Upload folder using huggingface_hub

README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- autotrain
+- text-generation
+widget:
+- text: "I love AutoTrain because "
+---
+
+# Model Trained Using AutoTrain

adapter_config.json

@@ -0,0 +1,22 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "EleutherAI/pythia-1.4b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc14c473ec8bccda37ba5e5234f6b1846f2f7a82a0b90fe196addb795f5cf39c
+size 12600513

checkpoint-2000/README.md

@@ -0,0 +1,34 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+### Framework versions
+
+- PEFT 0.6.0.dev0
+
+- PEFT 0.6.0.dev0

checkpoint-2000/adapter_config.json

@@ -0,0 +1,22 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "EleutherAI/pythia-1.4b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-2000/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc14c473ec8bccda37ba5e5234f6b1846f2f7a82a0b90fe196addb795f5cf39c
+size 12600513

checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1adae34196ec3965e7e84f66e4662daff93788c35046bf9b226b89476f46a75a
+size 25206149

checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52f736be3876a5ac9f6410e917bd20e1a67c9ccda046c91a3b5aec1573ae88ba
+size 14511

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aafb6a19627506a3cb78949236c86ac9f038aa80fc2f986cbd7c4c03d83a76bc
+size 627

checkpoint-2000/special_tokens_map.json

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

checkpoint-2000/tokenizer_config.json

@@ -0,0 +1,212 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50254": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50255": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50256": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50257": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-2000/trainer_state.json

