gpt-neo-125m-lama-finetuning

README.md

@@ -0,0 +1,59 @@
+---
+license: mit
+base_model: EleutherAI/gpt-neo-125m
+tags:
+- generated_from_trainer
+model-index:
+- name: gpt-neo-125m-lama-finetuning
+  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-lama-finetuning
+
+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: 3.3933
+
+## 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   | 386  | 3.4344          |
+| 3.4698        | 2.0   | 772  | 3.4000          |
+| 3.2617        | 3.0   | 1158 | 3.3933          |
+
+
+### 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 +1,2 @@
+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
+2024-01-24T10:42:18,codecarbon,b8801aef-3a51-412e-b10f-4f6965496fb1,488.82684874534607,0.013496571812545925,2.7610127895362295e-05,42.5,168.85500000000002,11.905189990997316,0.0057701170444488525,0.022078045979706643,0.0016151236272138395,0.029463286651369353,South Korea,KOR,,,,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 3060,126.9741,37.5112,31.747173309326172,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:fd4a3f68c3d58d2240f735ec911e38b71604d2146b5b8364e57d16b1157e8626
+size 500811336

runs/Jan24_10-34-05_kbs/events.out.tfevents.1706060049.kbs.15492.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c957755bfbe52b143560fe62f4078d2301ce866ab5f8b5304f002940807fb1cd
+size 6279

runs/Jan24_10-34-05_kbs/events.out.tfevents.1706060601.kbs.15492.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79f36d112740cb5cfa9d536fd2ca0cdb2fdc41e737eb46e04dc5a64f3dff4e14
+size 311

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90fac432a73052886dd0c38f63a2acd2996e2484e0bd82955f465b3ba747044d
+size 4283