初始化项目，由ModelHub XC社区提供模型

Model: Cisco1963/llmplasticity-en_fi_linear_0.125_1-seed42
Source: Original Platform

checkpoint-512/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-512/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-512/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:428803c934f64678db4899fcce4b5d82d82a00e8699429c498305d6ac0f3d03d
+size 497774208

checkpoint-512/special_tokens_map.json

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

checkpoint-512/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-512/trainer_state.json

@@ -0,0 +1,194 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.12447577949310157,
+  "eval_steps": 99999999,
+  "global_step": 512,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.000243116756822464,
+      "grad_norm": 245.63973999023438,
+      "learning_rate": 5e-05,
+      "loss": 175.7636,
+      "step": 1
+    },
+    {
+      "epoch": 0.000243116756822464,
+      "eval_accuracy": 0.03065178878801227,
+      "eval_loss": 10.476305961608887,
+      "eval_runtime": 122.5372,
+      "eval_samples_per_second": 51.397,
+      "eval_steps_per_second": 6.431,
+      "step": 1
+    },
+    {
+      "epoch": 0.000486233513644928,
+      "grad_norm": 113.21363067626953,
+      "learning_rate": 4.998784637822071e-05,
+      "loss": 161.0339,
+      "step": 2
+    },
+    {
+      "epoch": 0.000486233513644928,
+      "eval_accuracy": 0.03065178878801227,
+      "eval_loss": 10.297815322875977,
+      "eval_runtime": 120.5427,
+      "eval_samples_per_second": 52.247,
+      "eval_steps_per_second": 6.537,
+      "step": 2
+    },
+    {
+      "epoch": 0.000972467027289856,
+      "grad_norm": 65.4986801147461,
+      "learning_rate": 4.996353913466213e-05,
+      "loss": 156.102,
+      "step": 4
+    },
+    {
+      "epoch": 0.000972467027289856,
+      "eval_accuracy": 0.03066870675635363,
+      "eval_loss": 10.12234878540039,
+      "eval_runtime": 134.3118,
+      "eval_samples_per_second": 46.891,
+      "eval_steps_per_second": 5.867,
+      "step": 4
+    },
+    {
+      "epoch": 0.001944934054579712,
+      "grad_norm": 38.307884216308594,
+      "learning_rate": 4.991492464754497e-05,
+      "loss": 152.2924,
+      "step": 8
+    },
+    {
+      "epoch": 0.001944934054579712,
+      "eval_accuracy": 0.030665912963416524,
+      "eval_loss": 10.031266212463379,
+      "eval_runtime": 123.2321,
+      "eval_samples_per_second": 51.107,
+      "eval_steps_per_second": 6.394,
+      "step": 8
+    },
+    {
+      "epoch": 0.003889868109159424,
+      "grad_norm": 33.05560302734375,
+      "learning_rate": 4.981769567331065e-05,
+      "loss": 148.7256,
+      "step": 16
+    },
+    {
+      "epoch": 0.003889868109159424,
+      "eval_accuracy": 0.03471380850784451,
+      "eval_loss": 9.771815299987793,
+      "eval_runtime": 121.9704,
+      "eval_samples_per_second": 51.635,
+      "eval_steps_per_second": 6.461,
+      "step": 16
+    },
+    {
+      "epoch": 0.007779736218318848,
+      "grad_norm": 33.15456771850586,
+      "learning_rate": 4.9623237724842005e-05,
+      "loss": 141.2284,
+      "step": 32
+    },
+    {
+      "epoch": 0.007779736218318848,
+      "eval_accuracy": 0.04097904438002165,
+      "eval_loss": 9.279535293579102,
+      "eval_runtime": 124.7723,
+      "eval_samples_per_second": 50.476,
+      "eval_steps_per_second": 6.316,
+      "step": 32
+    },
+    {
+      "epoch": 0.015559472436637696,
+      "grad_norm": 20.02243423461914,
+      "learning_rate": 4.9234321827904715e-05,
+      "loss": 127.002,
+      "step": 64
+    },
+    {
+      "epoch": 0.015559472436637696,
+      "eval_accuracy": 0.06789103090028115,
+      "eval_loss": 8.393986701965332,
+      "eval_runtime": 137.4464,
+      "eval_samples_per_second": 45.821,
+      "eval_steps_per_second": 5.733,
+      "step": 64
+    },
+    {
+      "epoch": 0.031118944873275392,
+      "grad_norm": 28.861949920654297,
+      "learning_rate": 4.8456490034030144e-05,
+      "loss": 116.9628,
+      "step": 128
+    },
+    {
+      "epoch": 0.031118944873275392,
+      "eval_accuracy": 0.099492243654753,
+      "eval_loss": 7.541510105133057,
+      "eval_runtime": 137.5865,
+      "eval_samples_per_second": 45.775,
+      "eval_steps_per_second": 5.727,
+      "step": 128
+    },
+    {
+      "epoch": 0.062237889746550784,
+      "grad_norm": 32.826515197753906,
+      "learning_rate": 4.6900826446280993e-05,
+      "loss": 103.7502,
+      "step": 256
+    },
+    {
+      "epoch": 0.062237889746550784,
+      "eval_accuracy": 0.11699364908781108,
+      "eval_loss": 6.44133186340332,
+      "eval_runtime": 127.4576,
+      "eval_samples_per_second": 49.413,
+      "eval_steps_per_second": 6.182,
+      "step": 256
+    },
+    {
+      "epoch": 0.12447577949310157,
+      "grad_norm": 24.268686294555664,
+      "learning_rate": 4.37894992707827e-05,
+      "loss": 99.1234,
+      "step": 512
+    },
+    {
+      "epoch": 0.12447577949310157,
+      "eval_accuracy": 0.16933101386435265,
+      "eval_loss": 5.398009300231934,
+      "eval_runtime": 135.7602,
+      "eval_samples_per_second": 46.391,
+      "eval_steps_per_second": 5.804,
+      "step": 512
+    }
+  ],
+  "logging_steps": 99999999,
+  "max_steps": 4114,
+  "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": 3.4248069218304e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-512/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b77e2990878402dc5d0c31d34134b78517327dfb3901fc27f5a7b5979fdc9f2
+size 6033