Upload 10 files

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "./cache/base_model",
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "bad_words_ids": [
+    [
+      65000
+    ]
+  ],
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 65000,
+  "decoder_vocab_size": 65001,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 0,
+  "extra_pos_embeddings": 65001,
+  "forced_eos_token_id": 0,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": 512,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": 6,
+  "num_hidden_layers": 6,
+  "pad_token_id": 65000,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 65001
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      65000
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 65000,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 6,
+  "pad_token_id": 65000,
+  "renormalize_logits": true,
+  "transformers_version": "4.35.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:884d3d5a1c0129a037080fe8ee57f1d853679676835ba0efb7311a9cf44d2473
+size 309965092

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "zho",
+  "sp_model_kwargs": {},
+  "target_lang": "eng",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,125 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.932735426008969,
+  "eval_steps": 500,
+  "global_step": 5500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.820986547085202e-05,
+      "loss": 1.626,
+      "step": 500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.641614349775785e-05,
+      "loss": 1.4201,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_bleu": 33.3044,
+      "eval_gen_len": 28.8563,
+      "eval_loss": 1.3592603206634521,
+      "eval_runtime": 172.5107,
+      "eval_samples_per_second": 9.762,
+      "eval_steps_per_second": 0.614,
+      "step": 1115
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.462242152466368e-05,
+      "loss": 1.2694,
+      "step": 1500
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1.2828699551569507e-05,
+      "loss": 1.2085,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_bleu": 34.5144,
+      "eval_gen_len": 29.0564,
+      "eval_loss": 1.3197557926177979,
+      "eval_runtime": 172.4795,
+      "eval_samples_per_second": 9.763,
+      "eval_steps_per_second": 0.615,
+      "step": 2230
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 1.1034977578475336e-05,
+      "loss": 1.1369,
+      "step": 2500
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 9.244843049327356e-06,
+      "loss": 1.0786,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_bleu": 34.6844,
+      "eval_gen_len": 29.1496,
+      "eval_loss": 1.3080627918243408,
+      "eval_runtime": 175.6578,
+      "eval_samples_per_second": 9.587,
+      "eval_steps_per_second": 0.603,
+      "step": 3345
+    },
+    {
+      "epoch": 3.14,
+      "learning_rate": 7.451121076233184e-06,
+      "loss": 1.0529,
+      "step": 3500
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 5.657399103139014e-06,
+      "loss": 0.9958,
+      "step": 4000
+    },
+    {
+      "epoch": 4.0,
+      "eval_bleu": 34.862,
+      "eval_gen_len": 29.0529,
+      "eval_loss": 1.309422254562378,
+      "eval_runtime": 174.4734,
+      "eval_samples_per_second": 9.652,
+      "eval_steps_per_second": 0.608,
+      "step": 4460
+    },
+    {
+      "epoch": 4.04,
+      "learning_rate": 3.863677130044843e-06,
+      "loss": 0.9933,
+      "step": 4500
+    },
+    {
+      "epoch": 4.48,
+      "learning_rate": 2.069955156950673e-06,
+      "loss": 0.9477,
+      "step": 5000
+    },
+    {
+      "epoch": 4.93,
+      "learning_rate": 2.762331838565023e-07,
+      "loss": 0.9504,
+      "step": 5500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5575,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 1101235524599808.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da90a111e5c48fccd8a546276563b6683ef1cde307a5b3c1ecb8438f97ef2c84
+size 4271