add model

README.md

@@ -1,5 +1,5 @@
 ---
-license: mit
+license: apache-2.0
 tags:
 - generated_from_trainer
 datasets:
@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # gpt-neo-125M-Byethon
 
-This model is a fine-tuned version of [Sentdex/GPyT](https://huggingface.co/Sentdex/GPyT) on the None dataset.
+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: 1.6310
+- Loss: 0.6609
 
 ## Model description
 
@@ -50,14 +50,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 31   | 2.6150          |
-| No log        | 2.0   | 62   | 1.8266          |
-| No log        | 3.0   | 93   | 1.6310          |
+| No log        | 1.0   | 237  | 0.8348          |
+| No log        | 2.0   | 474  | 0.6931          |
+| 0.8151        | 3.0   | 711  | 0.6609          |
 
 
 ### Framework versions
 
-- Transformers 4.10.0
+- Transformers 4.10.2
 - Pytorch 1.9.0+cu102
 - Datasets 1.11.0
 - Tokenizers 0.10.3

config.json

@@ -1,32 +1,54 @@
 {
-  "_name_or_path": "Sentdex/GPyT",
+  "_name_or_path": "EleutherAI/gpt-neo-125M",
   "activation_function": "gelu_new",
   "architectures": [
-    "GPT2LMHeadModel"
+    "GPTNeoForCausalLM"
   ],
-  "attn_pdrop": 0.1,
-  "bos_token_id": 0,
-  "embd_pdrop": 0.1,
-  "eos_token_id": 2,
+  "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,
+  "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,
-  "model_type": "gpt2",
-  "n_ctx": 1024,
-  "n_embd": 768,
-  "n_head": 12,
-  "n_inner": null,
-  "n_layer": 12,
-  "n_positions": 1024,
-  "resid_pdrop": 0.1,
-  "scale_attn_weights": true,
+  "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": "4.10.0",
+  "transformers_version": "4.10.2",
   "use_cache": true,
-  "vocab_size": 52000
+  "vocab_size": 50257,
+  "window_size": 256
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db8ada5d04a75b73895b09ad0480668c25cf2b932efb03a58892523022d486cc
-size 515758313
+oid sha256:f4ee1561b1159962251651ccd460786ed1fde26d9fce492ff50948e8ecac3de2
+size 526017245

runs/Sep12_11-06-47_a8ec3b9c2c31/1631444984.2086613/events.out.tfevents.1631444984.a8ec3b9c2c31.89.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9642c69020dc6836366e98b4ee782ec7b60e3a0bcd7b1b0f48b25f3c36b2191f
+size 4181

runs/Sep12_11-06-47_a8ec3b9c2c31/events.out.tfevents.1631444984.a8ec3b9c2c31.89.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8696b5de2202bfcf8d8540339c277a917e7c1d7ce41ebf7caa5930e721943ce
+size 4679

runs/Sep12_11-06-47_a8ec3b9c2c31/events.out.tfevents.1631445273.a8ec3b9c2c31.89.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3d87a34b29fbc310268d819a4ce8982ee36161f626c9393e3366c7c6e87d715
+size 311

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4c12a69a8c8ca3816ecfaed1c985a39a507271f90d0aaca8329049e442a6e7e
+oid sha256:a66e18874ed322a431a41363fa044693475e667104a4a0ed2e9225c8563232be
 size 2671