初始化项目，由ModelHub XC社区提供模型

Model: Cisco1963/llmplasticity-de_fi_instant_0.5_1-seed42
Source: Original Platform

checkpoint-64/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-64/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-64/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad3539e17c6e8fb1d9d52b19d6d579420b12a2f2f5f225379f19f912073a7abd
+size 497774208

checkpoint-64/special_tokens_map.json

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

checkpoint-64/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-64/trainer_state.json

@@ -0,0 +1,146 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.013709634231242971,
+  "eval_steps": 99999999,
+  "global_step": 64,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00021421303486317142,
+      "grad_norm": 174.29400634765625,
+      "learning_rate": 5e-05,
+      "loss": 175.3938,
+      "step": 1
+    },
+    {
+      "epoch": 0.00021421303486317142,
+      "eval_accuracy": 0.024215843286987115,
+      "eval_loss": 10.354011535644531,
+      "eval_runtime": 152.0177,
+      "eval_samples_per_second": 52.06,
+      "eval_steps_per_second": 6.512,
+      "step": 1
+    },
+    {
+      "epoch": 0.00042842606972634284,
+      "grad_norm": 83.63705444335938,
+      "learning_rate": 4.998929106875134e-05,
+      "loss": 164.501,
+      "step": 2
+    },
+    {
+      "epoch": 0.00042842606972634284,
+      "eval_accuracy": 0.024217696048750854,
+      "eval_loss": 10.13454532623291,
+      "eval_runtime": 137.1006,
+      "eval_samples_per_second": 57.724,
+      "eval_steps_per_second": 7.221,
+      "step": 2
+    },
+    {
+      "epoch": 0.0008568521394526857,
+      "grad_norm": 43.825008392333984,
+      "learning_rate": 4.996787320625402e-05,
+      "loss": 158.761,
+      "step": 4
+    },
+    {
+      "epoch": 0.0008568521394526857,
+      "eval_accuracy": 0.024217696048750854,
+      "eval_loss": 9.977794647216797,
+      "eval_runtime": 136.1039,
+      "eval_samples_per_second": 58.147,
+      "eval_steps_per_second": 7.274,
+      "step": 4
+    },
+    {
+      "epoch": 0.0017137042789053714,
+      "grad_norm": 35.26683044433594,
+      "learning_rate": 4.9925037481259376e-05,
+      "loss": 155.013,
+      "step": 8
+    },
+    {
+      "epoch": 0.0017137042789053714,
+      "eval_accuracy": 0.054267762612305155,
+      "eval_loss": 9.693761825561523,
+      "eval_runtime": 137.244,
+      "eval_samples_per_second": 57.664,
+      "eval_steps_per_second": 7.213,
+      "step": 8
+    },
+    {
+      "epoch": 0.0034274085578107428,
+      "grad_norm": 40.224300384521484,
+      "learning_rate": 4.983936603127008e-05,
+      "loss": 149.2168,
+      "step": 16
+    },
+    {
+      "epoch": 0.0034274085578107428,
+      "eval_accuracy": 0.016920902635887105,
+      "eval_loss": 11.783411026000977,
+      "eval_runtime": 146.7615,
+      "eval_samples_per_second": 53.924,
+      "eval_steps_per_second": 6.746,
+      "step": 16
+    },
+    {
+      "epoch": 0.0068548171156214855,
+      "grad_norm": 37.21358871459961,
+      "learning_rate": 4.96680231312915e-05,
+      "loss": 145.3381,
+      "step": 32
+    },
+    {
+      "epoch": 0.0068548171156214855,
+      "eval_accuracy": 0.0519994881436834,
+      "eval_loss": 8.588780403137207,
+      "eval_runtime": 142.279,
+      "eval_samples_per_second": 55.623,
+      "eval_steps_per_second": 6.958,
+      "step": 32
+    },
+    {
+      "epoch": 0.013709634231242971,
+      "grad_norm": 23.38722038269043,
+      "learning_rate": 4.932533733133434e-05,
+      "loss": 115.3768,
+      "step": 64
+    },
+    {
+      "epoch": 0.013709634231242971,
+      "eval_accuracy": 0.07924990816477524,
+      "eval_loss": 7.433769702911377,
+      "eval_runtime": 147.5767,
+      "eval_samples_per_second": 53.626,
+      "eval_steps_per_second": 6.708,
+      "step": 64
+    }
+  ],
+  "logging_steps": 99999999,
+  "max_steps": 4669,
+  "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": 4281008652288000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-64/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f50924331c1de5e48d50012fff872f96fc7cbb023d365504e669dda3e5d82865
+size 5969