初始化项目，由ModelHub XC社区提供模型

Model: Cisco1963/llmplasticity-zh_fi_instant_0.5_1-seed42
Source: Original Platform

checkpoint-16/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-16/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-16/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41881e9e86636df3dc854607f9499fd06f6be3572bf8e2251e60e4e34c60e9f5
+size 497774208

checkpoint-16/special_tokens_map.json

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

checkpoint-16/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-16/trainer_state.json

@@ -0,0 +1,114 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0028504620866273245,
+  "eval_steps": 99999999,
+  "global_step": 16,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00017815388041420778,
+      "grad_norm": 232.1993865966797,
+      "learning_rate": 5e-05,
+      "loss": 175.5579,
+      "step": 1
+    },
+    {
+      "epoch": 0.00017815388041420778,
+      "eval_accuracy": 0.018891725076294615,
+      "eval_loss": 10.400674819946289,
+      "eval_runtime": 157.3868,
+      "eval_samples_per_second": 63.55,
+      "eval_steps_per_second": 7.949,
+      "step": 1
+    },
+    {
+      "epoch": 0.00035630776082841556,
+      "grad_norm": 114.17350769042969,
+      "learning_rate": 4.99910936943356e-05,
+      "loss": 160.0191,
+      "step": 2
+    },
+    {
+      "epoch": 0.00035630776082841556,
+      "eval_accuracy": 0.01293475420262966,
+      "eval_loss": 10.170297622680664,
+      "eval_runtime": 161.9764,
+      "eval_samples_per_second": 61.75,
+      "eval_steps_per_second": 7.723,
+      "step": 2
+    },
+    {
+      "epoch": 0.0007126155216568311,
+      "grad_norm": 51.90617370605469,
+      "learning_rate": 4.9973281083006775e-05,
+      "loss": 152.5677,
+      "step": 4
+    },
+    {
+      "epoch": 0.0007126155216568311,
+      "eval_accuracy": 0.022687935531173334,
+      "eval_loss": 9.972246170043945,
+      "eval_runtime": 181.1968,
+      "eval_samples_per_second": 55.2,
+      "eval_steps_per_second": 6.904,
+      "step": 4
+    },
+    {
+      "epoch": 0.0014252310433136622,
+      "grad_norm": 79.16446685791016,
+      "learning_rate": 4.993765586034913e-05,
+      "loss": 145.6416,
+      "step": 8
+    },
+    {
+      "epoch": 0.0014252310433136622,
+      "eval_accuracy": 0.08070331192803473,
+      "eval_loss": 10.352470397949219,
+      "eval_runtime": 167.7318,
+      "eval_samples_per_second": 59.631,
+      "eval_steps_per_second": 7.458,
+      "step": 8
+    },
+    {
+      "epoch": 0.0028504620866273245,
+      "grad_norm": 62.1901969909668,
+      "learning_rate": 4.9866405415033846e-05,
+      "loss": 139.5395,
+      "step": 16
+    },
+    {
+      "epoch": 0.0028504620866273245,
+      "eval_accuracy": 0.09230773591127327,
+      "eval_loss": 9.133565902709961,
+      "eval_runtime": 167.1804,
+      "eval_samples_per_second": 59.828,
+      "eval_steps_per_second": 7.483,
+      "step": 16
+    }
+  ],
+  "logging_steps": 99999999,
+  "max_steps": 5614,
+  "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": 1070252163072000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-16/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba3eb250aef75410ef75512c788296ebc638d28a3c2229946af64542de04b882
+size 5969