Training in progress, step 500

README.md

@@ -0,0 +1,99 @@
+---
+language:
+- cy
+license: apache-2.0
+base_model: facebook/wav2vec2-large-xlsr-53
+tags:
+- automatic-speech-recognition
+- python/custom_common_voice.py
+- generated_from_trainer
+datasets:
+- custom_common_voice
+metrics:
+- wer
+model-index:
+- name: wav2vec2-xlsr-53-ft-ccv-en-cy
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: PYTHON/CUSTOM_COMMON_VOICE.PY - CY
+      type: custom_common_voice
+      config: cy
+      split: validation
+      args: 'Config: cy, Training split: train, Eval split: validation'
+    metrics:
+    - name: Wer
+      type: wer
+      value: 0.21777283505046477
+---
+
+<!-- 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. -->
+
+# wav2vec2-xlsr-53-ft-ccv-en-cy
+
+This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the PYTHON/CUSTOM_COMMON_VOICE.PY - CY dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2909
+- Wer: 0.2178
+
+## 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: 0.0003
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 800
+- training_steps: 9000
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 5.8377        | 0.25  | 500  | 1.2190          | 0.8569 |
+| 0.9829        | 0.51  | 1000 | 0.5585          | 0.4701 |
+| 0.45          | 0.76  | 1500 | 0.4735          | 0.3901 |
+| 0.3151        | 1.01  | 2000 | 0.4125          | 0.3418 |
+| 0.2524        | 1.26  | 2500 | 0.3831          | 0.3117 |
+| 0.243         | 1.52  | 3000 | 0.3661          | 0.3078 |
+| 0.2341        | 1.77  | 3500 | 0.3489          | 0.2883 |
+| 0.211         | 2.02  | 4000 | 0.3500          | 0.2738 |
+| 0.1702        | 2.27  | 4500 | 0.3459          | 0.2704 |
+| 0.1634        | 2.53  | 5000 | 0.3305          | 0.2583 |
+| 0.1608        | 2.78  | 5500 | 0.3137          | 0.2479 |
+| 0.1481        | 3.03  | 6000 | 0.3288          | 0.2562 |
+| 0.1216        | 3.28  | 6500 | 0.3174          | 0.2446 |
+| 0.1181        | 3.54  | 7000 | 0.3000          | 0.2325 |
+| 0.1143        | 3.79  | 7500 | 0.2929          | 0.2326 |
+| 0.1049        | 4.04  | 8000 | 0.2921          | 0.2218 |
+| 0.0913        | 4.29  | 8500 | 0.2968          | 0.2208 |
+| 0.0883        | 4.55  | 9000 | 0.2909          | 0.2178 |
+
+
+### Framework versions
+
+- Transformers 4.33.3
+- Pytorch 2.0.1+cu117
+- Datasets 2.14.5
+- Tokenizers 0.13.3

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 72,
+  "<s>": 71
+}

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 4.55,
+    "eval_loss": 0.2908598780632019,
+    "eval_runtime": 1109.9533,
+    "eval_samples": 26295,
+    "eval_samples_per_second": 23.69,
+    "eval_steps_per_second": 0.741,
+    "eval_wer": 0.21777283505046477,
+    "train_loss": 0.47586327913072374,
+    "train_runtime": 55725.2112,
+    "train_samples": 126693,
+    "train_samples_per_second": 10.336,
+    "train_steps_per_second": 0.162
+}

config.json

@@ -0,0 +1,116 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "activation_dropout": 0.0,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 70,
+  "proj_codevector_dim": 768,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 73,
+  "xvector_output_dim": 512
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.55,
+    "eval_loss": 0.2908598780632019,
+    "eval_runtime": 1109.9533,
+    "eval_samples": 26295,
+    "eval_samples_per_second": 23.69,
+    "eval_steps_per_second": 0.741,
+    "eval_wer": 0.21777283505046477
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a61b18c9ee9860f31d39490c222d84fe01c48b00e6f7e1c3e09ce18165714fd8
+size 1262106780

