Training in progress, step 100

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "openai-community/gpt2-medium",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 1024,
+  "n_special": 0,
+  "predict_special_tokens": true,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": false,
+  "vocab_size": 50257
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:465d5c5210b93f51efdbc776dccbfeafd9cd0313e6f9af660f420e5f1c335784
+size 709676664

runs/Apr09_23-40-16_compsci-cluster-fitz-05/events.out.tfevents.1712720627.compsci-cluster-fitz-05.885536.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22f6733b3ce88d4d4f5dbbf7d74ae4c58cee75bc3ae74a154d2a9f1a7f7b5351
+size 4996

runs/Apr10_00-00-43_compsci-cluster-fitz-05/events.out.tfevents.1712721655.compsci-cluster-fitz-05.886096.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44d9477c7dabe79abec3183a3e68f8ec93d8e312f45b08291c772dc7339c1a37
+size 4996

runs/Apr10_00-10-14_compsci-cluster-fitz-05/events.out.tfevents.1712722219.compsci-cluster-fitz-05.886278.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e03cae556569763d27b1745d98c1e444cdb002e29ee75e42b73e69049056260
+size 4996

runs/Apr10_00-17-18_compsci-cluster-fitz-05/events.out.tfevents.1712722643.compsci-cluster-fitz-05.886429.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9996e3f5cfb30521548b108259932736ac5a9e148367ef332f009e0e6bacefd
+size 4996

runs/Apr10_03-34-27_compsci-cluster-fitz-05/events.out.tfevents.1712734475.compsci-cluster-fitz-05.897454.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6c9282274646c8efdab4390a599464878782af3f4b5eb4090ae6e9bd84abb52
+size 4996

runs/Apr10_03-39-45_compsci-cluster-fitz-05/events.out.tfevents.1712734827.compsci-cluster-fitz-05.897615.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c565d5559f5aa983ebd624bdc0ab0c78a314590bcedf3edc8455f6a208cff8b
+size 4996

runs/Apr10_03-49-47_compsci-cluster-fitz-05/events.out.tfevents.1712735426.compsci-cluster-fitz-05.897826.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63ab39d8330766b7a3de60f06b3bc73b913ece543588bbef75857e1ed590e6a7
+size 4996

runs/Apr10_04-14-22_compsci-cluster-fitz-05/events.out.tfevents.1712736906.compsci-cluster-fitz-05.898215.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11fed234c4abf98f9beac7ee57b60cafb48bd2bf832689ffa71feb0f69d4ff1b
+size 4996

runs/Apr10_04-19-42_compsci-cluster-fitz-05/events.out.tfevents.1712737194.compsci-cluster-fitz-05.898351.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:607edaeccbfa500361b8e6cd83798c60745b48b920bd98c85a39d4373d466bbd
+size 9330

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% for dialogue in chosen %}\n{% if dialogue.speaker == 'Human' %}Human: {{ dialogue.text + eos_token }}{% else %}Assistant: {{ dialogue.text + eos_token }}{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:156f62f2291d356be553e4ebdc6c852e562a9a7f3c361bd9b5a099ed69008fc6
+size 4984