Upload 13 files

README.md

@@ -0,0 +1,56 @@
+---
+base_model: /kaggle/working
+tags:
+- generated_from_trainer
+model-index:
+- name: 2_epoch
+  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. -->
+
+# 2_epoch
+
+This model is a fine-tuned version of [/kaggle/working](https://huggingface.co//kaggle/working) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1586
+- Cer: 24.1677
+
+## 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: 0.0001
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 512
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.33.0
+- Pytorch 2.0.0
+- Datasets 2.14.5
+- Tokenizers 0.13.3

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<mask>": 64000
+}

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 1.0,
+    "eval_cer": 24.167687516221125,
+    "eval_loss": 0.15863220393657684,
+    "eval_runtime": 53.136,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 37.639,
+    "eval_steps_per_second": 2.352,
+    "train_loss": 0.1019569671914423,
+    "train_runtime": 12051.5325,
+    "train_samples": 1019436,
+    "train_samples_per_second": 84.59,
+    "train_steps_per_second": 0.165
+}

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "/kaggle/working",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "MBartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.2,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.4,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.2,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_position_embeddings": 1024,
+  "model_type": "mbart",
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "tokenizer_class": "PhobertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.0",
+  "use_cache": true,
+  "vocab_size": 64001
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "eval_cer": 24.167687516221125,
+    "eval_loss": 0.15863220393657684,
+    "eval_runtime": 53.136,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 37.639,
+    "eval_steps_per_second": 2.352
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.33.0"
+}

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "PhobertTokenizer",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.1019569671914423,
+    "train_runtime": 12051.5325,
+    "train_samples": 1019436,
+    "train_samples_per_second": 84.59,
+    "train_steps_per_second": 0.165
+}

trainer_state.json

@@ -0,0 +1,142 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9999529153260613,
+  "eval_steps": 10000,
+  "global_step": 1991,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.497739829231542e-05,
+      "loss": 0.1028,
+      "step": 100
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 8.995479658463084e-05,
+      "loss": 0.1144,
+      "step": 200
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 8.493219487694626e-05,
+      "loss": 0.1181,
+      "step": 300
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 7.990959316926167e-05,
+      "loss": 0.1163,
+      "step": 400
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 7.48869914615771e-05,
+      "loss": 0.1128,
+      "step": 500
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 6.986438975389252e-05,
+      "loss": 0.1126,
+      "step": 600
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 6.484178804620794e-05,
+      "loss": 0.1125,
+      "step": 700
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 5.981918633852336e-05,
+      "loss": 0.1092,
+      "step": 800
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 5.479658463083878e-05,
+      "loss": 0.1047,
+      "step": 900
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.977398292315419e-05,
+      "loss": 0.1046,
+      "step": 1000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.475138121546962e-05,
+      "loss": 0.0999,
+      "step": 1100
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 3.972877950778504e-05,
+      "loss": 0.0952,
+      "step": 1200
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.470617780010045e-05,
+      "loss": 0.0928,
+      "step": 1300
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 2.968357609241587e-05,
+      "loss": 0.0945,
+      "step": 1400
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 2.466097438473129e-05,
+      "loss": 0.0916,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.963837267704671e-05,
+      "loss": 0.0914,
+      "step": 1600
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.4615770969362131e-05,
+      "loss": 0.0917,
+      "step": 1700
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 9.59316926167755e-06,
+      "loss": 0.0912,
+      "step": 1800
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 4.5705675539929685e-06,
+      "loss": 0.0914,
+      "step": 1900
+    },
+    {
+      "epoch": 1.0,
+      "step": 1991,
+      "total_flos": 4.238662023983923e+16,
+      "train_loss": 0.1019569671914423,
+      "train_runtime": 12051.5325,
+      "train_samples_per_second": 84.59,
+      "train_steps_per_second": 0.165
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1991,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 4.238662023983923e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6669c554346b49f4a3a14475253ec39c3d66c9c9219e5c6a9b46277ebe79c6d9
+size 4219