Training in progress, epoch 1

README.md

@@ -0,0 +1,78 @@
+---
+license: apache-2.0
+base_model: distilgpt2
+tags:
+- generated_from_trainer
+datasets:
+- wikitext
+metrics:
+- accuracy
+model-index:
+- name: clm
+  results:
+  - task:
+      name: Causal Language Modeling
+      type: text-generation
+    dataset:
+      name: wikitext wikitext-2-raw-v1
+      type: wikitext
+      config: wikitext-2-raw-v1
+      split: validation
+      args: wikitext-2-raw-v1
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.37187601824698596
+---
+
+<!-- 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. -->
+
+# clm
+
+This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the wikitext wikitext-2-raw-v1 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.4802
+- Accuracy: 0.3719
+
+## 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: 3e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 0
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 3.6158        | 0.99  | 72   | 3.4802          | 0.3719   |
+
+
+### Framework versions
+
+- Transformers 4.33.0.dev0
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.4
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 0.99,
+    "eval_accuracy": 0.37187601824698596,
+    "eval_loss": 3.4801909923553467,
+    "eval_runtime": 104.7921,
+    "eval_samples": 240,
+    "eval_samples_per_second": 2.29,
+    "eval_steps_per_second": 0.286,
+    "perplexity": 32.46592222670883,
+    "train_loss": 3.7061044375101724,
+    "train_runtime": 2296.6495,
+    "train_samples": 2318,
+    "train_samples_per_second": 1.009,
+    "train_steps_per_second": 0.031
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 0.99,
+    "eval_accuracy": 0.37187601824698596,
+    "eval_loss": 3.4801909923553467,
+    "eval_runtime": 104.7921,
+    "eval_samples": 240,
+    "eval_samples_per_second": 2.29,
+    "eval_steps_per_second": 0.286,
+    "perplexity": 32.46592222670883
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.33.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5429067da8fb648dfe8ccf6e5dbf2eb368f8e329340e7bee856ee6d7d5768aa
+size 498813948

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.99,
+    "train_loss": 3.7061044375101724,
+    "train_runtime": 2296.6495,
+    "train_samples": 2318,
+    "train_samples_per_second": 1.009,
+    "train_steps_per_second": 0.031
+}

trainer_state.json

@@ -0,0 +1,79 @@
+{
+  "best_metric": 0.37187601824698596,
+  "best_model_checkpoint": ".\\output\\checkpoint-72",
+  "epoch": 0.993103448275862,
+  "eval_steps": 500,
+  "global_step": 72,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.90625e-05,
+      "loss": 3.9372,
+      "step": 10
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 2.4375e-05,
+      "loss": 3.76,
+      "step": 20
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.96875e-05,
+      "loss": 3.6869,
+      "step": 30
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.5e-05,
+      "loss": 3.6689,
+      "step": 40
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.03125e-05,
+      "loss": 3.6483,
+      "step": 50
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 5.625e-06,
+      "loss": 3.6523,
+      "step": 60
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 9.375e-07,
+      "loss": 3.6158,
+      "step": 70
+    },
+    {
+      "epoch": 0.99,
+      "eval_accuracy": 0.37187601824698596,
+      "eval_loss": 3.4801909923553467,
+      "eval_runtime": 101.4158,
+      "eval_samples_per_second": 2.366,
+      "eval_steps_per_second": 0.296,
+      "step": 72
+    },
+    {
+      "epoch": 0.99,
+      "step": 72,
+      "total_flos": 602027713363968.0,
+      "train_loss": 3.7061044375101724,
+      "train_runtime": 2296.6495,
+      "train_samples_per_second": 1.009,
+      "train_steps_per_second": 0.031
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 72,
+  "num_train_epochs": 1,
+  "save_steps": 100.0,
+  "total_flos": 602027713363968.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eecc1a23813468abbfad1ed69d75b50571c855bff724ea47421074dd8f61c1e0
+size 4027