@@ -0,0 +1,415 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 199.0662251655629,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.07,
+      "learning_rate": 9.933774834437087e-07,
+      "loss": 2.1111,
+      "step": 30
+    },
+    {
+      "epoch": 5.07,
+      "learning_rate": 1.9867549668874175e-06,
+      "loss": 2.0911,
+      "step": 60
+    },
+    {
+      "epoch": 8.07,
+      "learning_rate": 2.9801324503311258e-06,
+      "loss": 2.0488,
+      "step": 90
+    },
+    {
+      "epoch": 11.07,
+      "learning_rate": 3.973509933774835e-06,
+      "loss": 1.9825,
+      "step": 120
+    },
+    {
+      "epoch": 14.07,
+      "learning_rate": 4.966887417218543e-06,
+      "loss": 1.8997,
+      "step": 150
+    },
+    {
+      "epoch": 17.07,
+      "learning_rate": 5.9602649006622515e-06,
+      "loss": 1.811,
+      "step": 180
+    },
+    {
+      "epoch": 20.07,
+      "learning_rate": 6.95364238410596e-06,
+      "loss": 1.7265,
+      "step": 210
+    },
+    {
+      "epoch": 23.07,
+      "learning_rate": 7.94701986754967e-06,
+      "loss": 1.6527,
+      "step": 240
+    },
+    {
+      "epoch": 26.07,
+      "learning_rate": 8.940397350993377e-06,
+      "loss": 1.5955,
+      "step": 270
+    },
+    {
+      "epoch": 29.07,
+      "learning_rate": 9.933774834437086e-06,
+      "loss": 1.5492,
+      "step": 300
+    },
+    {
+      "epoch": 32.07,
+      "learning_rate": 1.0927152317880796e-05,
+      "loss": 1.508,
+      "step": 330
+    },
+    {
+      "epoch": 35.07,
+      "learning_rate": 1.1920529801324503e-05,
+      "loss": 1.4678,
+      "step": 360
+    },
+    {
+      "epoch": 38.07,
+      "learning_rate": 1.2913907284768212e-05,
+      "loss": 1.4278,
+      "step": 390
+    },
+    {
+      "epoch": 41.07,
+      "learning_rate": 1.390728476821192e-05,
+      "loss": 1.3864,
+      "step": 420
+    },
+    {
+      "epoch": 44.07,
+      "learning_rate": 1.490066225165563e-05,
+      "loss": 1.3418,
+      "step": 450
+    },
+    {
+      "epoch": 47.07,
+      "learning_rate": 1.589403973509934e-05,
+      "loss": 1.2955,
+      "step": 480
+    },
+    {
+      "epoch": 50.07,
+      "learning_rate": 1.688741721854305e-05,
+      "loss": 1.2506,
+      "step": 510
+    },
+    {
+      "epoch": 53.07,
+      "learning_rate": 1.7880794701986755e-05,
+      "loss": 1.2051,
+      "step": 540
+    },
+    {
+      "epoch": 56.07,
+      "learning_rate": 1.8874172185430464e-05,
+      "loss": 1.1617,
+      "step": 570
+    },
+    {
+      "epoch": 59.07,
+      "learning_rate": 1.9867549668874173e-05,
+      "loss": 1.1198,
+      "step": 600
+    },
+    {
+      "epoch": 62.07,
+      "learning_rate": 2.0860927152317882e-05,
+      "loss": 1.0815,
+      "step": 630
+    },
+    {
+      "epoch": 65.07,
+      "learning_rate": 2.185430463576159e-05,
+      "loss": 1.0462,
+      "step": 660
+    },
+    {
+      "epoch": 68.07,
+      "learning_rate": 2.28476821192053e-05,
+      "loss": 1.0112,
+      "step": 690
+    },
+    {
+      "epoch": 71.07,
+      "learning_rate": 2.3841059602649006e-05,
+      "loss": 0.9762,
+      "step": 720
+    },
+    {
+      "epoch": 74.07,
+      "learning_rate": 2.4834437086092715e-05,
+      "loss": 0.941,
+      "step": 750
+    },
+    {
+      "epoch": 77.07,
+      "learning_rate": 2.5827814569536424e-05,
+      "loss": 0.9048,
+      "step": 780
+    },
+    {
+      "epoch": 80.07,
+      "learning_rate": 2.6821192052980134e-05,
+      "loss": 0.8728,
+      "step": 810
+    },
+    {
+      "epoch": 83.07,
+      "learning_rate": 2.781456953642384e-05,
+      "loss": 0.839,
+      "step": 840
+    },
+    {
+      "epoch": 86.07,
+      "learning_rate": 2.880794701986755e-05,
+      "loss": 0.8041,
+      "step": 870
+    },
+    {
+      "epoch": 89.07,
+      "learning_rate": 2.980132450331126e-05,
+      "loss": 0.7714,
+      "step": 900
+    },
+    {
+      "epoch": 92.07,
+      "learning_rate": 3.079470198675497e-05,
+      "loss": 0.7396,
+      "step": 930
+    },
+    {
+      "epoch": 95.07,
+      "learning_rate": 3.178807947019868e-05,
+      "loss": 0.7062,
+      "step": 960
+    },
+    {
+      "epoch": 98.07,
+      "learning_rate": 3.278145695364239e-05,
+      "loss": 0.6731,
+      "step": 990
+    },
+    {
+      "epoch": 101.07,
+      "learning_rate": 3.37748344370861e-05,
+      "loss": 0.6376,
+      "step": 1020
+    },
+    {
+      "epoch": 104.07,
+      "learning_rate": 3.47682119205298e-05,
+      "loss": 0.6083,
+      "step": 1050
+    },
+    {
+      "epoch": 107.07,
+      "learning_rate": 3.576158940397351e-05,
+      "loss": 0.5789,
+      "step": 1080
+    },
+    {
+      "epoch": 110.07,
+      "learning_rate": 3.675496688741722e-05,
+      "loss": 0.5487,
+      "step": 1110
+    },
+    {
+      "epoch": 113.07,
+      "learning_rate": 3.774834437086093e-05,
+      "loss": 0.5202,
+      "step": 1140
+    },
+    {
+      "epoch": 116.07,
+      "learning_rate": 3.8741721854304637e-05,
+      "loss": 0.4941,
+      "step": 1170
+    },
+    {
+      "epoch": 119.07,
+      "learning_rate": 3.9735099337748346e-05,
+      "loss": 0.4675,
+      "step": 1200
+    },
+    {
+      "epoch": 122.07,
+      "learning_rate": 4.0728476821192055e-05,
+      "loss": 0.4421,
+      "step": 1230
+    },
+    {
+      "epoch": 125.07,
+      "learning_rate": 4.1721854304635764e-05,
+      "loss": 0.4175,
+      "step": 1260
+    },
+    {
+      "epoch": 128.07,
+      "learning_rate": 4.271523178807947e-05,
+      "loss": 0.3933,
+      "step": 1290
+    },
+    {
+      "epoch": 131.07,
+      "learning_rate": 4.370860927152318e-05,
+      "loss": 0.3664,
+      "step": 1320
+    },
+    {
+      "epoch": 134.07,
+      "learning_rate": 4.470198675496689e-05,
+      "loss": 0.3446,
+      "step": 1350
+    },
+    {
+      "epoch": 137.07,
+      "learning_rate": 4.56953642384106e-05,
+      "loss": 0.32,
+      "step": 1380
+    },
+    {
+      "epoch": 140.07,
+      "learning_rate": 4.668874172185431e-05,
+      "loss": 0.305,
+      "step": 1410
+    },
+    {
+      "epoch": 143.07,
+      "learning_rate": 4.768211920529801e-05,
+      "loss": 0.2827,
+      "step": 1440
+    },
+    {
+      "epoch": 146.07,
+      "learning_rate": 4.867549668874172e-05,
+      "loss": 0.2646,
+      "step": 1470
+    },
+    {
+      "epoch": 149.07,
+      "learning_rate": 4.966887417218543e-05,
+      "loss": 0.2455,
+      "step": 1500
+    },
+    {
+      "epoch": 152.07,
+      "learning_rate": 5.0662251655629146e-05,
+      "loss": 0.2318,
+      "step": 1530
+    },
+    {
+      "epoch": 155.07,
+      "learning_rate": 5.165562913907285e-05,
+      "loss": 0.2141,
+      "step": 1560
+    },
+    {
+      "epoch": 158.07,
+      "learning_rate": 5.264900662251656e-05,
+      "loss": 0.1944,
+      "step": 1590
+    },
+    {
+      "epoch": 161.07,
+      "learning_rate": 5.364238410596027e-05,
+      "loss": 0.1807,
+      "step": 1620
+    },
+    {
+      "epoch": 164.07,
+      "learning_rate": 5.4635761589403976e-05,
+      "loss": 0.1731,
+      "step": 1650
+    },
+    {
+      "epoch": 167.07,
+      "learning_rate": 5.562913907284768e-05,
+      "loss": 0.1582,
+      "step": 1680
+    },
+    {
+      "epoch": 170.07,
+      "learning_rate": 5.6622516556291394e-05,
+      "loss": 0.1514,
+      "step": 1710
+    },
+    {
+      "epoch": 173.07,
+      "learning_rate": 5.76158940397351e-05,
+      "loss": 0.1379,
+      "step": 1740
+    },
+    {
+      "epoch": 176.07,
+      "learning_rate": 5.860927152317881e-05,
+      "loss": 0.1324,
+      "step": 1770
+    },
+    {
+      "epoch": 179.07,
+      "learning_rate": 5.960264900662252e-05,
+      "loss": 0.1194,
+      "step": 1800
+    },
+    {
+      "epoch": 182.07,
+      "learning_rate": 6.0596026490066224e-05,
+      "loss": 0.1099,
+      "step": 1830
+    },
+    {
+      "epoch": 185.07,
+      "learning_rate": 6.158940397350994e-05,
+      "loss": 0.1051,
+      "step": 1860
+    },
+    {
+      "epoch": 188.07,
+      "learning_rate": 6.258278145695365e-05,
+      "loss": 0.0955,
+      "step": 1890
+    },
+    {
+      "epoch": 191.07,
+      "learning_rate": 6.357615894039736e-05,
+      "loss": 0.094,
+      "step": 1920
+    },
+    {
+      "epoch": 194.07,
+      "learning_rate": 6.456953642384105e-05,
+      "loss": 0.0853,
+      "step": 1950
+    },
+    {
+      "epoch": 197.07,
+      "learning_rate": 6.556291390728478e-05,
+      "loss": 0.0786,
+      "step": 1980
+    }
+  ],
+  "logging_steps": 30,
+  "max_steps": 30200,
+  "num_train_epochs": 200,
+  "save_steps": 500,
+  "total_flos": 3.2310451765248e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8877555b98a39dae5880b5c4f790020efbadf582410dafdc23415d644bc37379
+size 4091

