初始化项目，由ModelHub XC社区提供模型

Model: Cisco1963/llmplasticity-en_zh_linear_0.125_1-seed42
Source: Original Platform

checkpoint-4/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": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "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": "4.57.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

checkpoint-4/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.57.1"
+}

checkpoint-4/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43508a14973a0e8abc1aad06f0cec0ce8dfe55464f2c889633022ac6e6d89524
+size 497774208

checkpoint-4/special_tokens_map.json

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

checkpoint-4/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|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-4/trainer_state.json

@@ -0,0 +1,82 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0007495637304849911,
+  "eval_steps": 99999999,
+  "global_step": 4,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0001873909326212478,
+      "grad_norm": 245.6398468017578,
+      "learning_rate": 5e-05,
+      "loss": 175.7636,
+      "step": 1
+    },
+    {
+      "epoch": 0.0001873909326212478,
+      "eval_accuracy": 0.015452299171252725,
+      "eval_loss": 10.732580184936523,
+      "eval_runtime": 219.7551,
+      "eval_samples_per_second": 35.922,
+      "eval_steps_per_second": 4.491,
+      "step": 1
+    },
+    {
+      "epoch": 0.0003747818652424956,
+      "grad_norm": 113.21331024169922,
+      "learning_rate": 4.9990631440884397e-05,
+      "loss": 161.0339,
+      "step": 2
+    },
+    {
+      "epoch": 0.0003747818652424956,
+      "eval_accuracy": 0.015452299171252725,
+      "eval_loss": 10.66187572479248,
+      "eval_runtime": 137.4523,
+      "eval_samples_per_second": 57.431,
+      "eval_steps_per_second": 7.181,
+      "step": 2
+    },
+    {
+      "epoch": 0.0007495637304849911,
+      "grad_norm": 65.50191497802734,
+      "learning_rate": 4.997189432265318e-05,
+      "loss": 156.102,
+      "step": 4
+    },
+    {
+      "epoch": 0.0007495637304849911,
+      "eval_accuracy": 0.015464063058397669,
+      "eval_loss": 10.59908676147461,
+      "eval_runtime": 188.7788,
+      "eval_samples_per_second": 41.816,
+      "eval_steps_per_second": 5.228,
+      "step": 4
+    }
+  ],
+  "logging_steps": 99999999,
+  "max_steps": 5337,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 99999999,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 267563040768000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-4/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce3911c8105531f25aca99fa1312694d86e429513e2a7b9d69730bbb90fc1e88
+size 6033