Upload initial fine-tuned model from C:/xampp/htdocs/cgp_website/backend_cgp_ai/cgp_model_fr-en
Browse files- .gitattributes +2 -0
- checkpoint-1500/config.json +56 -0
- checkpoint-1500/generation_config.json +16 -0
- checkpoint-1500/model.safetensors +3 -0
- checkpoint-1500/optimizer.pt +3 -0
- checkpoint-1500/rng_state.pth +3 -0
- checkpoint-1500/scheduler.pt +3 -0
- checkpoint-1500/trainer_state.json +244 -0
- checkpoint-1500/training_args.bin +3 -0
- checkpoint-1560/config.json +56 -0
- checkpoint-1560/generation_config.json +16 -0
- checkpoint-1560/model.safetensors +3 -0
- checkpoint-1560/optimizer.pt +3 -0
- checkpoint-1560/rng_state.pth +3 -0
- checkpoint-1560/scheduler.pt +3 -0
- checkpoint-1560/trainer_state.json +251 -0
- checkpoint-1560/training_args.bin +3 -0
- config.json +56 -0
- generation_config.json +16 -0
- model.safetensors +3 -0
- source.spm +3 -0
- special_tokens_map.json +5 -0
- target.spm +3 -0
- tokenizer_config.json +39 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
source.spm filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
target.spm filter=lfs diff=lfs merge=lfs -text
|
checkpoint-1500/config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_num_labels": 3,
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "swish",
|
| 5 |
+
"add_bias_logits": false,
|
| 6 |
+
"add_final_layer_norm": false,
|
| 7 |
+
"architectures": [
|
| 8 |
+
"MarianMTModel"
|
| 9 |
+
],
|
| 10 |
+
"attention_dropout": 0.0,
|
| 11 |
+
"bos_token_id": 0,
|
| 12 |
+
"classif_dropout": 0.0,
|
| 13 |
+
"classifier_dropout": 0.0,
|
| 14 |
+
"d_model": 512,
|
| 15 |
+
"decoder_attention_heads": 8,
|
| 16 |
+
"decoder_ffn_dim": 2048,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 6,
|
| 19 |
+
"decoder_start_token_id": 59513,
|
| 20 |
+
"decoder_vocab_size": 59514,
|
| 21 |
+
"dropout": 0.1,
|
| 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 |
+
"forced_eos_token_id": 0,
|
| 28 |
+
"gradient_checkpointing": false,
|
| 29 |
+
"id2label": {
|
| 30 |
+
"0": "LABEL_0",
|
| 31 |
+
"1": "LABEL_1",
|
| 32 |
+
"2": "LABEL_2"
|
| 33 |
+
},
|
| 34 |
+
"init_std": 0.02,
|
| 35 |
+
"is_encoder_decoder": true,
|
| 36 |
+
"label2id": {
|
| 37 |
+
"LABEL_0": 0,
|
| 38 |
+
"LABEL_1": 1,
|
| 39 |
+
"LABEL_2": 2
|
| 40 |
+
},
|
| 41 |
+
"max_length": null,
|
| 42 |
+
"max_position_embeddings": 512,
|
| 43 |
+
"model_type": "marian",
|
| 44 |
+
"normalize_before": false,
|
| 45 |
+
"normalize_embedding": false,
|
| 46 |
+
"num_beams": null,
|
| 47 |
+
"num_hidden_layers": 6,
|
| 48 |
+
"pad_token_id": 59513,
|
| 49 |
+
"scale_embedding": true,
|
| 50 |
+
"share_encoder_decoder_embeddings": true,
|
| 51 |
+
"static_position_embeddings": true,
|
| 52 |
+
"torch_dtype": "float32",
|
| 53 |
+
"transformers_version": "4.54.0",
|
| 54 |
+
"use_cache": true,
|
| 55 |
+
"vocab_size": 59514
|
| 56 |
+
}
|
checkpoint-1500/generation_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bad_words_ids": [
|
| 3 |
+
[
|
| 4 |
+
59513
|
| 5 |
+
]
|
| 6 |
+
],
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"decoder_start_token_id": 59513,
|
| 9 |
+
"eos_token_id": 0,
|
| 10 |