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "EleutherAI/pythia-1.4b",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.34.0.dev0",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.34.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0364d07ff3980a082aa1f8444218644a5a3ec4b6e5a290d3b4c4d0cc65673e0d
+size 2829399677

runs/Oct01_13-06-50_c7315105c6f1/events.out.tfevents.1696165611.c7315105c6f1.2441.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4742e41fb55299886270e924062313999b0abe116cbd11096fcbf93083540c34
+size 15313

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,212 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50254": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50255": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50256": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50257": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8877555b98a39dae5880b5c4f790020efbadf582410dafdc23415d644bc37379
+size 4091

training_params.json

@@ -0,0 +1 @@
+{"model": "EleutherAI/pythia-1.4b", "data_path": "Pravincoder/Traffic_and_legal_laws", "project_name": "pythia-legal-llm-v4", "train_split": "train", "valid_split": null, "text_column": "text", "lr": 0.0001, "epochs": 200, "batch_size": 2, "warmup_ratio": 0.1, "gradient_accumulation": 1, "optimizer": "adamw_torch", "scheduler": "linear", "weight_decay": 0.0, "max_grad_norm": 1.0, "seed": 42, "add_eos_token": false, "block_size": -1, "use_peft": true, "lora_r": 16, "lora_alpha": 32, "lora_dropout": 0.05, "logging_steps": -1, "evaluation_strategy": "epoch", "save_total_limit": 1, "save_strategy": "epoch", "auto_find_batch_size": true, "fp16": false, "push_to_hub": true, "use_int8": true, "model_max_length": 2048, "repo_id": "Pravincoder/pythia-legal-llm-v4", "use_int4": false, "trainer": "sft", "target_modules": null, "merge_adapter": true, "username": null, "use_flash_attention_2": false}