Uploading fine-tuned model only

config.json

@@ -0,0 +1,55 @@
+{
+  "_name_or_path": "EleutherAI/gpt-neo-125M",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTNeoForCausalLM"
+  ],
+  "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,
+  "classifier_dropout": 0.1,
+  "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,
+  "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": "4.49.0",
+  "use_cache": true,
+  "vocab_size": 50257,
+  "window_size": 256
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.49.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1af91c6cb779071320ec4d817bdd543c5f5d74d5ab43fe3a583a8c115b1a177a
+size 500811336

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc2cb92e87401fc9d027fb8cbc47004dbd9870f82f23afe265e8e7315b08d8d3
+size 1001718458

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f4e55af252e8a06d551e6bdee785deaa53008b886c0b98a60fa83e4e15a5459
+size 13990

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ad2e99d420cf6977163af29798d26b0b68b44610d7546e199cb5ab342393699
+size 1064

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": 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",
+  "extra_special_tokens": {},
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

trainer_state.json

@@ -0,0 +1,65 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 4,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_logits/chosen": -17.38763427734375,
+      "eval_logits/rejected": -17.937782287597656,
+      "eval_logps/chosen": -1147.5987548828125,
+      "eval_logps/rejected": -1209.950439453125,
+      "eval_loss": 0.0057400548830628395,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 8.250604629516602,
+      "eval_rewards/margins": 20.80431365966797,
+      "eval_rewards/rejected": -12.553709030151367,
+      "eval_runtime": 20.8787,
+      "eval_samples_per_second": 0.239,
+      "eval_steps_per_second": 0.096,
+      "step": 2
+    },
+    {
+      "epoch": 2.0,
+      "eval_logits/chosen": -17.409107208251953,
+      "eval_logits/rejected": -17.894569396972656,
+      "eval_logps/chosen": -1115.763427734375,
+      "eval_logps/rejected": -1251.18212890625,
+      "eval_loss": 0.0001020339404931292,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 11.434137344360352,
+      "eval_rewards/margins": 28.111000061035156,
+      "eval_rewards/rejected": -16.676864624023438,
+      "eval_runtime": 22.1862,
+      "eval_samples_per_second": 0.225,
+      "eval_steps_per_second": 0.09,
+      "step": 4
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbcf91c370ef26bc3adc94d1c29447b49c33c92c7251cc90d1c2ccb9c4e5e01d
+size 6136