Training in progress, epoch 1
Browse files
    	
        .gitignore
    ADDED
    
    | @@ -0,0 +1 @@ | |
|  | 
|  | |
| 1 | 
            +
            checkpoint-*/
         | 
    	
        config.json
    ADDED
    
    | @@ -0,0 +1,61 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "_name_or_path": "google/flan-t5-base",
         | 
| 3 | 
            +
              "architectures": [
         | 
| 4 | 
            +
                "T5ForConditionalGeneration"
         | 
| 5 | 
            +
              ],
         | 
| 6 | 
            +
              "d_ff": 2048,
         | 
| 7 | 
            +
              "d_kv": 64,
         | 
| 8 | 
            +
              "d_model": 768,
         | 
| 9 | 
            +
              "decoder_start_token_id": 0,
         | 
| 10 | 
            +
              "dense_act_fn": "gelu_new",
         | 
| 11 | 
            +
              "dropout_rate": 0.1,
         | 
| 12 | 
            +
              "eos_token_id": 1,
         | 
| 13 | 
            +
              "feed_forward_proj": "gated-gelu",
         | 
| 14 | 
            +
              "initializer_factor": 1.0,
         | 
| 15 | 
            +
              "is_encoder_decoder": true,
         | 
| 16 | 
            +
              "is_gated_act": true,
         | 
| 17 | 
            +
              "layer_norm_epsilon": 1e-06,
         | 
| 18 | 
            +
              "model_type": "t5",
         | 
| 19 | 
            +
              "n_positions": 512,
         | 
| 20 | 
            +
              "num_decoder_layers": 12,
         | 
| 21 | 
            +
              "num_heads": 12,
         | 
| 22 | 
            +
              "num_layers": 12,
         | 
| 23 | 
            +
              "output_past": true,
         | 
| 24 | 
            +
              "pad_token_id": 0,
         | 
| 25 | 
            +
              "relative_attention_max_distance": 128,
         | 
| 26 | 
            +
              "relative_attention_num_buckets": 32,
         | 
| 27 | 
            +
              "task_specific_params": {
         | 
| 28 | 
            +
                "summarization": {
         | 
| 29 | 
            +
                  "early_stopping": true,
         | 
| 30 | 
            +
                  "length_penalty": 2.0,
         | 
| 31 | 
            +
                  "max_length": 200,
         | 
| 32 | 
            +
                  "min_length": 30,
         | 
| 33 | 
            +
                  "no_repeat_ngram_size": 3,
         | 
| 34 | 
            +
                  "num_beams": 4,
         | 
| 35 | 
            +
                  "prefix": "summarize: "
         | 
| 36 | 
            +
                },
         | 
| 37 | 
            +
                "translation_en_to_de": {
         | 
| 38 | 
            +
                  "early_stopping": true,
         | 
| 39 | 
            +
                  "max_length": 300,
         | 
| 40 | 
            +
                  "num_beams": 4,
         | 
| 41 | 
            +
                  "prefix": "translate English to German: "
         | 
| 42 | 
            +
                },
         | 
| 43 | 
            +
                "translation_en_to_fr": {
         | 
| 44 | 
            +
                  "early_stopping": true,
         | 
| 45 | 
            +
                  "max_length": 300,
         | 
| 46 | 
            +
                  "num_beams": 4,
         | 
| 47 | 
            +
                  "prefix": "translate English to French: "
         | 
| 48 | 
            +
                },
         | 
| 49 | 
            +
                "translation_en_to_ro": {
         | 
| 50 | 
            +
                  "early_stopping": true,
         | 
| 51 | 
            +
                  "max_length": 300,
         | 
| 52 | 
            +
                  "num_beams": 4,
         | 
| 53 | 
            +
                  "prefix": "translate English to Romanian: "
         | 
| 54 | 
            +
                }
         | 
| 55 | 
            +
              },
         | 
| 56 | 
            +
              "tie_word_embeddings": false,
         | 
| 57 | 
            +
              "torch_dtype": "float32",
         | 
| 58 | 
            +
              "transformers_version": "4.28.1",
         | 
| 59 | 
            +
              "use_cache": true,
         | 
| 60 | 
            +
              "vocab_size": 32128
         | 
| 61 | 
            +
            }
         | 
    	
        logs/1685427965.855566/events.out.tfevents.1685427965.1b8f4c969eab.1116.1
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:fa46eab7479c830d8532c643e7a14b214a093aaa0a39076fa3c73bf213afd783
         | 
| 3 | 
            +
            size 6255
         | 
    	
        logs/events.out.tfevents.1685427965.1b8f4c969eab.1116.0
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:f500a5358c629c7eabf72bd52cacce5dae02677ac15d5b5fe9b8c681e34b3fa7
         | 
| 3 | 
            +
            size 5255
         | 
    	
        pytorch_model.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:c73ba7d7b5de47c5c4c2a5d35e35358ee11cb1b3a07e70963f12fbaaa9fef572
         | 
| 3 | 
            +
            size 990408885
         | 
    	
        training_args.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:be072498ccafcf54036c1b38ce1c2875ba7efe2b27e3c2cd3ad6c56fad212c16
         | 
| 3 | 
            +
            size 3835
         |