Upload 17 files

README.md

@@ -1,3 +1,59 @@
----
-license: apache-2.0
----
+---
+base_model: output_model_gpt2_20epoch
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: output_model_gpt2_50epoch
+  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. -->
+
+# output_model_gpt2_50epoch
+
+This model is a fine-tuned version of [output_model_gpt2_20epoch](https://huggingface.co/output_model_gpt2_20epoch) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 5.7376
+- Accuracy: 0.5284
+
+## 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: 3
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 18
+- total_train_batch_size: 54
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 30.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

added_tokens.json

@@ -0,0 +1,12 @@
+{
+  "<|action|>": 50257,
+  "<|belief|>": 50263,
+  "<|context|>": 50260,
+  "<|endofaction|>": 50261,
+  "<|endofbelief|>": 50266,
+  "<|endofcontext|>": 50258,
+  "<|endofresponse|>": 50259,
+  "<|response|>": 50265,
+  "<|system|>": 50262,
+  "<|user|>": 50264
+}

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 29.86,
+    "eval_accuracy": 0.5283621816943802,
+    "eval_loss": 5.737628936767578,
+    "eval_runtime": 26.229,
+    "eval_samples": 379,
+    "eval_samples_per_second": 14.45,
+    "eval_steps_per_second": 1.83,
+    "perplexity": 310.327731295789,
+    "train_loss": 0.05997911328854768,
+    "train_runtime": 6173.8501,
+    "train_samples": 1246,
+    "train_samples_per_second": 6.055,
+    "train_steps_per_second": 0.112
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "output_model_gpt2_20epoch",
+  "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": 50267
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 29.86,
+    "eval_accuracy": 0.5283621816943802,
+    "eval_loss": 5.737628936767578,
+    "eval_runtime": 26.229,
+    "eval_samples": 379,
+    "eval_samples_per_second": 14.45,
+    "eval_steps_per_second": 1.83,
+    "perplexity": 310.327731295789
+}

generation_config.json

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

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85cb23c6892d6e094618ab259722e0bb940424a58b46e836bcd8e922278056de
+size 497804928

runs/Jan27_19-25-13_f9b22a5f3ad7/events.out.tfevents.1706383524.f9b22a5f3ad7.21156.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:466552d9c62137e87f1958404cbef69f199d6351f61596848df6e8eadecf55c5
+size 5029

runs/Jan27_19-25-13_f9b22a5f3ad7/events.out.tfevents.1706389726.f9b22a5f3ad7.21156.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c73484fc593caefeda0b116bab62905caa7f5a80b454e258d7e21f4fcb4dc23b
+size 411

special_tokens_map.json

@@ -0,0 +1,95 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|action|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|endofcontext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|endofresponse|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|context|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|endofaction|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|belief|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|response|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|endofbelief|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "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
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,111 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "<|action|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50258": {
+      "content": "<|endofcontext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50259": {
+      "content": "<|endofresponse|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50260": {
+      "content": "<|context|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50261": {
+      "content": "<|endofaction|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50262": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50263": {
+      "content": "<|belief|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50265": {
+      "content": "<|response|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50266": {
+      "content": "<|endofbelief|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|action|>",
+    "<|endofcontext|>",
+    "<|endofresponse|>",
+    "<|context|>",
+    "<|endofaction|>",
+    "<|system|>",
+    "<|belief|>",
+    "<|user|>",
+    "<|response|>",
+    "<|endofbelief|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 29.86,
+    "train_loss": 0.05997911328854768,
+    "train_runtime": 6173.8501,
+    "train_samples": 1246,
+    "train_samples_per_second": 6.055,
+    "train_steps_per_second": 0.112
+}

trainer_state.json

@@ -0,0 +1,34 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 29.85576923076923,
+  "eval_steps": 500,
+  "global_step": 690,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 21.63,
+      "learning_rate": 0.0002753623188405797,
+      "loss": 0.0731,
+      "step": 500
+    },
+    {
+      "epoch": 29.86,
+      "step": 690,
+      "total_flos": 1.9441172348928e+16,
+      "train_loss": 0.05997911328854768,
+      "train_runtime": 6173.8501,
+      "train_samples_per_second": 6.055,
+      "train_steps_per_second": 0.112
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 690,
+  "num_train_epochs": 30,
+  "save_steps": 500,
+  "total_flos": 1.9441172348928e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c59dcfafcb6d01c00cf4062619c1f2e8bb0a3090183759bfa6f40d2a267f8dc2
+size 4600