files

README.md

@@ -1,52 +0,0 @@
----
-tags:
-- generated_from_trainer
-datasets:
-- allyc/My-Dataset
-model-index:
-- name: uspto-gpt2-medium-1
-  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. -->
-
-# uspto-gpt2-medium-1
-
-This model is a fine-tuned version of [](https://huggingface.co/) on the allyc/My-Dataset uspto dataset.
-
-## 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: 5e-05
-- train_batch_size: 32
-- eval_batch_size: 32
-- seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- training_steps: 68000
-
-### Training results
-
-
-
-### Framework versions
-
-- Transformers 4.35.0
-- Pytorch 2.0.1+cu117
-- Datasets 2.14.6
-- Tokenizers 0.14.1

all_results.json

@@ -1,8 +0,0 @@
-{
-    "epoch": 1.0,
-    "train_loss": 2.546952809053309,
-    "train_runtime": 116511.6778,
-    "train_samples": 68000,
-    "train_samples_per_second": 18.676,
-    "train_steps_per_second": 0.584
-}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94751abdb5fe49a9fce5e2d36e4de4eb9a19f85fcc531e2a734a624de7ee1f7f
+size 2838828805

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfdaa80090ee4ec33412e2f2792c86b0232add3b7828c892df95f17a76ea9f72
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d12e4b164e85df734dd297f0ea64d0ab36256e9460357384a2eb5681ab8f560
+size 627

train_results.json

@@ -1,8 +0,0 @@
-{
-    "epoch": 1.0,
-    "train_loss": 2.546952809053309,
-    "train_runtime": 116511.6778,
-    "train_samples": 68000,
-    "train_samples_per_second": 18.676,
-    "train_steps_per_second": 0.584
-}

trainer_state.json

@@ -823,15 +823,6 @@
       "learning_rate": 0.0,
       "loss": 2.482,
       "step": 68000
-    },
-    {
-      "epoch": 1.0,
-      "step": 68000,
-      "total_flos": 4.041705422585856e+18,
-      "train_loss": 2.546952809053309,
-      "train_runtime": 116511.6778,
-      "train_samples_per_second": 18.676,
-      "train_steps_per_second": 0.584
     }
   ],
   "logging_steps": 500,