初始化项目，由ModelHub XC社区提供模型

Model: fpadovani/bnc_np_13
Source: Original Platform

checkpoint-2500/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-2500/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-2500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4fd9d4bc6cedbb5d55b9f4a53101e8c8fa444e748e87a77cf5536e9c0ffd23d
+size 435544704

checkpoint-2500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8f957f3bc5abd0973a7c92ecb139c61c6e1bb1a68097ac95b547e4a510091ad
+size 871183627

checkpoint-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f655eadea0bb8fb3de92679308b6055c4b43becb869ffb037d950bf93bf9ffd6
+size 14709

checkpoint-2500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:861ce13e6ca091acee9a68ebfc5ca38479baf4b537c37b3949f071f77b81e9f0
+size 1383

checkpoint-2500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64c18a5545cf4e21a4422263bfc3007c9e2394c3dc59701db7dccff41ed54c63
+size 1465

checkpoint-2500/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-2500/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-2500/trainer_state.json

@@ -0,0 +1,131 @@
+{
+  "best_global_step": 2352,
+  "best_metric": 5.6633148193359375,
+  "best_model_checkpoint": null,
+  "epoch": 6.377551020408164,
+  "eval_steps": 500,
+  "global_step": 2500,
+  "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
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.707794725894928,
+      "learning_rate": 8.542349726775956e-05,
+      "loss": 5.7525,
+      "step": 1568
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 5.788422584533691,
+      "eval_runtime": 15.5176,
+      "eval_samples_per_second": 1623.64,
+      "eval_steps_per_second": 6.38,
+      "step": 1568
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.7633333802223206,
+      "learning_rate": 8.006830601092896e-05,
+      "loss": 5.6482,
+      "step": 1960
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 5.718640327453613,
+      "eval_runtime": 15.5828,
+      "eval_samples_per_second": 1616.851,
+      "eval_steps_per_second": 6.353,
+      "step": 1960
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.7929214239120483,
+      "learning_rate": 7.471311475409837e-05,
+      "loss": 5.5583,
+      "step": 2352
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 5.6633148193359375,
+      "eval_runtime": 15.6437,
+      "eval_samples_per_second": 1610.551,
+      "eval_steps_per_second": 6.328,
+      "step": 2352
+    }
+  ],
+  "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": 4.176165224448e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2500/training_args.bin

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