ashwinpreyan commited on Nov 7, 2023

Commit

3b7c393

1 Parent(s): a0e8f39

Upload folder using huggingface_hub

Browse files

Files changed (23) hide show

README.md +9 -0
adapter_config.json +21 -0
adapter_model.bin +3 -0
added_tokens.json +4 -0
checkpoint-500/README.md +34 -0
checkpoint-500/adapter_config.json +21 -0
checkpoint-500/adapter_model.bin +3 -0
checkpoint-500/added_tokens.json +4 -0
checkpoint-500/optimizer.pt +3 -0
checkpoint-500/rng_state.pth +3 -0
checkpoint-500/scheduler.pt +3 -0
checkpoint-500/special_tokens_map.json +24 -0
checkpoint-500/tokenizer.json +0 -0
checkpoint-500/tokenizer.model +3 -0
checkpoint-500/tokenizer_config.json +61 -0
checkpoint-500/trainer_state.json +319 -0
checkpoint-500/training_args.bin +3 -0
special_tokens_map.json +24 -0
tokenizer.json +0 -0
tokenizer.model +3 -0
tokenizer_config.json +61 -0
training_args.bin +3 -0
training_params.json +1 -0

README.md ADDED Viewed

	@@ -0,0 +1,9 @@

+---
+tags:
+- autotrain
+- text-generation
+widget:
+- text: "I love AutoTrain because "
+---
+# Model Trained Using AutoTrain

adapter_config.json ADDED Viewed

	@@ -0,0 +1,21 @@

+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "ehartford/dolphin-2.1-mistral-7b",
+  "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,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:50d65015ab88e5f12b05856a31f330c9e3aac9aaddc2844666dae408d24ee1cc
+size 27309386

added_tokens.json ADDED Viewed

	@@ -0,0 +1,4 @@

+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

checkpoint-500/README.md ADDED Viewed

	@@ -0,0 +1,34 @@

+---
+library_name: peft
+---
+## Training procedure
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- 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: nf4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float16
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- 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: nf4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float16
+### Framework versions
+- PEFT 0.5.0
+- PEFT 0.5.0

checkpoint-500/adapter_config.json ADDED Viewed

	@@ -0,0 +1,21 @@

+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "ehartford/dolphin-2.1-mistral-7b",
+  "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,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-500/adapter_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:50d65015ab88e5f12b05856a31f330c9e3aac9aaddc2844666dae408d24ee1cc
+size 27309386

checkpoint-500/added_tokens.json ADDED Viewed

	@@ -0,0 +1,4 @@

+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

checkpoint-500/optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1b49ba2470f085146dcf22b54e4aef6aa81a1589fa7655b5e25737cfc4c06088
+size 54633978

checkpoint-500/rng_state.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a547b0c9b8ed0db369c8aa3195461c4d3fb40f44488c4cc721ea0859a37308a1
+size 14180

checkpoint-500/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:35137eaed396f08075e26e0670438c2af1410770827a4bf2e64ce5b9e22665fa
+size 1064

checkpoint-500/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,24 @@

+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  }
+}

checkpoint-500/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

checkpoint-500/tokenizer.model ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

checkpoint-500/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,61 @@

+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 1024,
+  "pad_token": "<|im_end|>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}