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:640af29a66bf0fca78e79c6a8f356ea119a2dcedfd185bf572062ab2d460c286
+size 1262201133

runs/Mar05_08-26-36_6f484a5b3164/events.out.tfevents.1709633973.6f484a5b3164.1068.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17b7eae01d3551ee25179d0dcc46de1ed12b48af48c559f800e4497c69d45bda
+size 6860

runs/Oct12_12-35-37_8bec42e5e08c/events.out.tfevents.1697116115.8bec42e5e08c.128398.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f23bc9ed20787593c7faf592201602fe1cf35def9ac1cb498ed11a367e6476c
+size 9821

runs/Oct12_21-06-48_8bec42e5e08c/events.out.tfevents.1697150543.8bec42e5e08c.128877.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d2dff4eb34b2fb556943985a86283b971dd466ac9160e4f37efcb76876831ed
+size 15403

runs/Oct12_21-06-48_8bec42e5e08c/events.out.tfevents.1697206843.8bec42e5e08c.128877.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12386e0080f66dcacc204d5bca1aeafb6dd239e27c3944ad501b3cb823d0012a
+size 406

runs/Oct13_21-34-07_8bec42e5e08c/events.out.tfevents.1697231979.8bec42e5e08c.152123.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4be896e7c005133fb626a14277688a03c401441b0126d76e1ecb589f4292619
+size 15403

runs/Oct13_21-34-07_8bec42e5e08c/events.out.tfevents.1697278531.8bec42e5e08c.152123.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab6851d72d7a8ce34b81e108d994fdd2a363c41a3b8bf4eacfcc205fe1504e24
+size 406

runs/Oct16_10-01-23_8bec42e5e08c/events.out.tfevents.1697451328.8bec42e5e08c.175326.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6d067310699db36ae9c6ae4fbbeef5b609e07a0ec0bc9682839f63f9a7c18ad
+size 15403

runs/Oct16_10-01-23_8bec42e5e08c/events.out.tfevents.1697509159.8bec42e5e08c.175326.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06a734c7f708943c6cb0747de35e10fa6afab27ca9a49e1acc2585d23270dd31
+size 406

runs/Oct17_10-22-05_8bec42e5e08c/events.out.tfevents.1697538029.8bec42e5e08c.356730.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd31597a301ec4ce39ce5a26a5646208e808a74276f0ed1d73331acd15cf0cd3
+size 15403

runs/Oct17_10-22-05_8bec42e5e08c/events.out.tfevents.1697595206.8bec42e5e08c.356730.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20aa0529edd6ffdd713ca594feedd71853c7a668e9b63474ddc587456296a876
+size 406

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "added_tokens_decoder": {
+    "69": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "70": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "71": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "72": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "<s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.55,
+    "train_loss": 0.47586327913072374,
+    "train_runtime": 55725.2112,
+    "train_samples": 126693,
+    "train_samples_per_second": 10.336,
+    "train_steps_per_second": 0.162
+}

