gpt-neo-125m-cs-finetuning-40000

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-40000
+  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-40000
+
+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: 3.2299
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 3.3803        | 1.0   | 522  | 3.2999          |
+| 3.1475        | 2.0   | 1044 | 3.2434          |
+| 3.0589        | 3.0   | 1566 | 3.2299          |
+
+
+### 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 +1,4 @@
+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
+2024-03-19T16:24:24,codecarbon,c0140db9-5feb-4f6a-9b66-c8aa2d0f2ec8,3647.509316444397,0.0969745356327015,2.658650800300975e-05,42.5,167.889,11.905189990997316,0.0430554671054085,0.156599348812512,0.0120425381148852,0.2116973540328055,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
+2024-03-19T19:39:36,codecarbon,0c1d70a7-78c6-4374-8bff-a51a67d1442f,3712.2676560878754,0.099814275521301,2.6887682885045263e-05,42.5,168.36,11.905189990997316,0.0438209671242369,0.1618099081124747,0.0122656878630479,0.2178965630997597,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
+2024-03-20T10:24:04,codecarbon,dfa9a4ca-9251-402b-97ec-d61d25edb650,665.0919580459595,0.01834826875588466,2.7587566702493118e-05,42.5,167.481,11.905189990997316,0.007851012628111574,0.030006089831078383,0.0021975358163217255,0.040054638275511666,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 sha256:3ddc07aa6887ae4d3236d924bf65851ea6d5bd4c3e2809248ecfb39e39fa7bf6
+size 500811336

runs/Mar19_15-23-30_kbs/events.out.tfevents.1710829416.kbs.10536.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:840b53719bdb413e4287c796426cab2c8f1c2935fb4405c2bae5473b6a618225
+size 10687

runs/Mar19_18-37-38_kbs/events.out.tfevents.1710841064.kbs.10536.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25551455295ea708c2c629bb05289109a31207a366912cf3051e36da59666fe0
+size 10687

runs/Mar20_10-12-52_kbs/events.out.tfevents.1710897179.kbs.10536.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d139ed80f678f4f684aa2c7f9bcb0f80fa11ea9d92cf546d1aa8b376321f9310
+size 6448

runs/Mar20_10-12-52_kbs/events.out.tfevents.1710897872.kbs.10536.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a22751b6fea4155ac3c397fb39aff18bc1ed836d3db476b7fa09b94e167a4d82
+size 311

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1be77a69c33209aad1f38c2a1af2bc1e246289a369b000bef35770d3f76bd21f
+size 4283