+
"forced_eos_token_id": 0,
|
| 11 |
+
"max_length": 512,
|
| 12 |
+
"num_beams": 4,
|
| 13 |
+
"pad_token_id": 59513,
|
| 14 |
+
"renormalize_logits": true,
|
| 15 |
+
"transformers_version": "4.54.0"
|
| 16 |
+
}
|
checkpoint-1500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1dda8278d7e5a78a8accfe053257aa703d0418c38dc565e09b306469390b65d9
|
| 3 |
+
size 298705768
|
checkpoint-1500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85fcf5f8f8cd7bceb3df8732ca9d5bbae1f2a948323d0b8a670e676a822aa5d2
|
| 3 |
+
size 597082251
|
checkpoint-1500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:243c440838d8f2bbade2abb0b98188723f11aaf9fa54b5696781361417637f11
|
| 3 |
+
size 14455
|
checkpoint-1500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b115109ee567f26bb6998bd40abb8facf08418ac7ce039699b256838702124ac
|
| 3 |
+
size 1465
|
checkpoint-1500/trainer_state.json
ADDED
|
@@ -0,0 +1,244 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.8846153846153846,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 1500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.09615384615384616,
|
| 14 |
+
"grad_norm": 3.9840543270111084,
|
| 15 |
+
"learning_rate": 2.45e-05,
|
| 16 |
+
"loss": 3.2821,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.19230769230769232,
|
| 21 |
+
"grad_norm": 3.723275661468506,
|
| 22 |
+
"learning_rate": 4.9500000000000004e-05,
|
| 23 |
+
"loss": 2.0706,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.28846153846153844,
|
| 28 |
+
"grad_norm": 3.2212064266204834,
|
| 29 |
+
"learning_rate": 4.832191780821918e-05,
|
| 30 |
+
"loss": 2.0575,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.38461538461538464,
|
| 35 |
+
"grad_norm": 4.188878536224365,
|
| 36 |
+
"learning_rate": 4.660958904109589e-05,
|
| 37 |
+
"loss": 1.9627,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.4807692307692308,
|
| 42 |
+
"grad_norm": 4.127995014190674,
|
| 43 |
+
"learning_rate": 4.48972602739726e-05,
|
| 44 |
+
"loss": 1.8079,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.5769230769230769,
|
| 49 |
+
"grad_norm": 4.081024169921875,
|
| 50 |
+
"learning_rate": 4.318493150684932e-05,
|
| 51 |
+
"loss": 1.8104,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.6730769230769231,
|
| 56 |
+
"grad_norm": 3.8007733821868896,
|
| 57 |
+
"learning_rate": 4.147260273972603e-05,
|
| 58 |
+
"loss": 1.6722,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.7692307692307693,
|
| 63 |
+
"grad_norm": 4.7257819175720215,
|
| 64 |
+
"learning_rate": 3.976027397260274e-05,
|
| 65 |
+
"loss": 1.5827,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.8653846153846154,
|
| 70 |
+
"grad_norm": 3.466817617416382,
|
| 71 |
+
"learning_rate": 3.8047945205479454e-05,
|
| 72 |
+
"loss": 1.5404,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.9615384615384616,
|
| 77 |
+
"grad_norm": 4.541598796844482,
|
| 78 |
+
"learning_rate": 3.633561643835617e-05,
|
| 79 |
+
"loss": 1.6868,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.0576923076923077,
|
| 84 |
+
"grad_norm": 3.6558027267456055,
|
| 85 |
+
"learning_rate": 3.462328767123288e-05,
|
| 86 |
+
