Time is 206.50926883220671, Memory is 9.6GB

README.md

@@ -0,0 +1,63 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- xsum
+model-index:
+- name: retnet-Final-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-Final-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: 4.2312
+
+## 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: 0.001
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 4.9454        | 1.0   | 5762  | 4.4511          |
+| 4.3365        | 2.0   | 11525 | 4.2707          |
+| 4.2137        | 3.0   | 17286 | 4.2312          |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

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": 128,
+  "decoder_ffn_embed_dim": 128,
+  "decoder_layers": 3,
+  "decoder_normalize_before": true,
+  "decoder_retention_heads": 2,
+  "decoder_value_embed_dim": 128,
+  "deepnorm": false,
+  "drop_path_rate": 0.0,
+  "dropout": 0.0,
+  "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": 128,
+  "subln": true,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "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": "4.35.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dc15bfc5e194ebaea5d43860bde52899f4ad666cc7ff8ef1d58dc7c02b1e9d8
+size 53046256

runs/Nov28_15-03-52_7903b5605131/events.out.tfevents.1701183832.7903b5605131.488.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc013a18a4c2e236da3c11f9371038b772e57919fa9e2500d9d060e9e61e992
+size 6114

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 sha256:035739b4352bb749fbea6b490414c7186d331812f6e5d5632095f82cb461abdd
+size 4600