gpt-neo-125m-cs-finetuning-5000

README.md

@@ -1,59 +1,59 @@
----
-license: mit
-base_model: EleutherAI/gpt-neo-125m
-tags:
-- generated_from_trainer
-model-index:
-- name: gpt-neo-125m-cs-finetuning-5000
-  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-5000
-
-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: 3.3585
-
-## 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   | 65   | 3.4337          |
-| No log        | 2.0   | 130  | 3.3733          |
-| No log        | 3.0   | 195  | 3.3585          |
-
-
-### Framework versions
-
-- Transformers 4.36.2
-- Pytorch 1.13.1+cu117
-- Datasets 2.14.6
-- Tokenizers 0.15.0
+---
+license: mit
+base_model: EleutherAI/gpt-neo-125m
+tags:
+- generated_from_trainer
+model-index:
+- name: gpt-neo-125m-cs-finetuning-5000
+  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-5000
+
+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: 3.4019
+
+## 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   | 64   | 3.4786          |
+| No log        | 2.0   | 128  | 3.4167          |
+| No log        | 3.0   | 192  | 3.4019          |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 1.13.1+cu117
+- Datasets 2.14.6
+- Tokenizers 0.15.0

config.json

@@ -1,55 +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
-}
+{
+  "_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

@@ -1,2 +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
-2024-03-20T15:03:31,codecarbon,c0176a42-645f-4601-b986-12cb392fbd8b,80.7582950592041,0.002230554984087869,2.7620134655550165e-05,42.5,168.03,11.905189990997316,0.0009533025234937669,0.003649187882204122,0.00026685581055615505,0.004869346216254044,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
+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
+2024-05-27T10:05:04,codecarbon,ed651fc3-2a98-4e67-a9e0-f744ae19a45d,84.14403414726257,0.00230752610858073,2.7423526004734586e-05,42.5,165.118,11.905189990997316,0.000993247193263637,0.0037661414692739645,0.00027798706049114166,0.005037375723028744,South Korea,KOR,seoul,,,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 3060,126.9369,37.5551,31.747173309326172,machine,N,1.0

generation_config.json

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

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a977be68fd035fc625240d68804d673d72a84f0f8feac793e130e08666cc01f
+oid sha256:c86ec265247c7b2fb974b84898105bae31ec9225f9430908b4c0e022ea452005
 size 500811336

runs/May27_10-03-37_kbs/events.out.tfevents.1716771820.kbs.34172.12

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e031b63fcd6a985cfbd25cbd4a987f6b82b6c8cb6752a3f782e761b44a62b0c
+size 5969

runs/May27_10-03-37_kbs/events.out.tfevents.1716771906.kbs.34172.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9e174d5e97b07f28873155890cfd546362878a01c0446310ecfffd648a8c9c9
+size 311

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a3fdd8ff27ffd955cdbbe52f597988d6502c27d1a881d4bba1746a908ba512b
+oid sha256:4b4207a7c74ba885255a02310683bf297a00927d1231369c1f9377045a0d2814
 size 4283