"loss": 1.5891,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.1538461538461537,
|
| 91 |
+
"grad_norm": 3.7358193397521973,
|
| 92 |
+
"learning_rate": 3.291095890410959e-05,
|
| 93 |
+
"loss": 1.295,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 1.25,
|
| 98 |
+
"grad_norm": 3.8677425384521484,
|
| 99 |
+
"learning_rate": 3.11986301369863e-05,
|
| 100 |
+
"loss": 1.5011,
|
| 101 |
+
"step": 650
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.3461538461538463,
|
| 105 |
+
"grad_norm": 3.6683499813079834,
|
| 106 |
+
"learning_rate": 2.9486301369863017e-05,
|
| 107 |
+
"loss": 1.4383,
|
| 108 |
+
"step": 700
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 1.4423076923076923,
|
| 112 |
+
"grad_norm": 4.374536037445068,
|
| 113 |
+
"learning_rate": 2.777397260273973e-05,
|
| 114 |
+
"loss": 1.3915,
|
| 115 |
+
"step": 750
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 1.5384615384615383,
|
| 119 |
+
"grad_norm": 4.014420986175537,
|
| 120 |
+
"learning_rate": 2.606164383561644e-05,
|
| 121 |
+
"loss": 1.3268,
|
| 122 |
+
"step": 800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.6346153846153846,
|
| 126 |
+
"grad_norm": 3.4891932010650635,
|
| 127 |
+
"learning_rate": 2.4349315068493153e-05,
|
| 128 |
+
"loss": 1.3339,
|
| 129 |
+
"step": 850
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.7307692307692308,
|
| 133 |
+
"grad_norm": 3.5154852867126465,
|
| 134 |
+
"learning_rate": 2.2636986301369862e-05,
|
| 135 |
+
"loss": 1.4429,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.8269230769230769,
|
| 140 |
+
"grad_norm": 3.20439076423645,
|
| 141 |
+
"learning_rate": 2.0924657534246576e-05,
|
| 142 |
+
"loss": 1.4086,
|
| 143 |
+
"step": 950
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.9230769230769231,
|
| 147 |
+
"grad_norm": 3.0504961013793945,
|
| 148 |
+
"learning_rate": 1.921232876712329e-05,
|
| 149 |
+
"loss": 1.4228,
|
| 150 |
+
"step": 1000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 2.019230769230769,
|
| 154 |
+
"grad_norm": 4.06278133392334,
|
| 155 |
+
"learning_rate": 1.75e-05,
|
| 156 |
+
"loss": 1.3829,
|
| 157 |
+
"step": 1050
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 2.1153846153846154,
|
| 161 |
+
"grad_norm": 1.8991236686706543,
|
| 162 |
+
"learning_rate": 1.5787671232876715e-05,
|
| 163 |
+
"loss": 1.1774,
|
| 164 |
+
"step": 1100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.2115384615384617,
|
| 168 |
+
"grad_norm": 3.1005361080169678,
|
| 169 |
+
"learning_rate": 1.4075342465753425e-05,
|
| 170 |
+
"loss": 1.2079,
|
| 171 |
+
"step": 1150
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 2.3076923076923075,
|
| 175 |
+
"grad_norm": 3.7493646144866943,
|
| 176 |
+
"learning_rate": 1.2363013698630138e-05,
|
| 177 |
+
"loss": 1.2159,
|
| 178 |
+
"step": 1200
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 2.4038461538461537,
|
| 182 |
+
"grad_norm": 4.097714424133301,
|
| 183 |
+
"learning_rate": 1.0650684931506851e-05,
|
| 184 |
+
"loss": 1.3659,
|
| 185 |
+
"step": 1250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 2.5,
|
| 189 |
+
"grad_norm": 2.865206003189087,
