Time is 220.16162587006886 minutes, Memory is 9.4GB

README.md

@@ -0,0 +1,61 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- xsum
+model-index:
+- name: ReFormer-small-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. -->
+
+# ReFormer-small-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: 4.9202
+
+## 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
+- 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 |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 5.603         | 1.0   | 23050 | 5.1617          |
+| 5.0493        | 2.0   | 46100 | 4.9603          |
+| 4.9307        | 3.0   | 69150 | 4.9202          |
+
+
+### 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 +1,55 @@
+{
+  "architectures": [
+    "ReformerModelWithLMHead"
+  ],
+  "attention_head_size": 32,
+  "attn_layers": [
+    "local",
+    "lsh",
+    "local",
+    "lsh",
+    "local",
+    "lsh"
+  ],
+  "axial_norm_std": 1.0,
+  "axial_pos_embds": true,
+  "axial_pos_embds_dim": [
+    11,
+    11
+  ],
+  "axial_pos_shape": [
+    32,
+    32
+  ],
+  "chunk_size_lm_head": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 50256,
+  "feed_forward_size": 32,
+  "hash_seed": null,
+  "hidden_act": "relu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 22,
+  "initializer_range": 0.02,
+  "is_decoder": true,
+  "layer_norm_eps": 1e-12,
+  "local_attention_probs_dropout_prob": 0.0,
+  "local_attn_chunk_length": 64,
+  "local_num_chunks_after": 0,
+  "local_num_chunks_before": 1,
+  "lsh_attention_probs_dropout_prob": 0.0,
+  "lsh_attn_chunk_length": 64,
+  "lsh_num_chunks_after": 0,
+  "lsh_num_chunks_before": 1,
+  "max_position_embeddings": 1024,
+  "model_type": "reformer",
+  "num_attention_heads": 3,
+  "num_buckets": 32,
+  "num_hashes": 1,
+  "num_hidden_layers": 6,
+  "pad_token_id": 50257,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 50259
+}

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 sha256:5c683147c4cff616729496fa771adee11a0593eaf9710cc9a4f2d47c81ab90d0
+size 13696588

runs/Dec03_00-51-05_9c3128e00dd8/events.out.tfevents.1701564665.9c3128e00dd8.155.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc68db3572dabef50168ae75e30e38201c46be3217c9a19b492eeb17df3ba051
+size 4751

runs/Dec03_00-51-33_9c3128e00dd8/events.out.tfevents.1701564694.9c3128e00dd8.155.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25d9f916a48886d0432a080e4b218304f8b4bc60054679f0c13247644dba7062
+size 6419

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 sha256:389b135b8c5a874e75f05a1b2ce998e0ee982e1ea0e10c4606698225cff7155d
+size 4600