out_proj.weight",
    "aux_decoder.decoder.layers.0.norm1.bias",
    "aux_decoder.decoder.layers.0.norm1.weight",
    "aux_decoder.decoder.layers.0.norm2.bias",
    "aux_decoder.decoder.layers.0.norm2.weight",
    "aux_decoder.decoder.layers.0.norm3.bias",
    "aux_decoder.decoder.layers.0.norm3.weight",
    "aux_decoder.decoder.layers.0.self_attn.in_proj_bias",
    "aux_decoder.decoder.layers.0.self_attn.in_proj_weight",
    "aux_decoder.decoder.layers.0.self_attn.out_proj.bias",
    "aux_decoder.decoder.layers.0.self_attn.out_proj.weight",
    "aux_decoder.decoder.layers.1.linear1.bias",
    "aux_decoder.decoder.layers.1.linear1.weight",
    "aux_decoder.decoder.layers.1.linear2.bias",
    "aux_decoder.decoder.layers.1.linear2.weight",
    "aux_decoder.decoder.layers.1.multihead_attn.in_proj_bias",
    "aux_decoder.decoder.layers.1.multihead_attn.in_proj_weight",
    "aux_decoder.decoder.layers.1.multihead_attn.out_proj.bias",
    "aux_decoder.decoder.layers.1.multihead_attn.out_proj.weight",
    "aux_decoder.decoder.layers.1.norm1.bias",
    "aux_decoder.decoder.layers.1.norm1.weight",
    "aux_decoder.decoder.layers.1.norm2.bias",
    "aux_decoder.decoder.layers.1.norm2.weight",
    "aux_decoder.decoder.layers.1.norm3.bias",
    "aux_decoder.decoder.layers.1.norm3.weight",
    "aux_decoder.decoder.layers.1.self_attn.in_proj_bias",
    "aux_decoder.decoder.layers.1.self_attn.in_proj_weight",
    "aux_decoder.decoder.layers.1.self_attn.out_proj.bias",
    "aux_decoder.decoder.layers.1.self_attn.out_proj.weight",
    "aux_decoder.embedding.weight",
    "aux_decoder.lm_head.bias",
    "aux_decoder.lm_head.weight"
  ],
  "tensors": 221,
  "parameters": 51572625,
  "files": [
    {
      "name": "README.md",
      "bytes": 13969,
      "sha256": "39d5914cdb53dcfd14aefcb7838e870cbd981600ac21ac3734934a0534b2007f"
    },
    {
      "name": "__init__.py",
      "bytes": 296,
      "sha256": "9ac3b94df93a57b0dac01996acc6e5ef217e016f117fbc97fd05c473d7dbfc84"
    },
    {
      "name": "config.json",
      "bytes": 2507,
      "sha256": "746ce438be8325339c8e5a0b0caddcbd20d1cab56386f13e0157d147ce3f65ab"
    },
    {
      "name": "configuration_feraoun_pro.py",
      "bytes": 2423,
      "sha256": "32020487761b9375e0a6931cfdfd39551bccd8c50939a39108bdc845036b8b8f"
    },
    {
      "name": "model.safetensors",
      "bytes": 206313076,
      "sha256": "dfc55395ed15b9d727eae16594ec7f87c8ef28fdc2e6d5f7bd6e88d7bbafe165"
    },
    {
      "name": "modeling_feraoun_pro.py",
      "bytes": 7590,
      "sha256": "7c8018a171eb4647453140103bf919f98d2860339a74d819ef1869865a239563"
    },
    {
      "name": "tokenizer.json",
      "bytes": 4764,
      "sha256": "350100049e4f193563065147c35fce2dbcc344cf98420e0fa209c4b668864c37"
    },
    {
      "name": "tokenizer_config.json",
      "bytes": 193,
      "sha256": "444cfded3d0102faf5c8bb4706f540becd8103ce7344ddbbad8df2da0928fa52"
    }
  ]
}