|
| 190 |
+
"learning_rate": 8.93835616438356e-06,
|
| 191 |
+
"loss": 1.285,
|
| 192 |
+
"step": 1300
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 2.5961538461538463,
|
| 196 |
+
"grad_norm": 3.460542678833008,
|
| 197 |
+
"learning_rate": 7.226027397260274e-06,
|
| 198 |
+
"loss": 1.198,
|
| 199 |
+
"step": 1350
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 2.6923076923076925,
|
| 203 |
+
"grad_norm": 2.2605996131896973,
|
| 204 |
+
"learning_rate": 5.513698630136987e-06,
|
| 205 |
+
"loss": 1.2106,
|
| 206 |
+
"step": 1400
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.7884615384615383,
|
| 210 |
+
"grad_norm": 3.1552298069000244,
|
| 211 |
+
"learning_rate": 3.8013698630136993e-06,
|
| 212 |
+
"loss": 1.3443,
|
| 213 |
+
"step": 1450
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 2.8846153846153846,
|
| 217 |
+
"grad_norm": 4.187378883361816,
|
| 218 |
+
"learning_rate": 2.089041095890411e-06,
|
| 219 |
+
"loss": 1.1452,
|
| 220 |
+
"step": 1500
|
| 221 |
+
}
|
| 222 |
+
],
|
| 223 |
+
"logging_steps": 50,
|
| 224 |
+
"max_steps": 1560,
|
| 225 |
+
"num_input_tokens_seen": 0,
|
| 226 |
+
"num_train_epochs": 3,
|
| 227 |
+
"save_steps": 500,
|
| 228 |
+
"stateful_callbacks": {
|
| 229 |
+
"TrainerControl": {
|
| 230 |
+
"args": {
|
| 231 |
+
"should_epoch_stop": false,
|
| 232 |
+
"should_evaluate": false,
|
| 233 |
+
"should_log": false,
|
| 234 |
+
"should_save": true,
|
| 235 |
+
"should_training_stop": false
|
| 236 |
+
},
|
| 237 |
+
"attributes": {}
|
| 238 |
+
}
|
| 239 |
+
},
|
| 240 |
+
"total_flos": 203254596108288.0,
|
| 241 |
+
"train_batch_size": 4,
|
| 242 |
+
"trial_name": null,
|
| 243 |
+
"trial_params": null
|
| 244 |
+
}
|
checkpoint-1500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59d23639490f4265daeb5ab5b30258e42126708bd50c3787e6a97fcc503e10ef
|
| 3 |
+
size 5841
|
checkpoint-1560/config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_num_labels": 3,
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "swish",
|
| 5 |
+
"add_bias_logits": false,
|
| 6 |
+
"add_final_layer_norm": false,
|
| 7 |
+
"architectures": [
|
| 8 |
+
"MarianMTModel"
|
| 9 |
+
],
|
| 10 |
+
"attention_dropout": 0.0,
|
| 11 |
+
"bos_token_id": 0,
|
| 12 |
+
"classif_dropout": 0.0,
|
| 13 |
+
"classifier_dropout": 0.0,
|
| 14 |
+
"d_model": 512,
|
| 15 |
+
"decoder_attention_heads": 8,
|
| 16 |
+
"decoder_ffn_dim": 2048,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 6,
|
| 19 |
+
"decoder_start_token_id": 59513,
|
| 20 |
+
"decoder_vocab_size": 59514,
|
| 21 |
+
"dropout": 0.1,
|
| 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 |
+
"forced_eos_token_id": 0,
|
| 28 |
+
"gradient_checkpointing": false,
|
| 29 |
+
"id2label": {
|
| 30 |
+
"0": "LABEL_0",
|
| 31 |
+
"1": "LABEL_1",
|
| 32 |
+
"2": "LABEL_2"
|
| 33 |
+
},
|
| 34 |
+
"init_std": 0.02,
|
| 35 |
+
"is_encoder_decoder": true,
|
| 36 |
+
"label2id": {
|
| 37 |
+
"LABEL_0": 0,
|
| 38 |
+
"LABEL_1": 1,
|
| 39 |
+
"LABEL_2": 2
|
| 40 |
+
},
|
| 41 |
+
"max_length": null,
|
| 42 |
+
"max_position_embeddings": 512,
|
| 43 |
+
"model_type": "marian",
|