trainer_state.json

@@ -0,0 +1,322 @@
+{
+  "best_metric": 0.2908598780632019,
+  "best_model_checkpoint": "/models/hfhub/DewiBrynJones/wav2vec2-xlsr-53-ft-ccv-en-cy/checkpoint-9000",
+  "epoch": 4.545454545454545,
+  "eval_steps": 500,
+  "global_step": 9000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00014925,
+      "loss": 5.8377,
+      "step": 400
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 1.2190359830856323,
+      "eval_runtime": 1220.4523,
+      "eval_samples_per_second": 21.545,
+      "eval_steps_per_second": 0.674,
+      "eval_wer": 0.8568814654720188,
+      "step": 500
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00029925,
+      "loss": 0.9829,
+      "step": 800
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 0.5584714412689209,
+      "eval_runtime": 1188.1001,
+      "eval_samples_per_second": 22.132,
+      "eval_steps_per_second": 0.692,
+      "eval_wer": 0.4700631596617496,
+      "step": 1000
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00028543902439024386,
+      "loss": 0.45,
+      "step": 1200
+    },
+    {
+      "epoch": 0.76,
+      "eval_loss": 0.4735090434551239,
+      "eval_runtime": 1202.8188,
+      "eval_samples_per_second": 21.861,
+      "eval_steps_per_second": 0.683,
+      "eval_wer": 0.39008750026229094,
+      "step": 1500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00027080487804878047,
+      "loss": 0.3636,
+      "step": 1600
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00025617073170731703,
+      "loss": 0.3151,
+      "step": 2000
+    },
+    {
+      "epoch": 1.01,
+      "eval_loss": 0.4124945402145386,
+      "eval_runtime": 1160.0644,
+      "eval_samples_per_second": 22.667,
+      "eval_steps_per_second": 0.709,
+      "eval_wer": 0.34183435801666073,
+      "step": 2000
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00024153658536585365,
+      "loss": 0.2524,
+      "step": 2400
+    },
+    {
+      "epoch": 1.26,
+      "eval_loss": 0.3830628991127014,
+      "eval_runtime": 1409.4338,
+      "eval_samples_per_second": 18.656,
+      "eval_steps_per_second": 0.583,
+      "eval_wer": 0.3117191598296158,
+      "step": 2500
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00022690243902439024,
+      "loss": 0.243,
+      "step": 2800
+    },
+    {
+      "epoch": 1.52,
+      "eval_loss": 0.3661448061466217,
+      "eval_runtime": 1425.6726,
+      "eval_samples_per_second": 18.444,
+      "eval_steps_per_second": 0.577,
+      "eval_wer": 0.30780368046666806,
+      "step": 3000
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.0002122682926829268,
+      "loss": 0.2341,
+      "step": 3200
+    },
+    {
+      "epoch": 1.77,
+      "eval_loss": 0.3488619327545166,
+      "eval_runtime": 1416.3145,
+      "eval_samples_per_second": 18.566,
+      "eval_steps_per_second": 0.58,
+      "eval_wer": 0.2883060201019787,
+      "step": 3500
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.00019763414634146341,
+      "loss": 0.2235,
+      "step": 3600
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 0.00018299999999999998,
+      "loss": 0.211,
+      "step": 4000
+    },
+    {
+      "epoch": 2.02,
+      "eval_loss": 0.34998372197151184,
+      "eval_runtime": 1154.299,
+      "eval_samples_per_second": 22.78,
+      "eval_steps_per_second": 0.712,
+      "eval_wer": 0.27384434605619323,
+      "step": 4000
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 0.0001683658536585366,
+      "loss": 0.1702,
+      "step": 4400
+    },
+    {
+      "epoch": 2.27,
+      "eval_loss": 0.34594303369522095,
+      "eval_runtime": 1230.9263,
+      "eval_samples_per_second": 21.362,
+      "eval_steps_per_second": 0.668,
+      "eval_wer": 0.27035272887508655,
+      "step": 4500
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 0.00015373170731707315,
+      "loss": 0.1634,
+      "step": 4800
+    },
+    {
+      "epoch": 2.53,
+      "eval_loss": 0.33047276735305786,
+      "eval_runtime": 1138.5459,
+      "eval_samples_per_second": 23.095,
+      "eval_steps_per_second": 0.722,
+      "eval_wer": 0.2583125249176406,
+      "step": 5000
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 0.00013909756097560974,
+      "loss": 0.1608,
+      "step": 5200
+    },
+    {
+      "epoch": 2.78,
+      "eval_loss": 0.3136747479438782,
+      "eval_runtime": 1199.9023,
+      "eval_samples_per_second": 21.914,
+      "eval_steps_per_second": 0.685,
+      "eval_wer": 0.24792580313490148,
+      "step": 5500
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 0.00012446341463414633,
+      "loss": 0.1542,
+      "step": 5600
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 0.00010982926829268292,
+      "loss": 0.1481,
+      "step": 6000
+    },
+    {
+      "epoch": 3.03,
+      "eval_loss": 0.32883504033088684,
+      "eval_runtime": 1167.9676,
+      "eval_samples_per_second": 22.513,
+      "eval_steps_per_second": 0.704,
+      "eval_wer": 0.2562183939400298,
+      "step": 6000
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 9.519512195121951e-05,
+      "loss": 0.1216,
+      "step": 6400
+    },
+    {
+      "epoch": 3.28,
+      "eval_loss": 0.3174259662628174,
+      "eval_runtime": 1161.665,
+      "eval_samples_per_second": 22.636,
+      "eval_steps_per_second": 0.708,
+      "eval_wer": 0.24461464213022222,
+      "step": 6500
+    },
+    {
+      "epoch": 3.43,
+      "learning_rate": 8.05609756097561e-05,
+      "loss": 0.1181,
+      "step": 6800
+    },
+    {
+      "epoch": 3.54,
+      "eval_loss": 0.30002185702323914,
+      "eval_runtime": 1207.6988,
+      "eval_samples_per_second": 21.773,
+      "eval_steps_per_second": 0.681,
+      "eval_wer": 0.2324569318253352,
+      "step": 7000
+    },
+    {
+      "epoch": 3.64,
+      "learning_rate": 6.592682926829267e-05,
+      "loss": 0.1143,
+      "step": 7200
+    },
+    {
+      "epoch": 3.79,
+      "eval_loss": 0.29287537932395935,
+      "eval_runtime": 1095.1242,
+      "eval_samples_per_second": 24.011,
+      "eval_steps_per_second": 0.751,
+      "eval_wer": 0.23258702813857357,
+      "step": 7500
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 5.129268292682927e-05,
+      "loss": 0.1139,
+      "step": 7600
+    },
+    {
+      "epoch": 4.04,
+      "learning_rate": 3.665853658536585e-05,
+      "loss": 0.1049,
+      "step": 8000
+    },
+    {
+      "epoch": 4.04,
+      "eval_loss": 0.2921387255191803,
+      "eval_runtime": 1091.9168,
+      "eval_samples_per_second": 24.082,
+      "eval_steps_per_second": 0.753,
+      "eval_wer": 0.22178483748452482,
+      "step": 8000
+    },
+    {
+      "epoch": 4.24,
+      "learning_rate": 2.2024390243902437e-05,
+      "loss": 0.0913,
+      "step": 8400
+    },
+    {
+      "epoch": 4.29,
+      "eval_loss": 0.2968423664569855,
+      "eval_runtime": 1104.263,
+      "eval_samples_per_second": 23.812,
+      "eval_steps_per_second": 0.744,
+      "eval_wer": 0.2208196067734016,
+      "step": 8500
+    },
+    {
+      "epoch": 4.44,
+      "learning_rate": 7.4268292682926826e-06,
+      "loss": 0.0883,
+      "step": 8800
+    },
+    {
+      "epoch": 4.55,
+      "eval_loss": 0.2908598780632019,
+      "eval_runtime": 1095.7607,
+      "eval_samples_per_second": 23.997,
+      "eval_steps_per_second": 0.75,
+      "eval_wer": 0.21777283505046477,
+      "step": 9000
+    },
+    {
+      "epoch": 4.55,
+      "step": 9000,
+      "total_flos": 8.920242900072627e+19,
+      "train_loss": 0.47586327913072374,
+      "train_runtime": 55725.2112,
+      "train_samples_per_second": 10.336,
+      "train_steps_per_second": 0.162
+    }
+  ],
+  "logging_steps": 400,
+  "max_steps": 9000,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 8.920242900072627e+19,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41391707330b917a182f50c624eca53c007657cb0e0a4d70d8f10b192c1076b1
+size 4984