checkpoint-500/trainer_state.json ADDED Viewed

	@@ -0,0 +1,319 @@

+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 99.09615384615384,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.1,
+      "learning_rate": 3.846153846153847e-06,
+      "loss": 1.9435,
+      "step": 10
+    },
+    {
+      "epoch": 3.1,
+      "learning_rate": 7.692307692307694e-06,
+      "loss": 1.7464,
+      "step": 20
+    },
+    {
+      "epoch": 5.1,
+      "learning_rate": 1.1153846153846154e-05,
+      "loss": 1.4021,
+      "step": 30
+    },
+    {
+      "epoch": 7.1,
+      "learning_rate": 1.5e-05,
+      "loss": 0.9709,
+      "step": 40
+    },
+    {
+      "epoch": 9.1,
+      "learning_rate": 1.8846153846153846e-05,
+      "loss": 0.7347,
+      "step": 50
+    },
+    {
+      "epoch": 11.1,
+      "learning_rate": 2.2692307692307694e-05,
+      "loss": 0.5554,
+      "step": 60
+    },
+    {
+      "epoch": 13.1,
+      "learning_rate": 2.6538461538461538e-05,
+      "loss": 0.4468,
+      "step": 70
+    },
+    {
+      "epoch": 15.1,
+      "learning_rate": 3.0384615384615382e-05,
+      "loss": 0.3523,
+      "step": 80
+    },
+    {
+      "epoch": 17.1,
+      "learning_rate": 3.4230769230769234e-05,
+      "loss": 0.2729,
+      "step": 90
+    },
+    {
+      "epoch": 19.1,
+      "learning_rate": 3.807692307692308e-05,
+      "loss": 0.2064,
+      "step": 100
+    },
+    {
+      "epoch": 21.1,
+      "learning_rate": 4.192307692307693e-05,
+      "loss": 0.1537,
+      "step": 110
+    },
+    {
+      "epoch": 23.1,
+      "learning_rate": 4.576923076923077e-05,
+      "loss": 0.113,
+      "step": 120
+    },
+    {
+      "epoch": 25.1,
+      "learning_rate": 4.961538461538462e-05,
+      "loss": 0.0768,
+      "step": 130
+    },
+    {
+      "epoch": 27.1,
+      "learning_rate": 5.3076923076923076e-05,
+      "loss": 0.0523,
+      "step": 140
+    },
+    {
+      "epoch": 29.1,
+      "learning_rate": 5.692307692307692e-05,
+      "loss": 0.0387,
+      "step": 150
+    },
+    {
+      "epoch": 31.1,
+      "learning_rate": 6.0769230769230765e-05,
+      "loss": 0.0333,
+      "step": 160
+    },
+    {
+      "epoch": 33.1,
+      "learning_rate": 6.461538461538462e-05,
+      "loss": 0.025,
+      "step": 170
+    },
+    {
+      "epoch": 35.1,
+      "learning_rate": 6.846153846153847e-05,
+      "loss": 0.0188,
+      "step": 180
+    },
+    {
+      "epoch": 37.1,
+      "learning_rate": 7.23076923076923e-05,
+      "loss": 0.0153,
+      "step": 190
+    },
+    {
+      "epoch": 39.1,
+      "learning_rate": 7.615384615384616e-05,
+      "loss": 0.0109,
+      "step": 200
+    },
+    {
+      "epoch": 41.1,
+      "learning_rate": 8e-05,
+      "loss": 0.0112,
+      "step": 210
+    },
+    {
+      "epoch": 43.1,
+      "learning_rate": 8.384615384615386e-05,
+      "loss": 0.0118,
+      "step": 220
+    },
+    {
+      "epoch": 45.1,
+      "learning_rate": 8.76923076923077e-05,
+      "loss": 0.0079,
+      "step": 230
+    },
+    {
+      "epoch": 47.1,
+      "learning_rate": 9.153846153846155e-05,
+      "loss": 0.009,
+      "step": 240
+    },
+    {
+      "epoch": 49.1,
+      "learning_rate": 9.53846153846154e-05,
+      "loss": 0.0074,
+      "step": 250
+    },
+    {
+      "epoch": 51.1,
+      "learning_rate": 9.923076923076923e-05,
+      "loss": 0.0069,
+      "step": 260
+    },
+    {
+      "epoch": 53.1,
+      "learning_rate": 0.00010307692307692307,
+      "loss": 0.0077,
+      "step": 270
+    },
+    {
+      "epoch": 55.1,
+      "learning_rate": 0.00010692307692307692,
+      "loss": 0.006,
+      "step": 280
+    },
+    {
+      "epoch": 57.1,
+      "learning_rate": 0.00011076923076923077,
+      "loss": 0.0064,
+      "step": 290
+    },
+    {
+      "epoch": 59.1,
+      "learning_rate": 0.00011461538461538461,
+      "loss": 0.0059,
+      "step": 300
+    },
+    {
+      "epoch": 61.1,
