Training in progress, epoch 2, checkpoint
Browse files- checkpoint-1373760/config.json +24 -0
- checkpoint-1373760/optimizer.pt +3 -0
- checkpoint-1373760/pytorch_model.bin +3 -0
- checkpoint-1373760/rng_state.pth +3 -0
- checkpoint-1373760/scheduler.pt +3 -0
- checkpoint-1373760/special_tokens_map.json +5 -0
- checkpoint-1373760/tokenizer.json +0 -0
- checkpoint-1373760/tokenizer_config.json +12 -0
- checkpoint-1373760/trainer_state.json +0 -0
- checkpoint-1373760/training_args.bin +3 -0
    	
        checkpoint-1373760/config.json
    ADDED
    
    | @@ -0,0 +1,24 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "architectures": [
         | 
| 3 | 
            +
                "RNNForLanguageModeling"
         | 
| 4 | 
            +
              ],
         | 
| 5 | 
            +
              "bidirectional": false,
         | 
| 6 | 
            +
              "dropout_p": 0.1,
         | 
| 7 | 
            +
              "emb_init_range": 0.1,
         | 
| 8 | 
            +
              "embedding_dim": 1024,
         | 
| 9 | 
            +
              "embedding_kwargs": {},
         | 
| 10 | 
            +
              "hidden_dim": 1024,
         | 
| 11 | 
            +
              "lin_init_range": 0.03125,
         | 
| 12 | 
            +
              "lm_in_features": 1024,
         | 
| 13 | 
            +
              "model_type": "rnn",
         | 
| 14 | 
            +
              "num_layers": 2,
         | 
| 15 | 
            +
              "output_last_state": false,
         | 
| 16 | 
            +
              "output_recurrent_outputs": false,
         | 
| 17 | 
            +
              "recur_init_range": 0.03125,
         | 
| 18 | 
            +
              "rnn_kwargs": {},
         | 
| 19 | 
            +
              "rnn_type": "LSTM",
         | 
| 20 | 
            +
              "tie_weights": true,
         | 
| 21 | 
            +
              "torch_dtype": "float32",
         | 
| 22 | 
            +
              "transformers_version": "4.33.3",
         | 
| 23 | 
            +
              "vocab_size": 50002
         | 
| 24 | 
            +
            }
         | 
    	
        checkpoint-1373760/optimizer.pt
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:7030cd88e47a0b9bdadf314812ea07fbbd2fe3106dec20f72aa76dd8d8efb6df
         | 
| 3 | 
            +
            size 544373707
         | 
    	
        checkpoint-1373760/pytorch_model.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:81f4ca660305195373eba5240ce24fd9c0f6c2ec373f73407dd57ff63b04ab66
         | 
| 3 | 
            +
            size 272184705
         | 
    	
        checkpoint-1373760/rng_state.pth
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:0efd0c5d663a3bdeb071359fabdb090b5800fdbe3bb0ca5cc5a075a4d186a58a
         | 
| 3 | 
            +
            size 14511
         | 
    	
        checkpoint-1373760/scheduler.pt
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:edb751c373a8bfc88e1cb36b82d18091e66771e1d89dc289ff8953481ce5a115
         | 
| 3 | 
            +
            size 627
         | 
    	
        checkpoint-1373760/special_tokens_map.json
    ADDED
    
    | @@ -0,0 +1,5 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "eos_token": "<eos>",
         | 
| 3 | 
            +
              "pad_token": "<pad>",
         | 
| 4 | 
            +
              "unk_token": "<unk>"
         | 
| 5 | 
            +
            }
         | 
    	
        checkpoint-1373760/tokenizer.json
    ADDED
    
    | The diff for this file is too large to render. 
		See raw diff | 
|  | 
    	
        checkpoint-1373760/tokenizer_config.json
    ADDED
    
    | @@ -0,0 +1,12 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "clean_up_tokenization_spaces": true,
         | 
| 3 | 
            +
              "eos_token": "<eos>",
         | 
| 4 | 
            +
              "max_length": null,
         | 
| 5 | 
            +
              "model_max_length": 512,
         | 
| 6 | 
            +
              "pad_to_multiple_of": null,
         | 
| 7 | 
            +
              "pad_token": "<pad>",
         | 
| 8 | 
            +
              "pad_token_type_id": 0,
         | 
| 9 | 
            +
              "padding_side": "right",
         | 
| 10 | 
            +
              "tokenizer_class": "PreTrainedTokenizerFast",
         | 
| 11 | 
            +
              "unk_token": "<unk>"
         | 
| 12 | 
            +
            }
         | 
    	
        checkpoint-1373760/trainer_state.json
    ADDED
    
    | The diff for this file is too large to render. 
		See raw diff | 
|  | 
    	
        checkpoint-1373760/training_args.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:143c1383e3fa6d90917a5942ecf47b62aab8f123ed6af7622b00509c33fd6258
         | 
| 3 | 
            +
            size 4219
         | 
