Upload 11 files

README.md

@@ -1,12 +1,6 @@
 ---
 library_name: peft
 base_model: Sakonii/distilgpt2-nepali
-license: apache-2.0
-datasets:
-- Bibek1129/nepali_SQuAD_multiple_qsns
-language:
-- ne
-pipeline_tag: text-generation
 ---
 
 # Model Card for Model ID

adapter_config.json

@@ -0,0 +1,30 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Sakonii/distilgpt2-nepali",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "c_proj",
+    "lm_head",
+    "c_fc",
+    "c_attn"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7df55f938a36adbc331f4638f59c8c111ca427c441c7f3aa9c5595dade78966b
+size 170364520

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fd98899c51448b98aa5f8372267a409a84792612f01284e9f7c6d3c2be9a446
+size 31966906

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f6e404d99f48d71f4aa39106b5d5b4ed22efdd437298179d99bd7e77546ebc4
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92b4bf3b5450f1ce67be35c30bc019d175d5b6cf7a6f330f56db97eb9e0bbfa3
+size 1064

special_tokens_map.json

@@ -0,0 +1,45 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "add_eos_token": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "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": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,182 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 50.0,
+  "eval_steps": 500,
+  "global_step": 118100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.12,
+      "grad_norm": 1.353366494178772,
+      "learning_rate": 0.0002,
+      "loss": 3.6004,
+      "step": 5000
+    },
+    {
+      "epoch": 4.23,
+      "grad_norm": 1.4591169357299805,
+      "learning_rate": 0.0002,
+      "loss": 3.3767,
+      "step": 10000
+    },
+    {
+      "epoch": 6.35,
+      "grad_norm": 1.5558066368103027,
+      "learning_rate": 0.0002,
+      "loss": 3.3035,
+      "step": 15000
+    },
+    {
+      "epoch": 8.47,
+      "grad_norm": 1.54267418384552,
+      "learning_rate": 0.0002,
+      "loss": 3.2643,
+      "step": 20000
+    },
+    {
+      "epoch": 10.58,
+      "grad_norm": 1.6217669248580933,
+      "learning_rate": 0.0002,
+      "loss": 3.238,
+      "step": 25000
+    },
+    {
+      "epoch": 12.7,
+      "grad_norm": 1.5397529602050781,
+      "learning_rate": 0.0002,
+      "loss": 3.2201,
+      "step": 30000
+    },
+    {
+      "epoch": 14.82,
+      "grad_norm": 1.5048496723175049,
+      "learning_rate": 0.0002,
+      "loss": 3.2048,
+      "step": 35000
+    },
+    {
+      "epoch": 16.93,
+      "grad_norm": 1.5197534561157227,
+      "learning_rate": 0.0002,
+      "loss": 3.1947,
+      "step": 40000
+    },
+    {
+      "epoch": 19.05,
+      "grad_norm": 1.5024417638778687,
+      "learning_rate": 0.0002,
+      "loss": 3.1829,
+      "step": 45000
+    },
+    {
+      "epoch": 21.17,
+      "grad_norm": 1.5805625915527344,
+      "learning_rate": 0.0002,
+      "loss": 3.1729,
+      "step": 50000
+    },
+    {
+      "epoch": 23.29,
+      "grad_norm": 1.5682896375656128,
+      "learning_rate": 0.0002,
+      "loss": 3.1681,
+      "step": 55000
+    },
+    {
+      "epoch": 25.4,
+      "grad_norm": 1.5147111415863037,
+      "learning_rate": 0.0002,
+      "loss": 3.1619,
+      "step": 60000
+    },
+    {
+      "epoch": 27.52,
+      "grad_norm": 1.6233525276184082,
+      "learning_rate": 0.0002,
+      "loss": 3.1557,
+      "step": 65000
+    },
+    {
+      "epoch": 29.64,
+      "grad_norm": 1.5563185214996338,
+      "learning_rate": 0.0002,
+      "loss": 3.153,
+      "step": 70000
+    },
+    {
+      "epoch": 31.75,
+      "grad_norm": 1.5635435581207275,
+      "learning_rate": 0.0002,
+      "loss": 3.151,
+      "step": 75000
+    },
+    {
+      "epoch": 33.87,
+      "grad_norm": 1.471053957939148,
+      "learning_rate": 0.0002,
+      "loss": 3.1449,
+      "step": 80000
+    },
+    {
+      "epoch": 35.99,
+      "grad_norm": 1.5087348222732544,
+      "learning_rate": 0.0002,
+      "loss": 3.1414,
+      "step": 85000
+    },
+    {
+      "epoch": 38.1,
+      "grad_norm": 1.6342508792877197,
+      "learning_rate": 0.0002,
+      "loss": 3.1363,
+      "step": 90000
+    },
+    {
+      "epoch": 40.22,
+      "grad_norm": 1.7150408029556274,
+      "learning_rate": 0.0002,
+      "loss": 3.1327,
+      "step": 95000
+    },
+    {
+      "epoch": 42.34,
+      "grad_norm": 1.8055483102798462,
+      "learning_rate": 0.0002,
+      "loss": 3.1319,
+      "step": 100000
+    },
+    {
+      "epoch": 44.45,
+      "grad_norm": 1.509770154953003,
+      "learning_rate": 0.0002,
+      "loss": 3.13,
+      "step": 105000
+    },
+    {
+      "epoch": 46.57,
+      "grad_norm": 1.6583279371261597,
+      "learning_rate": 0.0002,
+      "loss": 3.1266,
+      "step": 110000
+    },
+    {
+      "epoch": 48.69,
+      "grad_norm": 1.7038261890411377,
+      "learning_rate": 0.0002,
+      "loss": 3.1273,
+      "step": 115000
+    }
+  ],
+  "logging_steps": 5000,
+  "max_steps": 118100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 500,
+  "total_flos": 7.86717088860818e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc49f4b336eeaa68f4661a657d0ab6a846ff743e9a59c9b32b51489b7cd5a138
+size 4920