+      "learning_rate": 0.00011846153846153846,
+      "loss": 0.0063,
+      "step": 310
+    },
+    {
+      "epoch": 63.1,
+      "learning_rate": 0.00012230769230769231,
+      "loss": 0.0069,
+      "step": 320
+    },
+    {
+      "epoch": 65.1,
+      "learning_rate": 0.00012615384615384615,
+      "loss": 0.0069,
+      "step": 330
+    },
+    {
+      "epoch": 67.1,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 0.0042,
+      "step": 340
+    },
+    {
+      "epoch": 69.1,
+      "learning_rate": 0.00013384615384615385,
+      "loss": 0.0049,
+      "step": 350
+    },
+    {
+      "epoch": 71.1,
+      "learning_rate": 0.0001376923076923077,
+      "loss": 0.0046,
+      "step": 360
+    },
+    {
+      "epoch": 73.1,
+      "learning_rate": 0.00014153846153846156,
+      "loss": 0.0041,
+      "step": 370
+    },
+    {
+      "epoch": 75.1,
+      "learning_rate": 0.0001453846153846154,
+      "loss": 0.0047,
+      "step": 380
+    },
+    {
+      "epoch": 77.1,
+      "learning_rate": 0.00014923076923076923,
+      "loss": 0.0053,
+      "step": 390
+    },
+    {
+      "epoch": 79.1,
+      "learning_rate": 0.00015307692307692307,
+      "loss": 0.005,
+      "step": 400
+    },
+    {
+      "epoch": 81.1,
+      "learning_rate": 0.00015692307692307693,
+      "loss": 0.0057,
+      "step": 410
+    },
+    {
+      "epoch": 83.1,
+      "learning_rate": 0.00016076923076923077,
+      "loss": 0.0059,
+      "step": 420
+    },
+    {
+      "epoch": 85.1,
+      "learning_rate": 0.0001646153846153846,
+      "loss": 0.0038,
+      "step": 430
+    },
+    {
+      "epoch": 87.1,
+      "learning_rate": 0.00016846153846153847,
+      "loss": 0.005,
+      "step": 440
+    },
+    {
+      "epoch": 89.1,
+      "learning_rate": 0.00017230769230769234,
+      "loss": 0.0034,
+      "step": 450
+    },
+    {
+      "epoch": 91.1,
+      "learning_rate": 0.00017615384615384615,
+      "loss": 0.0021,
+      "step": 460
+    },
+    {
+      "epoch": 93.1,
+      "learning_rate": 0.00018,
+      "loss": 0.002,
+      "step": 470
+    },
+    {
+      "epoch": 95.1,
+      "learning_rate": 0.00018384615384615385,
+      "loss": 0.0035,
+      "step": 480
+    },
+    {
+      "epoch": 97.1,
+      "learning_rate": 0.0001876923076923077,
+      "loss": 0.0029,
+      "step": 490
+    },
+    {
+      "epoch": 99.1,
+      "learning_rate": 0.00019153846153846155,
+      "loss": 0.0021,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5200,
+  "num_train_epochs": 100,
+  "save_steps": 500,
+  "total_flos": 7.87136794066944e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:0a5ac2427389e034687a9e031f2e957eeeeb07b1e2c41abceabffe1c0c3d4f84
+size 4472

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,24 @@

+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  }
+}

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer.model ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,61 @@

+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 1024,
+  "pad_token": "<|im_end|>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:0a5ac2427389e034687a9e031f2e957eeeeb07b1e2c41abceabffe1c0c3d4f84
+size 4472

training_params.json ADDED Viewed

	@@ -0,0 +1 @@

+ {"model": "ehartford/dolphin-2.1-mistral-7b", "data_path": "ashwinpreyan/prodoction", "project_name": "percival", "train_split": "train", "valid_split": null, "text_column": "text", "rejected_text_column": "rejected", "lr": 0.0002, "epochs": 100, "batch_size": 4, "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": false, "fp16": false, "push_to_hub": true, "use_int8": false, "model_max_length": 1024, "repo_id": "ashwinpreyan/percival-dolphin", "use_int4": true, "trainer": "sft", "target_modules": "q_proj,v_proj", "merge_adapter": false, "username": null, "use_flash_attention_2": false, "log": "none", "disable_gradient_checkpointing": false, "model_ref": null, "dpo_beta": 0.1, "prompt_text_column": "prompt"}