初始化项目，由ModelHub XC社区提供模型

Model: fpadovani/bnc_np_13
Source: Original Platform

checkpoint-1500/config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "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": 2,
+  "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,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 30000
+}

checkpoint-1500/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "4.56.1"
+}

checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21aa2a984147a45e08e4cdceff13cee97111076c6158c5bce7476879f60fb8cb
+size 435544704

checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49a05bda4730f89a3ea266bc073ab1f97af95dbf9ee95f2785dbbc92ab6ca0e5
+size 871183627

checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83aee1b7bd3b3a1a1b1ba0548f8113e8b54fe7f81f23941e1c6b3d2a6fda6448
+size 14709

checkpoint-1500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca372268f4fa9335030c0cb7aedb6cdba75f457da50e7a4034abb1a2d0843689
+size 1383

checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f4eed346f914b4fdd6a141e9a558801bb5c9c8b8cc72e80a9693fee3bc5e665
+size 1465

checkpoint-1500/special_tokens_map.json

@@ -0,0 +1,8 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "</s>",
+  "sep_token": "<sep>",
+  "unk_token": "<unk>"
+}

checkpoint-1500/tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sep_token": "<sep>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}

checkpoint-1500/trainer_state.json

@@ -0,0 +1,86 @@
+{
+  "best_global_step": 1176,
+  "best_metric": 5.884053707122803,
+  "best_model_checkpoint": null,
+  "epoch": 3.826530612244898,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002551020408163265,
+      "grad_norm": 16.32339096069336,
+      "learning_rate": 0.0,
+      "loss": 10.3351,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6908162236213684,
+      "learning_rate": 7.82e-05,
+      "loss": 7.1094,
+      "step": 392
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 6.317445755004883,
+      "eval_runtime": 15.5824,
+      "eval_samples_per_second": 1616.887,
+      "eval_steps_per_second": 6.353,
+      "step": 392
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.7368313074111938,
+      "learning_rate": 9.613387978142077e-05,
+      "loss": 6.0963,
+      "step": 784
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 6.024065017700195,
+      "eval_runtime": 15.5591,
+      "eval_samples_per_second": 1619.314,
+      "eval_steps_per_second": 6.363,
+      "step": 784
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.7423638701438904,
+      "learning_rate": 9.077868852459017e-05,
+      "loss": 5.8833,
+      "step": 1176
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 5.884053707122803,
+      "eval_runtime": 15.6179,
+      "eval_samples_per_second": 1613.212,
+      "eval_steps_per_second": 6.339,
+      "step": 1176
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7840,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.506149863424e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52cf954a78a3d6fc682ff0c3b6ee4cda69040297e62c644ea0256038484a747a
+size 5905