load_model

We load data, weights and important parameters for the model

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "BueormLLC/CleanGPT",
+  "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": "4.42.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.42.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f06541cef2542bfe1c5e51c5013188fa980eaf805a2ba2048e82da798ace6522
+size 497774208

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d285b214ff9eb000bdc26aac9b035606764b96d34f9f5236535bb42e0ab3722
+size 995642298

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:549a8235ab4fe89a52f68cd8f2066d72d9d3c145ac02436bdb0adf36fca0dec5
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0daba17a72d1aa993bd866cf1c63e35f955a56ce5c903da992079fc3684233b8
+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 +1,22 @@
+{
+  "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",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

trainer_state.json

@@ -0,0 +1,173 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 10392,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3849114703618168,
+      "grad_norm": 1.290488839149475,
+      "learning_rate": 5e-05,
+      "loss": 7.6662,
+      "step": 500
+    },
+    {
+      "epoch": 0.7698229407236336,
+      "grad_norm": 1.1826180219650269,
+      "learning_rate": 4.747270521633644e-05,
+      "loss": 6.3593,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1547344110854503,
+      "grad_norm": 1.238223910331726,
+      "learning_rate": 4.494541043267287e-05,
+      "loss": 6.132,
+      "step": 1500
+    },
+    {
+      "epoch": 1.539645881447267,
+      "grad_norm": 1.1373482942581177,
+      "learning_rate": 4.24181156490093e-05,
+      "loss": 5.9398,
+      "step": 2000
+    },
+    {
+      "epoch": 1.924557351809084,
+      "grad_norm": 1.2479649782180786,
+      "learning_rate": 3.9890820865345734e-05,
+      "loss": 5.8258,
+      "step": 2500
+    },
+    {
+      "epoch": 2.3094688221709005,
+      "grad_norm": 1.5960040092468262,
+      "learning_rate": 3.736352608168217e-05,
+      "loss": 5.6365,
+      "step": 3000
+    },
+    {
+      "epoch": 2.6943802925327174,
+      "grad_norm": 1.454331398010254,
+      "learning_rate": 3.4836231298018604e-05,
+      "loss": 5.578,
+      "step": 3500
+    },
+    {
+      "epoch": 3.079291762894534,
+      "grad_norm": 1.5335205793380737,
+      "learning_rate": 3.2308936514355035e-05,
+      "loss": 5.5167,
+      "step": 4000
+    },
+    {
+      "epoch": 3.464203233256351,
+      "grad_norm": 1.5028727054595947,
+      "learning_rate": 2.9781641730691466e-05,
+      "loss": 5.3757,
+      "step": 4500
+    },
+    {
+      "epoch": 3.849114703618168,
+      "grad_norm": 1.7399624586105347,
+      "learning_rate": 2.7254346947027904e-05,
+      "loss": 5.3516,
+      "step": 5000
+    },
+    {
+      "epoch": 4.234026173979984,
+      "grad_norm": 1.6884772777557373,
+      "learning_rate": 2.4727052163364335e-05,
+      "loss": 5.286,
+      "step": 5500
+    },
+    {
+      "epoch": 4.618937644341801,
+      "grad_norm": 1.8180075883865356,
+      "learning_rate": 2.219975737970077e-05,
+      "loss": 5.1973,
+      "step": 6000
+    },
+    {
+      "epoch": 5.003849114703618,
+      "grad_norm": 1.6495822668075562,
+      "learning_rate": 1.96724625960372e-05,
+      "loss": 5.1844,
+      "step": 6500
+    },
+    {
+      "epoch": 5.388760585065435,
+      "grad_norm": 1.929316759109497,
+      "learning_rate": 1.7145167812373636e-05,
+      "loss": 5.0743,
+      "step": 7000
+    },
+    {
+      "epoch": 5.773672055427252,
+      "grad_norm": 1.9738694429397583,
+      "learning_rate": 1.4617873028710069e-05,
+      "loss": 5.0788,
+      "step": 7500
+    },
+    {
+      "epoch": 6.158583525789068,
+      "grad_norm": 1.9357603788375854,
+      "learning_rate": 1.2090578245046502e-05,
+      "loss": 5.0497,
+      "step": 8000
+    },
+    {
+      "epoch": 6.543494996150885,
+      "grad_norm": 2.0328495502471924,
+      "learning_rate": 9.563283461382936e-06,
+      "loss": 4.9795,
+      "step": 8500
+    },
+    {
+      "epoch": 6.928406466512702,
+      "grad_norm": 2.1695396900177,
+      "learning_rate": 7.03598867771937e-06,
+      "loss": 4.9729,
+      "step": 9000
+    },
+    {
+      "epoch": 7.313317936874519,
+      "grad_norm": 2.4989547729492188,
+      "learning_rate": 4.508693894055803e-06,
+      "loss": 4.9227,
+      "step": 9500
+    },
+    {
+      "epoch": 7.698229407236336,
+      "grad_norm": 2.1488616466522217,
+      "learning_rate": 1.981399110392236e-06,
+      "loss": 4.9139,
+      "step": 10000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10392,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 10000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.1712322691072e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfe3c1ee4a1e601a606aca8b79d3e2e73720343bd516dac207d73e6f246551ec
+size 5112