gpt-neo-125m-cs-finetuning-10000-2

README.md

@@ -0,0 +1,59 @@
+---
+license: mit
+base_model: EleutherAI/gpt-neo-125m
+tags:
+- generated_from_trainer
+model-index:
+- name: gpt-neo-125m-cs-finetuning-10000-2
+  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. -->
+
+# gpt-neo-125m-cs-finetuning-10000-2
+
+This model is a fine-tuned version of [EleutherAI/gpt-neo-125m](https://huggingface.co/EleutherAI/gpt-neo-125m) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.3213
+
+## 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: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 130  | 3.3903          |
+| No log        | 2.0   | 260  | 3.3344          |
+| No log        | 3.0   | 390  | 3.3213          |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 1.13.1+cu117
+- Datasets 2.14.6
+- Tokenizers 0.15.0

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": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 50257,
+  "window_size": 256
+}

emissions.csv

@@ -0,0 +1,3 @@
+timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
+2024-03-26T17:25:38,codecarbon,9c97083e-b232-454a-9222-602cf20281a7,168.14643454551697,0.0046201703461238,2.7477064016324496e-05,42.5,166.799,11.905189990997316,0.0019848614114854,0.0075454761418133,0.0005555868708181,0.0100859244241168,South Korea,KOR,gyeonggi-do,,,Windows-10-10.0.19045-SP0,3.9.18,2.2.3,20,12th Gen Intel(R) Core(TM) i7-12700,1,1 x NVIDIA GeForce RTX 3060,127.1377,37.4331,31.74717330932617,machine,N,1.0
+2024-03-26T18:05:30,codecarbon,9f994406-2a0a-4112-bee8-9320dbd4e771,168.16500115394592,0.004624389146684945,2.749911762229031e-05,42.5,167.838,11.905189990997316,0.001985116079449654,0.007554412805462876,0.0005556052653468027,0.010095134150259331,South Korea,KOR,gyeonggi-do,,,Windows-10-10.0.19045-SP0,3.9.18,2.2.3,20,12th Gen Intel(R) Core(TM) i7-12700,1,1 x NVIDIA GeForce RTX 3060,127.1377,37.4331,31.747173309326172,machine,N,1.0

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.36.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56965b2f0eb79041031341f91bbb9f31edbd72ebad977cb4a1576468a1acf09b
+size 500811336

runs/Mar26_17-22-46_kbs/events.out.tfevents.1711441370.kbs.26488.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:729ce84e98e72e976b9caff43a2d670b70a42c5358e975aa442cfc0d19b65f72
+size 5983

runs/Mar26_17-22-46_kbs/events.out.tfevents.1711441542.kbs.26488.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d39921ddd9ef95628307cff8a85da14508286628e7219b4f0d415665eaf23146
+size 311

runs/Mar26_18-02-38_kbs/events.out.tfevents.1711443761.kbs.26488.16

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf0e88d54667cac287e1222a2222e7d33970edcb4e60a96513f18023d8de0053
+size 5983

runs/Mar26_18-02-38_kbs/events.out.tfevents.1711443949.kbs.26488.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1523a487c4b27617e39e1e7b5ba1ab2130a7d7ad87622ab2aa47401b83525cfc
+size 311

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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
+  },
+  "pad_token": "<|endoftext|>",
+  "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": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:002cdf2e314687f84f90b5e918189983d1b05441033accef7e29212e179ef8ad
+size 4283