Model save

README.md

@@ -1,5 +1,6 @@
 ---
 license: mit
+base_model: EleutherAI/gpt-neo-125m
 tags:
 - generated_from_trainer
 model-index:
@@ -32,15 +33,15 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0005
-- train_batch_size: 2
-- eval_batch_size: 2
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 8
-- total_train_batch_size: 16
+- total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 1000
-- num_epochs: 1
+- num_epochs: 10
 
 ### Training results
 
@@ -48,7 +49,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.27.2
-- Pytorch 2.0.1+cu117
-- Datasets 2.11.0
-- Tokenizers 0.13.3
+- Transformers 4.34.1
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

config.json

@@ -29,6 +29,7 @@
     ]
   ],
   "bos_token_id": 50256,
+  "classifier_dropout": 0.1,
   "embed_dropout": 0,
   "eos_token_id": 50256,
   "gradient_checkpointing": false,
@@ -47,7 +48,7 @@
   "summary_type": "cls_index",
   "summary_use_proj": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.27.2",
+  "transformers_version": "4.34.1",
   "use_cache": true,
   "vocab_size": 50257,
   "window_size": 256

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 50256,
   "eos_token_id": 50256,
-  "transformers_version": "4.27.2"
+  "transformers_version": "4.34.1"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83bd0533a64a880ad6ce6412997ee7dfdedb53b03379dc0466f6f75432d1fbef
-size 551184237
+oid sha256:19cc63c4021e53c2bb43f82d8e64224c653bed34c1c9b21e061b43586963c8bc
+size 500847626

tokenizer_config.json

@@ -1,33 +1,22 @@
 {
   "add_bos_token": false,
   "add_prefix_space": false,
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
   },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
   "errors": "replace",
   "model_max_length": 2048,
-  "pad_token": null,
-  "special_tokens_map_file": null,
+  "pad_token": "<|endoftext|>",
   "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8b5062ceaec3391e29ad92c16c1942fe5c0b0db03c5e48c5d2cdce5b37cfa92
-size 3643
+oid sha256:6015b01fad7f25081386f02ea5af100f0ce5a0605c672df478afb91cbafb5a69
+size 4600