| 44 |
+
"normalize_before": false,
|
| 45 |
+
"normalize_embedding": false,
|
| 46 |
+
"num_beams": null,
|
| 47 |
+
"num_hidden_layers": 6,
|
| 48 |
+
"pad_token_id": 59513,
|
| 49 |
+
"scale_embedding": true,
|
| 50 |
+
"share_encoder_decoder_embeddings": true,
|
| 51 |
+
"static_position_embeddings": true,
|
| 52 |
+
"torch_dtype": "float32",
|
| 53 |
+
"transformers_version": "4.54.0",
|
| 54 |
+
"use_cache": true,
|
| 55 |
+
"vocab_size": 59514
|
| 56 |
+
}
|
checkpoint-1560/generation_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bad_words_ids": [
|
| 3 |
+
[
|
| 4 |
+
59513
|
| 5 |
+
]
|
| 6 |
+
],
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"decoder_start_token_id": 59513,
|
| 9 |
+
"eos_token_id": 0,
|
| 10 |
+
"forced_eos_token_id": 0,
|
| 11 |
+
"max_length": 512,
|
| 12 |
+
"num_beams": 4,
|
| 13 |
+
"pad_token_id": 59513,
|
| 14 |
+
"renormalize_logits": true,
|
| 15 |
+
"transformers_version": "4.54.0"
|
| 16 |
+
}
|
checkpoint-1560/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5b2f95fd9b97137a8d7cf4eb3f77a1229e707259bad1b00639962e38fcef94b
|
| 3 |
+
size 298705768
|
checkpoint-1560/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b332b753668915a9dafdbbfee6a7371bcc85f8ed5e5ab598ab7f2b844b2db18
|
| 3 |
+
size 597082251
|
checkpoint-1560/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0632a368254e74926741726fe2cbd8395408338fe2c1c6292e682c4c690fb404
|
| 3 |
+
size 14455
|
checkpoint-1560/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c22ff8f3700b53856d5759d28956e3d850e72df1ac1cf5ea7e6c56963a1cbba
|
| 3 |
+
size 1465
|
checkpoint-1560/trainer_state.json
ADDED
|
@@ -0,0 +1,251 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 1560,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.09615384615384616,
|
| 14 |
+
"grad_norm": 3.9840543270111084,
|
| 15 |
+
"learning_rate": 2.45e-05,
|
| 16 |
+
"loss": 3.2821,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.19230769230769232,
|
| 21 |
+
"grad_norm": 3.723275661468506,
|
| 22 |
+
"learning_rate": 4.9500000000000004e-05,
|
| 23 |
+
"loss": 2.0706,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.28846153846153844,
|
| 28 |
+
"grad_norm": 3.2212064266204834,
|
| 29 |
+
"learning_rate": 4.832191780821918e-05,
|
| 30 |
+
"loss": 2.0575,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.38461538461538464,
|
| 35 |
+
"grad_norm": 4.188878536224365,
|
| 36 |
+
"learning_rate": 4.660958904109589e-05,
|
| 37 |
+
"loss": 1.9627,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.4807692307692308,
|
| 42 |
+
"grad_norm": 4.127995014190674,
|
| 43 |
+
"learning_rate": 4.48972602739726e-05,
|
| 44 |
+
"loss": 1.8079,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.5769230769230769,
|
| 49 |
+
"grad_norm": 4.081024169921875,
|
| 50 |
+
"learning_rate": 4.318493150684932e-05,
|
| 51 |
+
"loss": 1.8104,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.6730769230769231,
|
| 56 |
+
"grad_norm": 3.8007733821868896,
|
| 57 |
+
"learning_rate": 4.147260273972603e-05,
|
| 58 |
+
"loss": 1.6722,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.7692307692307693,
|
| 63 |
+
