retnet-summarization

README.md

@@ -0,0 +1,61 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- xsum
+model-index:
+- name: retnet-summarization
+  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. -->
+
+# retnet-summarization
+
+This model is a fine-tuned version of [](https://huggingface.co/) on the xsum dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.8453
+
+## 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: 0.0006
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 4.3722        | 1.0   | 12500 | 3.8453          |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|pad|>": 50257,
+  "<|sep|>": 50258
+}

config.json

@@ -0,0 +1,37 @@
+{
+  "activation_dropout": 0.0,
+  "activation_fn": "swish",
+  "architectures": [
+    "RetNetForCausalLM"
+  ],
+  "decoder_embed_dim": 512,
+  "decoder_ffn_embed_dim": 864,
+  "decoder_layers": 6,
+  "decoder_normalize_before": true,
+  "decoder_retention_heads": 2,
+  "decoder_value_embed_dim": 864,
+  "deepnorm": false,
+  "drop_path_rate": 0.1,
+  "dropout": 0.1,
+  "eos_token_id": 50256,
+  "forward_impl": "parallel",
+  "initializer_range": 0.02,
+  "is_decoder": true,
+  "layernorm_embedding": true,
+  "layernorm_eps": 1e-06,
+  "model_type": "retnet",
+  "no_scale_embedding": false,
+  "output_retentions": false,
+  "pad_token_id": 50257,
+  "recurrent_chunk_size": 512,
+  "subln": true,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0",
+  "use_cache": true,
+  "use_ffn_rms_norm": false,
+  "use_glu": true,
+  "use_lm_decay": false,
+  "vocab_size": 50259,
+  "z_loss_coeff": 0.0
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 50256,
+  "pad_token_id": 50257,
+  "transformers_version": "4.35.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:621100b7d82b0c756b370ff4e4ad210f296a81bc20b0903f644049236b779c35
+size 282181632

runs/Nov04_20-14-37_06626b08ccdc/events.out.tfevents.1699128878.06626b08ccdc.742.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:593a2d090a49c2d5cb89c2d13a5a6bc653b2fa0a6b7d78123ecb79540b09fabe
+size 5224

runs/Nov04_20-14-37_06626b08ccdc/events.out.tfevents.1699136493.06626b08ccdc.742.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38dfbbdc37269a13dd13e6b70a2e75a74da1357b7afe921d2a27eafadcd1f8fd
+size 359

special_tokens_map.json

@@ -0,0 +1,19 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "<|sep|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,37 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50258": {
+      "content": "<|sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "pad_token": "<|pad|>",
+  "sep_token": "<|sep|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6758a222c5a8fb23ed432a5ecdcba3b77e388b262c786457940802f927879730
+size 4600