initial commit

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,52 @@
+---
+license: mit
+base_model: EleutherAI/gpt-neo-125m
+tags:
+- generated_from_trainer
+model-index:
+- name: results
+  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. -->
+
+# results
+
+This model is a fine-tuned version of [EleutherAI/gpt-neo-125m](https://huggingface.co/EleutherAI/gpt-neo-125m) on an unknown dataset.
+
+## 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: 4
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 50.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.40.0
+- Pytorch 2.0.1
+- Datasets 2.19.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 50.0,
+    "total_flos": 2.15757062406144e+16,
+    "train_loss": 0.8480533966651329,
+    "train_runtime": 3860.2683,
+    "train_samples": 413,
+    "train_samples_per_second": 5.349,
+    "train_steps_per_second": 1.347
+}

config.json

@@ -0,0 +1,55 @@
+{
+  "_name_or_path": "EleutherAI/gpt-neo-125m",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTNeoForCausalLM"
+  ],
+  "attention_dropout": 0,
+  "attention_layers": [
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local"
+  ],
+  "attention_types": [
+    [
+      [
+        "global",
+        "local"
+      ],
+      6
+    ]
+  ],
+  "bos_token_id": 50256,
+  "classifier_dropout": 0.1,
+  "embed_dropout": 0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": null,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neo",
+  "num_heads": 12,
+  "num_layers": 12,
+  "resid_dropout": 0,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.0",
+  "use_cache": true,
+  "vocab_size": 50257,
+  "window_size": 256
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.40.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d05fac5df35fa889ec2a7846e009e95c062c83b08a4bcc4d0fbb177f290105f
+size 500811336

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "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 +1,22 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 2048,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 50.0,
+    "total_flos": 2.15757062406144e+16,
+    "train_loss": 0.8480533966651329,
+    "train_runtime": 3860.2683,
+    "train_samples": 413,
+    "train_samples_per_second": 5.349,
+    "train_steps_per_second": 1.347
+}

trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 50.0,
+  "eval_steps": 500,
+  "global_step": 5200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 4.8076923076923075,
+      "grad_norm": 1.7345516681671143,
+      "learning_rate": 4.519230769230769e-05,
+      "loss": 2.5155,
+      "step": 500
+    },
+    {
+      "epoch": 9.615384615384615,
+      "grad_norm": 2.026956558227539,
+      "learning_rate": 4.038461538461539e-05,
+      "loss": 1.8965,
+      "step": 1000
+    },
+    {
+      "epoch": 14.423076923076923,
+      "grad_norm": 2.5122456550598145,
+      "learning_rate": 3.557692307692308e-05,
+      "loss": 1.3434,
+      "step": 1500
+    },
+    {
+      "epoch": 19.23076923076923,
+      "grad_norm": 3.1581993103027344,
+      "learning_rate": 3.0769230769230774e-05,
+      "loss": 0.9183,
+      "step": 2000
+    },
+    {
+      "epoch": 24.03846153846154,
+      "grad_norm": 3.239306688308716,
+      "learning_rate": 2.5961538461538464e-05,
+      "loss": 0.6282,
+      "step": 2500
+    },
+    {
+      "epoch": 28.846153846153847,
+      "grad_norm": 3.0082170963287354,
+      "learning_rate": 2.1153846153846154e-05,
+      "loss": 0.4492,
+      "step": 3000
+    },
+    {
+      "epoch": 33.65384615384615,
+      "grad_norm": 1.718727946281433,
+      "learning_rate": 1.6346153846153847e-05,
+      "loss": 0.3356,
+      "step": 3500
+    },
+    {
+      "epoch": 38.46153846153846,
+      "grad_norm": 1.2525819540023804,
+      "learning_rate": 1.153846153846154e-05,
+      "loss": 0.2574,
+      "step": 4000
+    },
+    {
+      "epoch": 43.26923076923077,
+      "grad_norm": 0.5725437998771667,
+      "learning_rate": 6.730769230769231e-06,
+      "loss": 0.2151,
+      "step": 4500
+    },
+    {
+      "epoch": 48.07692307692308,
+      "grad_norm": 7.273406028747559,
+      "learning_rate": 1.9230769230769234e-06,
+      "loss": 0.1871,
+      "step": 5000
+    },
+    {
+      "epoch": 50.0,
+      "step": 5200,
+      "total_flos": 2.15757062406144e+16,
+      "train_loss": 0.8480533966651329,
+      "train_runtime": 3860.2683,
+      "train_samples_per_second": 5.349,
+      "train_steps_per_second": 1.347
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 500,
+  "total_flos": 2.15757062406144e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e382783de1f39729e4514bf3c44429b87a80c7807bb2d12749f35bbe703ce815
+size 4539