初始化项目，由ModelHub XC社区提供模型

Model: Raiff1982/Codette-Ultimate
Source: Original Platform

metrics/all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 0.005797101449275362,
+    "eval_loss": 10.829381942749023,
+    "eval_runtime": 0.1784,
+    "eval_samples": 18,
+    "eval_samples_per_second": 100.873,
+    "eval_steps_per_second": 100.873,
+    "perplexity": 50482.49607226202,
+    "total_flos": 233472.0,
+    "train_loss": 10.746472358703613,
+    "train_runtime": 1.3081,
+    "train_samples": 345,
+    "train_samples_per_second": 1.529,
+    "train_steps_per_second": 1.529
+}

metrics/config.json

@@ -0,0 +1,39 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "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": 2,
+  "n_head": 2,
+  "n_inner": null,
+  "n_layer": 2,
+  "n_positions": 1024,
+  "pad_token_id": 50256,
+  "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
+    }
+  },
+  "transformers_version": "4.56.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

metrics/eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.005797101449275362,
+    "eval_loss": 10.829381942749023,
+    "eval_runtime": 0.1784,
+    "eval_samples": 18,
+    "eval_samples_per_second": 100.873,
+    "eval_steps_per_second": 100.873,
+    "perplexity": 50482.49607226202
+}

metrics/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": [
+    50256
+  ],
+  "pad_token_id": 50256,
+  "transformers_version": "4.56.2"
+}

metrics/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
+  }
+}

metrics/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": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

metrics/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.005797101449275362,
+    "total_flos": 233472.0,
+    "train_loss": 10.746472358703613,
+    "train_runtime": 1.3081,
+    "train_samples": 345,
+    "train_samples_per_second": 1.529,
+    "train_steps_per_second": 1.529
+}

metrics/trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.005797101449275362,
+  "eval_steps": 1,
+  "global_step": 2,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002898550724637681,
+      "grad_norm": 0.3978370130062103,
+      "learning_rate": 0.0,
+      "loss": 10.7491,
+      "step": 1
+    },
+    {
+      "epoch": 0.005797101449275362,
+      "grad_norm": 0.526188313961029,
+      "learning_rate": 2e-05,
+      "loss": 10.7438,
+      "step": 2
+    },
+    {
+      "epoch": 0.005797101449275362,
+      "step": 2,
+      "total_flos": 233472.0,
+      "train_loss": 10.746472358703613,
+      "train_runtime": 1.3081,
+      "train_samples_per_second": 1.529,
+      "train_steps_per_second": 1.529
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 2,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 233472.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}