"grad_norm": 4.7257819175720215,
|
| 64 |
+
"learning_rate": 3.976027397260274e-05,
|
| 65 |
+
"loss": 1.5827,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.8653846153846154,
|
| 70 |
+
"grad_norm": 3.466817617416382,
|
| 71 |
+
"learning_rate": 3.8047945205479454e-05,
|
| 72 |
+
"loss": 1.5404,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.9615384615384616,
|
| 77 |
+
"grad_norm": 4.541598796844482,
|
| 78 |
+
"learning_rate": 3.633561643835617e-05,
|
| 79 |
+
"loss": 1.6868,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.0576923076923077,
|
| 84 |
+
"grad_norm": 3.6558027267456055,
|
| 85 |
+
"learning_rate": 3.462328767123288e-05,
|
| 86 |
+
"loss": 1.5891,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.1538461538461537,
|
| 91 |
+
"grad_norm": 3.7358193397521973,
|
| 92 |
+
"learning_rate": 3.291095890410959e-05,
|
| 93 |
+
"loss": 1.295,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 1.25,
|
| 98 |
+
"grad_norm": 3.8677425384521484,
|
| 99 |
+
"learning_rate": 3.11986301369863e-05,
|
| 100 |
+
"loss": 1.5011,
|
| 101 |
+
"step": 650
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.3461538461538463,
|
| 105 |
+
"grad_norm": 3.6683499813079834,
|
| 106 |
+
"learning_rate": 2.9486301369863017e-05,
|
| 107 |
+
"loss": 1.4383,
|
| 108 |
+
"step": 700
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 1.4423076923076923,
|
| 112 |
+
"grad_norm": 4.374536037445068,
|
| 113 |
+
"learning_rate": 2.777397260273973e-05,
|
| 114 |
+
"loss": 1.3915,
|
| 115 |
+
"step": 750
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 1.5384615384615383,
|
| 119 |
+
"grad_norm": 4.014420986175537,
|
| 120 |
+
"learning_rate": 2.606164383561644e-05,
|
| 121 |
+
"loss": 1.3268,
|
| 122 |
+
"step": 800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.6346153846153846,
|
| 126 |
+
"grad_norm": 3.4891932010650635,
|
| 127 |
+
"learning_rate": 2.4349315068493153e-05,
|
| 128 |
+
"loss": 1.3339,
|
| 129 |
+
"step": 850
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.7307692307692308,
|
| 133 |
+
"grad_norm": 3.5154852867126465,
|
| 134 |
+
"learning_rate": 2.2636986301369862e-05,
|
| 135 |
+
"loss": 1.4429,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.8269230769230769,
|
| 140 |
+
"grad_norm": 3.20439076423645,
|
| 141 |
+
"learning_rate": 2.0924657534246576e-05,
|
| 142 |
+
"loss": 1.4086,
|
| 143 |
+
"step": 950
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.9230769230769231,
|
| 147 |
+
"grad_norm": 3.0504961013793945,
|
| 148 |
+
"learning_rate": 1.921232876712329e-05,
|
| 149 |
+
"loss": 1.4228,
|
| 150 |
+
"step": 1000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 2.019230769230769,
|
| 154 |
+
"grad_norm": 4.06278133392334,
|
| 155 |
+
"learning_rate": 1.75e-05,
|
| 156 |
+
"loss": 1.3829,
|
| 157 |
+
"step": 1050
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 2.1153846153846154,
|
| 161 |
+
"grad_norm": 1.8991236686706543,
|
| 162 |
+
"learning_rate": 1.5787671232876715e-05,
|
| 163 |
+
"loss": 1.1774,
|
| 164 |
+
"step": 1100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.2115384615384617,
|
| 168 |
+
