Upload 16 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+generated_predictions.txt filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,69 @@
----
-license: mit
----
+---
+library_name: transformers
+language:
+- zh
+- en
+base_model: ai_challenger-epoch-1
+tags:
+- generated_from_trainer
+metrics:
+- bleu
+model-index:
+- name: pretrain_zh_en_ai_challenger_output
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# pretrain_zh_en_ai_challenger_output
+
+This model is a fine-tuned version of [ai_challenger-epoch-1](https://huggingface.co/ai_challenger-epoch-1) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4557
+- Bleu: 27.0414
+- Meteor: 0.5451
+- Gen Len: 15.2255
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 64
+- eval_batch_size: 64
+- seed: 2024
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5.0
+
+### Training results
+
+| Training Loss | Epoch | Step   | Validation Loss | Bleu    | Meteor | Gen Len |
+|:-------------:|:-----:|:------:|:---------------:|:-------:|:------:|:-------:|
+| 1.6733        | 1.0   | 156250 | 1.5656          | 25.9104 | 0.5364 | 15.4366 |
+| 1.6415        | 2.0   | 312500 | 1.5193          | 26.7033 | 0.5449 | 15.6291 |
+| 1.5831        | 3.0   | 468750 | 1.4901          | 27.2345 | 0.5479 | 15.5704 |
+| 1.5352        | 4.0   | 625000 | 1.4695          | 27.7312 | 0.5521 | 15.528  |
+| 1.4946        | 5.0   | 781250 | 1.4557          | 27.9356 | 0.5543 | 15.548  |
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.5.0+cu124
+- Datasets 3.0.1
+- Tokenizers 0.20.1

all_results.json

@@ -0,0 +1,25 @@
+{
+    "epoch": 5.0,
+    "eval_bleu": 27.0414,
+    "eval_gen_len": 15.2255,
+    "eval_loss": 1.4556750059127808,
+    "eval_meteor": 0.5451,
+    "eval_runtime": 104.0159,
+    "eval_samples": 8000,
+    "eval_samples_per_second": 76.911,
+    "eval_steps_per_second": 1.202,
+    "predict_bleu": 2.4866,
+    "predict_gen_len": 28.2458,
+    "predict_loss": 5.196128845214844,
+    "predict_meteor": 0.1243,
+    "predict_runtime": 4126.7668,
+    "predict_samples": 227568,
+    "predict_samples_per_second": 55.144,
+    "predict_steps_per_second": 0.862,
+    "total_flos": 6.095033471871222e+17,
+    "train_loss": 1.58551646,
+    "train_runtime": 202290.4129,
+    "train_samples": 10000000,
+    "train_samples_per_second": 247.169,
+    "train_steps_per_second": 3.862
+}

config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "ai_challenger-epoch-1",
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "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": null,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": null,
+  "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": "4.45.2",
+  "use_cache": true,
+  "vocab_size": 65001
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 5.0,
+    "eval_bleu": 27.0414,
+    "eval_gen_len": 15.2255,
+    "eval_loss": 1.4556750059127808,
+    "eval_meteor": 0.5451,
+    "eval_runtime": 104.0159,
+    "eval_samples": 8000,
+    "eval_samples_per_second": 76.911,
+    "eval_steps_per_second": 1.202
+}

generated_predictions.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd65ea3cf65bdceeced9512ead9a612e21cd2df2ac492503ef14b49e378e2469
+size 29532490

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": "4.45.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddaf0c712aaff08d463a9aa7d188a1b6f104d3ed1400ba8faf6cd212ff24ba55
+size 309965092

predict_results.json

@@ -0,0 +1,10 @@
+{
+    "predict_bleu": 2.4866,
+    "predict_gen_len": 28.2458,
+    "predict_loss": 5.196128845214844,
+    "predict_meteor": 0.1243,
+    "predict_runtime": 4126.7668,
+    "predict_samples": 227568,
+    "predict_samples_per_second": 55.144,
+    "predict_steps_per_second": 0.862
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

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": false,
+  "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>"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "total_flos": 6.095033471871222e+17,
+    "train_loss": 1.58551646,
+    "train_runtime": 202290.4129,
+    "train_samples": 10000000,
+    "train_samples_per_second": 247.169,
+    "train_steps_per_second": 3.862
+}

trainer_state.json

@@ -0,0 +1,132 @@
+{
+  "best_metric": 1.4556750059127808,
+  "best_model_checkpoint": "./pretrain_zh_en_ai_challenger_output/checkpoint-781250",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 781250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.1560218334198,
+      "learning_rate": 4e-05,
+      "loss": 1.6733,
+      "step": 156250
+    },
+    {
+      "epoch": 1.0,
+      "eval_bleu": 25.9104,
+      "eval_gen_len": 15.4366,
+      "eval_loss": 1.5656293630599976,
+      "eval_meteor": 0.5364,
+      "eval_runtime": 284.4687,
+      "eval_samples_per_second": 28.123,
+      "eval_steps_per_second": 0.439,
+      "step": 156250
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.892058849334717,
+      "learning_rate": 3e-05,
+      "loss": 1.6415,
+      "step": 312500
+    },
+    {
+      "epoch": 2.0,
+      "eval_bleu": 26.7033,
+      "eval_gen_len": 15.6291,
+      "eval_loss": 1.5193185806274414,
+      "eval_meteor": 0.5449,
+      "eval_runtime": 290.9826,
+      "eval_samples_per_second": 27.493,
+      "eval_steps_per_second": 0.43,
+      "step": 312500
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.1033926010131836,
+      "learning_rate": 2e-05,
+      "loss": 1.5831,
+      "step": 468750
+    },
+    {
+      "epoch": 3.0,
+      "eval_bleu": 27.2345,
+      "eval_gen_len": 15.5704,
+      "eval_loss": 1.490054965019226,
+      "eval_meteor": 0.5479,
+      "eval_runtime": 274.3255,
+      "eval_samples_per_second": 29.162,
+      "eval_steps_per_second": 0.456,
+      "step": 468750
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.870877742767334,
+      "learning_rate": 1e-05,
+      "loss": 1.5352,
+      "step": 625000
+    },
+    {
+      "epoch": 4.0,
+      "eval_bleu": 27.7312,
+      "eval_gen_len": 15.528,
+      "eval_loss": 1.4695134162902832,
+      "eval_meteor": 0.5521,
+      "eval_runtime": 247.2387,
+      "eval_samples_per_second": 32.357,
+      "eval_steps_per_second": 0.506,
+      "step": 625000
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.8743324279785156,
+      "learning_rate": 0.0,
+      "loss": 1.4946,
+      "step": 781250
+    },
+    {
+      "epoch": 5.0,
+      "eval_bleu": 27.9356,
+      "eval_gen_len": 15.548,
+      "eval_loss": 1.4556750059127808,
+      "eval_meteor": 0.5543,
+      "eval_runtime": 242.25,
+      "eval_samples_per_second": 33.024,
+      "eval_steps_per_second": 0.516,
+      "step": 781250
+    },
+    {
+      "epoch": 5.0,
+      "step": 781250,
+      "total_flos": 6.095033471871222e+17,
+      "train_loss": 1.58551646,
+      "train_runtime": 202290.4129,
+      "train_samples_per_second": 247.169,
+      "train_steps_per_second": 3.862
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 781250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.095033471871222e+17,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38bb9018f38096365eda4f6b6eefb3c91ad3010caeb8da767c33d5abd58aeb48
+size 5368