End of training

README.md

@@ -0,0 +1,54 @@
+---
+license: mit
+base_model: openai-community/gpt2
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: output
+  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
+
+This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/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: 0.0002
+- 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: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "openai-community/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,
+  "pretraining_tp": 1,
+  "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": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.41.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7d00560d8910fbed77ffad4065dee5011c41ba401b1064e749c498ba9e20373
+size 497774208

runs/Jul16_05-48-36_0bfbe0e29374/events.out.tfevents.1721108918.0bfbe0e29374.791.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c397bedc7fdf7a0f9eca09f27cadcae5610bdf129d51f7d31d075a1ef71abc1a
+size 88

runs/Jul16_05-55-49_3b4a963881e2/events.out.tfevents.1721109358.3b4a963881e2.237.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e50e87de723d246c1f216ee868098ef516a6aa79c64b71f4acc6f27c459e045
+size 5147

runs/Jul16_06-27-29_c67da8beb2ab/events.out.tfevents.1721111258.c67da8beb2ab.706.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d067ce105b9a18bf39fc419a78bddb8cc68c339aec578da677a0ee4ecc23e8c4
+size 88

runs/Jul16_06-37-41_fbe318abd33b/events.out.tfevents.1721111870.fbe318abd33b.570.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce3c9e75a60c0c89349ce58253268a21ca5e39ca511a97c50514f2833166cdc9
+size 5170

runs/Jul16_06-44-14_fbe318abd33b/events.out.tfevents.1721112254.fbe318abd33b.570.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:674341e9d30249c3ccc8be8e1013182b7fde61c6a3c61c5b753b3a05ca1aceb8
+size 88

runs/Jul16_06-49-04_29b3c896743f/events.out.tfevents.1721112553.29b3c896743f.293.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3358749e53c3b7093aea425c184fab882d0c660a8627c845aab3ffe46b958464
+size 5169

runs/Jul16_07-40-52_ab5b939594e7/events.out.tfevents.1721115657.ab5b939594e7.247.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6e8cea7cb74780a44f48d76ba926542f13da5d94f8d75d3689a160a64b1f6f7
+size 5168

runs/Jul16_07-59-19_36bd45907894/events.out.tfevents.1721116761.36bd45907894.455.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69ee14294840f6a30e91cf4d58000e9ba6ed438ced8e181ae0583e19d61c2d0f
+size 5678

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "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|>",
+  "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 sha256:207982bfb51029562c8efe20e10985851043eff77b072f6ea52b1b424084323e
+size 5304