"grad_norm": 3.1005361080169678,
|
| 169 |
+
"learning_rate": 1.4075342465753425e-05,
|
| 170 |
+
"loss": 1.2079,
|
| 171 |
+
"step": 1150
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 2.3076923076923075,
|
| 175 |
+
"grad_norm": 3.7493646144866943,
|
| 176 |
+
"learning_rate": 1.2363013698630138e-05,
|
| 177 |
+
"loss": 1.2159,
|
| 178 |
+
"step": 1200
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 2.4038461538461537,
|
| 182 |
+
"grad_norm": 4.097714424133301,
|
| 183 |
+
"learning_rate": 1.0650684931506851e-05,
|
| 184 |
+
"loss": 1.3659,
|
| 185 |
+
"step": 1250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 2.5,
|
| 189 |
+
"grad_norm": 2.865206003189087,
|
| 190 |
+
"learning_rate": 8.93835616438356e-06,
|
| 191 |
+
"loss": 1.285,
|
| 192 |
+
"step": 1300
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 2.5961538461538463,
|
| 196 |
+
"grad_norm": 3.460542678833008,
|
| 197 |
+
"learning_rate": 7.226027397260274e-06,
|
| 198 |
+
"loss": 1.198,
|
| 199 |
+
"step": 1350
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 2.6923076923076925,
|
| 203 |
+
"grad_norm": 2.2605996131896973,
|
| 204 |
+
"learning_rate": 5.513698630136987e-06,
|
| 205 |
+
"loss": 1.2106,
|
| 206 |
+
"step": 1400
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.7884615384615383,
|
| 210 |
+
"grad_norm": 3.1552298069000244,
|
| 211 |
+
"learning_rate": 3.8013698630136993e-06,
|
| 212 |
+
"loss": 1.3443,
|
| 213 |
+
"step": 1450
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 2.8846153846153846,
|
| 217 |
+
"grad_norm": 4.187378883361816,
|
| 218 |
+
"learning_rate": 2.089041095890411e-06,
|
| 219 |
+
"loss": 1.1452,
|
| 220 |
+
"step": 1500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 2.980769230769231,
|
| 224 |
+
"grad_norm": 4.166136264801025,
|
| 225 |
+
"learning_rate": 3.767123287671233e-07,
|
| 226 |
+
"loss": 1.3042,
|
| 227 |
+
"step": 1550
|
| 228 |
+
}
|
| 229 |
+
],
|
| 230 |
+
"logging_steps": 50,
|
| 231 |
+
"max_steps": 1560,
|
| 232 |
+
"num_input_tokens_seen": 0,
|
| 233 |
+
"num_train_epochs": 3,
|
| 234 |
+
"save_steps": 500,
|
| 235 |
+
"stateful_callbacks": {
|
| 236 |
+
"TrainerControl": {
|
| 237 |
+
"args": {
|
| 238 |
+
"should_epoch_stop": false,
|
| 239 |
+
"should_evaluate": false,
|
| 240 |
+
"should_log": false,
|
| 241 |
+
"should_save": true,
|
| 242 |
+
"should_training_stop": true
|
| 243 |
+
},
|
| 244 |
+
"attributes": {}
|
| 245 |
+
}
|
| 246 |
+
},
|
| 247 |
+
"total_flos": 211322406961152.0,
|
| 248 |
+
"train_batch_size": 4,
|
| 249 |
+
"trial_name": null,
|
| 250 |
+
"trial_params": null
|
| 251 |
+
}
|
checkpoint-1560/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59d23639490f4265daeb5ab5b30258e42126708bd50c3787e6a97fcc503e10ef
|
| 3 |
+
size 5841
|
config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_num_labels": 3,
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "swish",
|
| 5 |
+
"add_bias_logits": false,
|
| 6 |
+
"add_final_layer_norm": false,
|
| 7 |
+
"architectures": [
|
| 8 |
+
"MarianMTModel"
|
| 9 |
+
],
|
| 10 |
+
"attention_dropout": 0.0,
|
| 11 |
+
"bos_token_id": 0,
|
| 12 |
+