vocab.json

@@ -0,0 +1,73 @@
+{
+  "#": 1,
+  "'": 2,
+  "+": 3,
+  "-": 4,
+  "[PAD]": 70,
+  "[UNK]": 69,
+  "a": 5,
+  "b": 6,
+  "c": 7,
+  "d": 8,
+  "e": 9,
+  "f": 10,
+  "g": 11,
+  "h": 12,
+  "i": 13,
+  "j": 14,
+  "k": 15,
+  "l": 16,
+  "m": 17,
+  "n": 18,
+  "o": 19,
+  "p": 20,
+  "q": 21,
+  "r": 22,
+  "s": 23,
+  "t": 24,
+  "u": 25,
+  "v": 26,
+  "w": 27,
+  "x": 28,
+  "y": 29,
+  "z": 30,
+  "|": 0,
+  "ß": 31,
+  "à": 32,
+  "á": 33,
+  "â": 34,
+  "ã": 35,
+  "ä": 36,
+  "ç": 37,
+  "è": 38,
+  "é": 39,
+  "ê": 40,
+  "ë": 41,
+  "î": 42,
+  "ï": 43,
+  "ò": 44,
+  "ó": 45,
+  "ô": 46,
+  "ö": 47,
+  "ø": 48,
+  "ú": 49,
+  "û": 50,
+  "ü": 51,
+  "ÿ": 52,
+  "ı": 53,
+  "ł": 54,
+  "ń": 55,
+  "ō": 56,
+  "œ": 57,
+  "ř": 58,
+  "ş": 59,
+  "š": 60,
+  "ū": 61,
+  "ŵ": 62,
+  "ŷ": 63,
+  "ə": 64,
+  "α": 65,
+  "„": 66,
+  "奔": 67,
+  "熊": 68
+}