gpt-neo-125m-cs-finetuning-2000

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 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: 3.4125
+- Loss: 3.4720
 
 ## Model description
 
@@ -46,9 +46,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 26   | 3.4946          |
-| No log        | 2.0   | 52   | 3.4299          |
-| No log        | 3.0   | 78   | 3.4125          |
+| No log        | 1.0   | 38   | 3.5591          |
+| No log        | 2.0   | 76   | 3.4891          |
+| No log        | 3.0   | 114  | 3.4720          |
 
 
 ### Framework versions

emissions.csv

@@ -1,2 +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
-2024-05-26T20:14:54,codecarbon,1de0dc73-1494-46f8-bb61-a3b55382f387,32.59400200843811,0.0008983140370200965,2.75607161338315e-05,42.5,164.88400000000004,11.905189990997316,0.00038473128643300793,0.0014686568728680082,0.00010764937995535244,0.0019610375392563684,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
+2024-05-26T20:14:54,codecarbon,1de0dc73-1494-46f8-bb61-a3b55382f387,32.59400200843811,0.00089831403702,2.75607161338315e-05,42.5,164.88400000000004,11.905189990997316,0.000384731286433,0.001468656872868,0.0001076493799553,0.0019610375392563,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 3060,126.9369,37.5551,31.74717330932617,machine,N,1.0
+2024-05-26T20:17:31,codecarbon,aa3c234f-dcc0-44b5-9c49-c99671e91809,49.65600037574768,0.0013653883028426365,2.7496944830649332e-05,42.5,166.966,11.905189990997316,0.0005861694973376062,0.0022304668421365154,0.0001640336792401154,0.002980670018714237,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

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02e565194dee717dd8cce22dffbe6e858dd7170891d76eff23478e903d09a2ec
+oid sha256:1ad913ba031ee9994fa1a6dcf653894b7bfb0cc4812a83af8d90713580d84d64
 size 500811336

runs/May26_20-16-38_kbs/events.out.tfevents.1716722202.kbs.34172.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf78c49ae67c99686bc955d5ab29654b6e425f610f6c02b559fbfb61dfaaf043
+size 5953

runs/May26_20-16-38_kbs/events.out.tfevents.1716722253.kbs.34172.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d86a5bb584de08fa9f4b69c926200503cafc7d0018a52ce6a5d5d887b0ca6fa
+size 306

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fbf8f3fb420a90d240e6dfe21cea55f1b25f097a935314955129e3f9cfd805e
+oid sha256:4830095572a87177b016529bcd498d5c162a143e4d2113cc88f147124e006367
 size 4283