"classif_dropout": 0.0,
|
| 13 |
+
"classifier_dropout": 0.0,
|
| 14 |
+
"d_model": 512,
|
| 15 |
+
"decoder_attention_heads": 8,
|
| 16 |
+
"decoder_ffn_dim": 2048,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 6,
|
| 19 |
+
"decoder_start_token_id": 59513,
|
| 20 |
+
"decoder_vocab_size": 59514,
|
| 21 |
+
"dropout": 0.1,
|
| 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 |
+
"forced_eos_token_id": 0,
|
| 28 |
+
"gradient_checkpointing": false,
|
| 29 |
+
"id2label": {
|
| 30 |
+
"0": "LABEL_0",
|
| 31 |
+
"1": "LABEL_1",
|
| 32 |
+
"2": "LABEL_2"
|
| 33 |
+
},
|
| 34 |
+
"init_std": 0.02,
|
| 35 |
+
"is_encoder_decoder": true,
|
| 36 |
+
"label2id": {
|
| 37 |
+
"LABEL_0": 0,
|
| 38 |
+
"LABEL_1": 1,
|
| 39 |
+
"LABEL_2": 2
|
| 40 |
+
},
|
| 41 |
+
"max_length": null,
|
| 42 |
+
"max_position_embeddings": 512,
|
| 43 |
+
"model_type": "marian",
|
| 44 |
+
"normalize_before": false,
|
| 45 |
+
"normalize_embedding": false,
|
| 46 |
+
"num_beams": null,
|
| 47 |
+
"num_hidden_layers": 6,
|
| 48 |
+
"pad_token_id": 59513,
|
| 49 |
+
"scale_embedding": true,
|
| 50 |
+
"share_encoder_decoder_embeddings": true,
|
| 51 |
+
"static_position_embeddings": true,
|
| 52 |
+
"torch_dtype": "float32",
|
| 53 |
+
"transformers_version": "4.54.0",
|
| 54 |
+
"use_cache": true,
|
| 55 |
+
"vocab_size": 59514
|
| 56 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bad_words_ids": [
|
| 3 |
+
[
|
| 4 |
+
59513
|
| 5 |
+
]
|
| 6 |
+
],
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"decoder_start_token_id": 59513,
|
| 9 |
+
"eos_token_id": 0,
|
| 10 |
+
"forced_eos_token_id": 0,
|
| 11 |
+
"max_length": 512,
|
| 12 |
+
"num_beams": 4,
|
| 13 |
+
"pad_token_id": 59513,
|
| 14 |
+
"renormalize_logits": true,
|
| 15 |
+
"transformers_version": "4.54.0"
|
| 16 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5b2f95fd9b97137a8d7cf4eb3f77a1229e707259bad1b00639962e38fcef94b
|
| 3 |
+
size 298705768
|
source.spm
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78d0e717c77053f1c4b856d8661d9cb87c64f083a35418c087b9146300e4f585
|
| 3 |
+
size 802397
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token": "</s>",
|
| 3 |
+
"pad_token": "<pad>",
|
| 4 |
+
"unk_token": "<unk>"
|
| 5 |
+
}
|
target.spm
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:173e9f493a668fe396d599e28d414a201193094e6ffd7a4678e5aab0f6d3d838
|
| 3 |
+
size 778395
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "</s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<unk>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"59513": {
|
| 20 |
+
"content": "<pad>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
}
|
| 27 |
+
},
|
| 28 |
+
"clean_up_tokenization_spaces": false,
|
| 29 |
+
"eos_token": "</s>",
|
| 30 |
+
"extra_special_tokens": {},
|
| 31 |
+
"model_max_length": 512,
|
| 32 |
+
"pad_token": "<pad>",
|
| 33 |
+
"separate_vocabs": false,
|
| 34 |
+
"source_lang": "fr",
|
| 35 |
+
"sp_model_kwargs": {},
|
| 36 |
+
"target_lang": "en",
|
| 37 |
+
"tokenizer_class": "MarianTokenizer",
|
| 38 |
+
"unk_token": "<unk>"
|
| 39 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|