End of training

README.md

@@ -0,0 +1,54 @@
+---
+license: mit
+base_model: gpt2
+tags:
+- generated_from_trainer
+datasets:
+- code_search_net
+model-index:
+- name: codeparrot-ds
+  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. -->
+
+# codeparrot-ds
+
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the code_search_net 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: 0.0005
+- train_batch_size: 64
+- eval_batch_size: 64
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 512
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 50
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.1.2+cu118
+- Datasets 2.16.1
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 128,
+  "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": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 50000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.36.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c34344b742ae3aa80cbfa73e0aa5905a25824aeec13580607a6bc424cb0e212
+size 496984704

runs/Feb03_13-15-23_oisit-selab3/events.out.tfevents.1706987724.oisit-selab3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb45f4606ff53902f7b148fb4655ff888c538028082196e7ede16e41d8d8fbb6
+size 4538

runs/Feb03_17-15-00_oisit-selab3/events.out.tfevents.1707002101.oisit-selab3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d103dc9b7d684a4a09842c70f69805151e9169a5f9dc0482edd40779fc7c58d
+size 4538

runs/Feb04_13-29-03_oisit-selab3/events.out.tfevents.1707074944.oisit-selab3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:253f1c3983a5bd8ef1d40dab4650e7db9ee874ae2627001a5ef2fee36d67f9ae
+size 3598

runs/Feb04_14-43-44_oisit-selab3/events.out.tfevents.1707079425.oisit-selab3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed2229d4c0518a36678b24474356d09c71d38cabc03663745a39198e5b0d9324
+size 4538

runs/Feb04_17-38-10_oisit-selab3/events.out.tfevents.1707089893.oisit-selab3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe1e98bdafcb9f5b8daac7729866f7372cba9e7834ae2dad8f68df360e7526e1
+size 4538

runs/Feb04_18-28-44_oisit-selab3/events.out.tfevents.1707092926.oisit-selab3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b9e6bace05500053b042006724e67c2769bf58154d36fb4aa1267f2dae9d867
+size 4538

runs/Feb04_22-33-09_oisit-selab3/events.out.tfevents.1707107599.oisit-selab3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aacd77a006d3d42424f70d01819b8875d927671e6b28a2cccc5d0d922f357045
+size 4533

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "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": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e6006e05bcb967f4d9e345692684e2bffaa0f7a7b12523c6169640c54e087e3
+size 4728