初始化项目，由ModelHub XC社区提供模型

Model: Cisco1963/llmplasticity-zh_en_instant_0.25_1-seed42
Source: Original Platform

checkpoint-256/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-256/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-256/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85e75d4d36b842c670b5904598254d2d1843850d7e523dc23fbb3cb062315d75
+size 497774208

checkpoint-256/special_tokens_map.json

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

checkpoint-256/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-256/trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0893913271207525,
+  "eval_steps": 99999999,
+  "global_step": 256,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00034918487156543944,
+      "grad_norm": 232.1994171142578,
+      "learning_rate": 5e-05,
+      "loss": 175.5579,
+      "step": 1
+    },
+    {
+      "epoch": 0.00034918487156543944,
+      "eval_accuracy": 0.023954123581349192,
+      "eval_loss": 10.253963470458984,
+      "eval_runtime": 128.4941,
+      "eval_samples_per_second": 61.419,
+      "eval_steps_per_second": 7.681,
+      "step": 1
+    },
+    {
+      "epoch": 0.0006983697431308789,
+      "grad_norm": 114.17286682128906,
+      "learning_rate": 4.9982541899441346e-05,
+      "loss": 160.0191,
+      "step": 2
+    },
+    {
+      "epoch": 0.0006983697431308789,
+      "eval_accuracy": 0.016392362385855185,
+      "eval_loss": 9.9473237991333,
+      "eval_runtime": 128.9886,
+      "eval_samples_per_second": 61.184,
+      "eval_steps_per_second": 7.652,
+      "step": 2
+    },
+    {
+      "epoch": 0.0013967394862617578,
+      "grad_norm": 51.907196044921875,
+      "learning_rate": 4.9947625698324026e-05,
+      "loss": 152.5682,
+      "step": 4
+    },
+    {
+      "epoch": 0.0013967394862617578,
+      "eval_accuracy": 0.028750051402635483,
+      "eval_loss": 9.692176818847656,
+      "eval_runtime": 127.9133,
+      "eval_samples_per_second": 61.698,
+      "eval_steps_per_second": 7.716,
+      "step": 4
+    },
+    {
+      "epoch": 0.0027934789725235156,
+      "grad_norm": 79.11775970458984,
+      "learning_rate": 4.9877793296089386e-05,
+      "loss": 145.6449,
+      "step": 8
+    },
+    {
+      "epoch": 0.0027934789725235156,
+      "eval_accuracy": 0.1025968115998036,
+      "eval_loss": 10.163084030151367,
+      "eval_runtime": 156.5451,
+      "eval_samples_per_second": 50.414,
+      "eval_steps_per_second": 6.305,
+      "step": 8
+    },
+    {
+      "epoch": 0.005586957945047031,
+      "grad_norm": 62.22785186767578,
+      "learning_rate": 4.973812849162011e-05,
+      "loss": 139.486,
+      "step": 16
+    },
+    {
+      "epoch": 0.005586957945047031,
+      "eval_accuracy": 0.11699363697303629,
+      "eval_loss": 8.626287460327148,
+      "eval_runtime": 126.9555,
+      "eval_samples_per_second": 62.164,
+      "eval_steps_per_second": 7.774,
+      "step": 16
+    },
+    {
+      "epoch": 0.011173915890094062,
+      "grad_norm": 48.77768325805664,
+      "learning_rate": 4.9458798882681565e-05,
+      "loss": 113.3273,
+      "step": 32
+    },
+    {
+      "epoch": 0.011173915890094062,
+      "eval_accuracy": 0.15826276928168595,
+      "eval_loss": 7.515727519989014,
+      "eval_runtime": 126.3816,
+      "eval_samples_per_second": 62.446,
+      "eval_steps_per_second": 7.81,
+      "step": 32
+    },
+    {
+      "epoch": 0.022347831780188124,
+      "grad_norm": 30.68110466003418,
+      "learning_rate": 4.890013966480447e-05,
+      "loss": 92.5668,
+      "step": 64
+    },
+    {
+      "epoch": 0.022347831780188124,
+      "eval_accuracy": 0.16659792338307128,
+      "eval_loss": 6.12502384185791,
+      "eval_runtime": 139.2964,
+      "eval_samples_per_second": 56.656,
+      "eval_steps_per_second": 7.086,
+      "step": 64
+    },
+    {
+      "epoch": 0.04469566356037625,
+      "grad_norm": 59.65339279174805,
+      "learning_rate": 4.778282122905028e-05,
+      "loss": 63.429,
+      "step": 128
+    },
+    {
+      "epoch": 0.04469566356037625,
+      "eval_accuracy": 0.18046078065616022,
+      "eval_loss": 5.348491191864014,
+      "eval_runtime": 131.9171,
+      "eval_samples_per_second": 59.825,
+      "eval_steps_per_second": 7.482,
+      "step": 128
+    },
+    {
+      "epoch": 0.0893913271207525,
+      "grad_norm": 11.741301536560059,
+      "learning_rate": 4.55481843575419e-05,
+      "loss": 57.462,
+      "step": 256
+    },
+    {
+      "epoch": 0.0893913271207525,
+      "eval_accuracy": 0.17872138978853822,
+      "eval_loss": 5.072287082672119,
+      "eval_runtime": 129.0224,
+      "eval_samples_per_second": 61.168,
+      "eval_steps_per_second": 7.65,
+      "step": 256
+    }
+  ],
+  "logging_steps": 99999999,
+  "max_steps": 2864,
+  "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": 1.7124034609152e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-256/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74130c7252837fa33b9701cd94f78c04cb379dee23ad570b37b33bab98964e36
+size 6033