Training in progress, epoch 1
Browse files- config.json +55 -0
- generation_config.json +42 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0.0,
|
| 3 |
+
"activation_function": "swish",
|
| 4 |
+
"add_bias_logits": false,
|
| 5 |
+
"add_final_layer_norm": false,
|
| 6 |
+
"architectures": [
|
| 7 |
+
"MarianMTModel"
|
| 8 |
+
],
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"bos_token_id": 0,
|
| 11 |
+
"classif_dropout": 0.0,
|
| 12 |
+
"classifier_dropout": 0.0,
|
| 13 |
+
"d_model": 512,
|
| 14 |
+
"decoder_attention_heads": 8,
|
| 15 |
+
"decoder_ffn_dim": 2048,
|
| 16 |
+
"decoder_layerdrop": 0.0,
|
| 17 |
+
"decoder_layers": 6,
|
| 18 |
+
"decoder_start_token_id": 65000,
|
| 19 |
+
"decoder_vocab_size": 65001,
|
| 20 |
+
"dropout": 0.1,
|
| 21 |
+
"dtype": "float32",
|
| 22 |
+
"encoder_attention_heads": 8,
|
| 23 |
+
"encoder_ffn_dim": 2048,
|
| 24 |
+
"encoder_layerdrop": 0.0,
|
| 25 |
+
"encoder_layers": 6,
|
| 26 |
+
"eos_token_id": 0,
|
| 27 |
+
"extra_pos_embeddings": 65001,
|
| 28 |
+
"force_bos_token_to_be_generated": false,
|
| 29 |
+
"id2label": {
|
| 30 |
+
"0": "LABEL_0",
|
| 31 |
+
"1": "LABEL_1",
|
| 32 |
+
"2": "LABEL_2"
|
| 33 |
+
},
|
| 34 |
+
"init_std": 0.02,
|
| 35 |
+
"is_decoder": false,
|
| 36 |
+
"is_encoder_decoder": true,
|
| 37 |
+
"label2id": {
|
| 38 |
+
"LABEL_0": 0,
|
| 39 |
+
"LABEL_1": 1,
|
| 40 |
+
"LABEL_2": 2
|
| 41 |
+
},
|
| 42 |
+
"max_position_embeddings": 512,
|
| 43 |
+
"model_type": "marian",
|
| 44 |
+
"normalize_before": false,
|
| 45 |
+
"normalize_embedding": false,
|
| 46 |
+
"num_hidden_layers": 6,
|
| 47 |
+
"pad_token_id": 65000,
|
| 48 |
+
"scale_embedding": true,
|
| 49 |
+
"share_encoder_decoder_embeddings": true,
|
| 50 |
+
"static_position_embeddings": true,
|
| 51 |
+
"tie_word_embeddings": true,
|
| 52 |
+
"transformers_version": "5.0.0",
|
| 53 |
+
"use_cache": false,
|
| 54 |
+
"vocab_size": 65001
|
| 55 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"assistant_confidence_threshold": 0.4,
|
| 3 |
+
"assistant_lookbehind": 10,
|
| 4 |
+
"bad_words_ids": [
|
| 5 |
+
[
|
| 6 |
+
65000
|
| 7 |
+
]
|
| 8 |
+
],
|
| 9 |
+
"bos_token_id": 0,
|
| 10 |
+
"decoder_start_token_id": 65000,
|
| 11 |
+
"diversity_penalty": 0.0,
|
| 12 |
+
"do_sample": false,
|
| 13 |
+
"early_stopping": false,
|
| 14 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 15 |
+
"encoder_repetition_penalty": 1.0,
|
| 16 |
+
"eos_token_id": 0,
|
| 17 |
+
"epsilon_cutoff": 0.0,
|
| 18 |
+
"eta_cutoff": 0.0,
|
| 19 |
+
"forced_eos_token_id": 0,
|
| 20 |
+
"length_penalty": 1.0,
|
| 21 |
+
"max_length": 512,
|
| 22 |
+
"min_length": 0,
|
| 23 |
+
"no_repeat_ngram_size": 0,
|
| 24 |
+
"num_assistant_tokens": 20,
|
| 25 |
+
"num_assistant_tokens_schedule": "constant",
|
| 26 |
+
"num_beam_groups": 1,
|
| 27 |
+
"num_beams": 4,
|
| 28 |
+
"num_return_sequences": 1,
|
| 29 |
+
"output_scores": false,
|
| 30 |
+
"pad_token_id": 65000,
|
| 31 |
+
"remove_invalid_values": false,
|
| 32 |
+
"renormalize_logits": true,
|
| 33 |
+
"repetition_penalty": 1.0,
|
| 34 |
+
"return_dict_in_generate": false,
|
| 35 |
+
"target_lookbehind": 10,
|
| 36 |
+
"temperature": 1.0,
|
| 37 |
+
"top_k": 50,
|
| 38 |
+
"top_p": 1.0,
|
| 39 |
+
"transformers_version": "5.0.0",
|
| 40 |
+
"typical_p": 1.0,
|
| 41 |
+
"use_cache": true
|
| 42 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:144bf2ebe413cf75b20179ffb3c18e55a4c4672c58255ca108993b5ce2669c52
|
| 3 |
+
size 576209740
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92deea573859af6644949c10dbf461b1d446742059420e9e6f97878f2d05220a
|
| 3 |
+
size 5393
|