初始化项目，由ModelHub XC社区提供模型

Model: alakxender/dhivehi-gpt2-base
Source: Original Platform

checkpoint-123/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "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,
+  "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
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 50258
+}

checkpoint-123/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.46.3"
+}

checkpoint-123/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf64a93419d4aeb9079da0eb6f33276c930b740d901b4378ae9f11c5aa786d0f
+size 497777280

checkpoint-123/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47fe9f7fcec27cf0397fed0aea7d3d4b1d7b7b7d1a8e0ac31f5ed4f19e45be2e
+size 995648442

checkpoint-123/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f9c2abd33f8421dbe1f81a265d65c5e9b7976e8c94fcbf0c6fa98d24a1e34d4
+size 14244

checkpoint-123/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4447704abe5a3947412c6e315c46fd7fa1c7b8d0c8048f8a9031f4f62c23812
+size 1064

checkpoint-123/trainer_state.json

@@ -0,0 +1,125 @@
+{
+  "best_metric": 1.382002830505371,
+  "best_model_checkpoint": "dhivehi-gpt2-base/checkpoint-100",
+  "epoch": 3.0,
+  "eval_steps": 100,
+  "global_step": 123,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.24390243902439024,
+      "grad_norm": 83.27034759521484,
+      "learning_rate": 2.5000000000000004e-07,
+      "loss": 2.4436,
+      "step": 10
+    },
+    {
+      "epoch": 0.4878048780487805,
+      "grad_norm": 60.58613967895508,
+      "learning_rate": 7.5e-07,
+      "loss": 2.321,
+      "step": 20
+    },
+    {
+      "epoch": 0.7317073170731707,
+      "grad_norm": 29.228893280029297,
+      "learning_rate": 1.25e-06,
+      "loss": 2.0685,
+      "step": 30
+    },
+    {
+      "epoch": 0.975609756097561,
+      "grad_norm": 18.66552734375,
+      "learning_rate": 1.7500000000000002e-06,
+      "loss": 1.8913,
+      "step": 40
+    },
+    {
+      "epoch": 1.2195121951219512,
+      "grad_norm": 10.73972225189209,
+      "learning_rate": 2.25e-06,
+      "loss": 1.7331,
+      "step": 50
+    },
+    {
+      "epoch": 1.4634146341463414,
+      "grad_norm": 6.437626361846924,
+      "learning_rate": 2.7500000000000004e-06,
+      "loss": 1.6317,
+      "step": 60
+    },
+    {
+      "epoch": 1.7073170731707317,
+      "grad_norm": 3.9424028396606445,
+      "learning_rate": 3.2500000000000002e-06,
+      "loss": 1.5445,
+      "step": 70
+    },
+    {
+      "epoch": 1.951219512195122,
+      "grad_norm": 2.4789206981658936,
+      "learning_rate": 3.75e-06,
+      "loss": 1.4638,
+      "step": 80
+    },
+    {
+      "epoch": 2.1951219512195124,
+      "grad_norm": 1.7527034282684326,
+      "learning_rate": 4.250000000000001e-06,
+      "loss": 1.3972,
+      "step": 90
+    },
+    {
+      "epoch": 2.4390243902439024,
+      "grad_norm": 1.9903717041015625,
+      "learning_rate": 4.75e-06,
+      "loss": 1.3272,
+      "step": 100
+    },
+    {
+      "epoch": 2.4390243902439024,
+      "eval_loss": 1.382002830505371,
+      "eval_runtime": 5.1108,
+      "eval_samples_per_second": 56.742,
+      "eval_steps_per_second": 1.957,
+      "step": 100
+    },
+    {
+      "epoch": 2.682926829268293,
+      "grad_norm": 3.0437378883361816,
+      "learning_rate": 5.25e-06,
+      "loss": 1.292,
+      "step": 110
+    },
+    {
+      "epoch": 2.926829268292683,
+      "grad_norm": 5.521629810333252,
+      "learning_rate": 5.750000000000001e-06,
+      "loss": 1.2725,
+      "step": 120
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 123,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4080858955776000.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-123/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33253810238ac5f6e19d65eaf18a7b5652de403635f7f896af35a9b7b932f10a
+size 5240