End of training

README.md

@@ -0,0 +1,59 @@
+---
+license: mit
+base_model: gpt2
+tags:
+- generated_from_trainer
+model-index:
+- name: bert-base-banking77-pt2
+  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. -->
+
+# bert-base-banking77-pt2
+
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.2330
+
+## 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: 1
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 19.3915       | 1.0   | 10   | 4.2030          |
+| 3.99          | 2.0   | 20   | 3.7262          |
+| 3.2015        | 3.0   | 30   | 3.2330          |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

added_tokens.json

@@ -0,0 +1,15 @@
+{
+  "<INGR_END>": 50264,
+  "<INGR_START>": 50262,
+  "<INPUT_END>": 50259,
+  "<INPUT_START>": 50257,
+  "<INSTR_END>": 50267,
+  "<INSTR_START>": 50265,
+  "<NEXT_INGR>": 50263,
+  "<NEXT_INPUT>": 50258,
+  "<NEXT_STEP>": 50266,
+  "<RECIPE_END>": 50269,
+  "<RECIPE_START>": 50268,
+  "<TITLE_END>": 50261,
+  "<TITLE_START>": 50260
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 50270
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.35.2"
+}

logs/events.out.tfevents.1702135689.62a1e4c74a80.18125.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eef68f5c33606a80a51f360015dec3111cf6673e85a459e3f2959a3239fc92c0
+size 4607

logs/events.out.tfevents.1702136019.62a1e4c74a80.27684.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb2da1fc21c725f7094b82ec13d944fe8cb3e25473ad372257aadeafdb0eb2bd
+size 4606

logs/events.out.tfevents.1702136233.62a1e4c74a80.28401.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f02fcaae7b8f2bc495bfced5b15e254f734eb33a73f14777b63914c57fb379ed
+size 8806

logs/events.out.tfevents.1702136512.62a1e4c74a80.28401.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b66631c802141a6210f8b52fb9b1f1333002f5d61f578d19a4b2293dae7cbe23
+size 8388

logs/events.out.tfevents.1702136802.62a1e4c74a80.28401.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5204396018d2ba3e29ea854b35753a904ac5dcfbd678ed4a965f48b9f2514e1b
+size 6062

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f88ed9b657a61945ca24ea5091d4c155db10756fe037cc5b74535e0209d21b87
+size 497814144

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,126 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "<INPUT_START>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "<NEXT_INPUT>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "<INPUT_END>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "<TITLE_START>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "<TITLE_END>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "<INGR_START>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "<NEXT_INGR>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "<INGR_END>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "<INSTR_START>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "<NEXT_STEP>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "<INSTR_END>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "<RECIPE_START>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "<RECIPE_END>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": 3.2330009937286377,
+  "best_model_checkpoint": "bert-base-banking77-pt2/checkpoint-30",
+  "epoch": 3.0,
+  "eval_steps": 10,
+  "global_step": 30,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 19.3915,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 4.202950954437256,
+      "eval_runtime": 0.2436,
+      "eval_samples_per_second": 41.048,
+      "eval_steps_per_second": 8.21,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 3.99,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.726235866546631,
+      "eval_runtime": 0.2518,
+      "eval_samples_per_second": 39.71,
+      "eval_steps_per_second": 7.942,
+      "step": 20
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 3.2015,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 3.2330009937286377,
+      "eval_runtime": 0.1321,
+      "eval_samples_per_second": 75.687,
+      "eval_steps_per_second": 15.137,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "step": 30,
+      "total_flos": 1959690240000.0,
+      "train_loss": 8.860979080200195,
+      "train_runtime": 31.0574,
+      "train_samples_per_second": 0.966,
+      "train_steps_per_second": 0.966
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 30,
+  "num_train_epochs": 3,
+  "save_steps": 10,
+  "total_flos": 1959690240000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7970c7cd0327b87b79a84430af71446e02fdc5a4b54a72df844b541e577b729e
+size 4600