Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<|endofcompletion|>": 50258,
+  "<|endofinstruction|>": 50259,
+  "<|pad|>": 50260,
+  "<|startofinstruction|>": 50257
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "nicholasKluge/Aira-2-124M",
+  "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": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "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": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": false,
+  "vocab_size": 50261
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.35.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d55cd39dfa0bf2eeea8f8b2c78d426b1b786396a1f5221e7e2ded577535aff3
+size 497786496

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76d571a09ae602ac936a1ffe89782e0e8dd39c79ffb6bc996f548603fe54dc0b
+size 995666874

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e10d3adea581148c2a192fe65983c3f0c0783eeae4728c05d8600b22fa89695
+size 1064

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "bos_token": {
+    "content": "<|startofinstruction|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endofcompletion|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": "<|endofinstruction|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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
+    },
+    "50257": {
+      "content": "<|startofinstruction|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50258": {
+      "content": "<|endofcompletion|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50259": {
+      "content": "<|endofinstruction|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50260": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startofinstruction|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endofcompletion|>",
+  "errors": "replace",
+  "model_max_length": 1024,
+  "pad_token": "<|pad|>",
+  "sep_token": "<|endofinstruction|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

trainer_state.json

@@ -0,0 +1,33 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.04895960832313342,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.976714865090827e-05,
+      "logits/chosen": -10.627127647399902,
+      "logits/rejected": -7.845921516418457,
+      "logps/chosen": -296.1811828613281,
+      "logps/rejected": -265.0650634765625,
+      "loss": 0.031,
+      "rewards/accuracies": 0.9868749976158142,
+      "rewards/chosen": 2.7860028743743896,
+      "rewards/margins": 35.578575134277344,
+      "rewards/rejected": -32.792572021484375,
+      "step": 200
+    }
+  ],
+  "logging_steps": 200,
+  "max_steps": 2400,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "total_flos": 0.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4128496d17e86f3228a418cbab2c1bab6bebe29461cf603a075c52115b3897d9
+size 4600