End of training

README.md

@@ -0,0 +1,56 @@
+---
+license: mit
+base_model: gpt2
+tags:
+- generated_from_trainer
+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 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: 0.0005
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.39.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

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": "4.39.2",
+  "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": "4.39.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fac742868defa99c8a14e5f9b0e4308dad5b53d01605479acdb531fdf1c02f4c
+size 496984704

runs/Apr25_15-33-02_sunfu-DSKT-ubn/events.out.tfevents.1714030384.sunfu-DSKT-ubn.1090.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c58490a7f45b1d08eb1454783de71ce139b560a0a3e047a6531f89013b8f391a
+size 4818

runs/Apr25_15-40-16_sunfu-DSKT-ubn/events.out.tfevents.1714030819.sunfu-DSKT-ubn.1218.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81d9ee6ae6e15fd88574748e6be8af3392561663b3307395f5b91d19d393219a
+size 4818

runs/Apr25_15-42-44_sunfu-DSKT-ubn/events.out.tfevents.1714030966.sunfu-DSKT-ubn.1710.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c911b995483a82d39de118a49bcb6fbca9cf8d83d1c650367d2a14bd40ea4a4
+size 4818

runs/Apr25_15-45-09_sunfu-DSKT-ubn/events.out.tfevents.1714031120.sunfu-DSKT-ubn.2145.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29e806e5fe51dc6f17febb839fd5bfd8d6950b590c23cf0f5710051f13a063bc
+size 4818

runs/Apr25_15-48-31_sunfu-DSKT-ubn/events.out.tfevents.1714031315.sunfu-DSKT-ubn.2585.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4715b53c43c9fae73cc4fbeede11d8209eac19885faf46e49a6bd1a6af5e7305
+size 4818

runs/Apr25_15-51-49_sunfu-DSKT-ubn/events.out.tfevents.1714031512.sunfu-DSKT-ubn.3013.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:024cb83110efb5a071e30061c125ba45eb96eeca0a5632ef3049eb4519a2c4dc
+size 4818

runs/Apr25_15-53-39_sunfu-DSKT-ubn/events.out.tfevents.1714031625.sunfu-DSKT-ubn.3114.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a14d7a2af28e2e96e4122caa68c801bd9a4650317300461997aab46f8ab5d970
+size 4818

runs/Apr25_15-57-23_sunfu-DSKT-ubn/events.out.tfevents.1714031845.sunfu-DSKT-ubn.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8823f6aae76052ed1406cc805f9f09801abdcae7bcfbd1310c25babe7ac7006b
+size 4816

runs/Apr25_15-58-53_sunfu-DSKT-ubn/events.out.tfevents.1714031940.sunfu-DSKT-ubn.977.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb2cee42635fc33cc1d076059aae07c8b6a24b1dea969c8dd34e027d52783594
+size 5170

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:a81c1aca4d8d3060c25b71e6b47a7f0d48f214452bac2a976b783ee00c6d70c8
+size 4920