Upload 15 files

README.md

@@ -0,0 +1,52 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- arrow
+model-index:
+- name: hubert-pythia-70m_librispeech.train.mix
+  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. -->
+
+# hubert-pythia-70m_librispeech.train.mix
+
+This model is a fine-tuned version of [speechmix/pythia-70m-test](https://huggingface.co/speechmix/pythia-70m-test) on the arrow dataset.
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 50000
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.31.0.dev0
+- Pytorch 2.0.0+cu118
+- Datasets 2.13.1
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.42,
+    "train_loss": 2.0794223800468443,
+    "train_runtime": 42713.4006,
+    "train_samples": 281241,
+    "train_samples_per_second": 9.365,
+    "train_steps_per_second": 1.171
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "speechmix/pythia-70m-test",
+  "architectures": [
+    "HubertGPTNeoXCrossForConditionalGeneration"
+  ],
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "cross_hidden_size": 768,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 6,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0.dev0",
+  "use_cache": false,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1f2d34d736997e581b4d7ec29ed8fd1b4db1011c9476aed4ad74a881e4ac0c9
+size 741157929

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

summary.txt

@@ -0,0 +1,4 @@
+validation.clean wer score:1.444689533473034
+validation.other wer score:1.5404746084480303
+test.clean wer score:1.5075478388612389
+test.other wer score:1.5289747894363885

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.42,
+    "train_loss": 2.0794223800468443,
+    "train_runtime": 42713.4006,
+    "train_samples": 281241,
+    "train_samples_per_second": 9.365,
+    "train_steps_per_second": 1.171
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96b9128f4e435c7d5a2217554bde5666402064011827a7577e35131440618dc0
+size 4027