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 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
+  "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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e093eb6228bbc2b0849b7ea09073df2e38de38d08cb0852c9e0db77696c91e7c
+size 33600461

checkpoint-16/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: 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-16/adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
+  "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-16/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e093eb6228bbc2b0849b7ea09073df2e38de38d08cb0852c9e0db77696c91e7c
+size 33600461

checkpoint-16/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d84ba31890c07416c69263d14bb11d3b98a36fd3072a042ff509819814d472a3
+size 67216581

checkpoint-16/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18f55f528bdf77873e47f9f7ebfea3b611ab91c7618f8ae2616e7abb68d1eed0
+size 14575

checkpoint-16/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb0bdcb9c4dd07b3606c1fbebf102a106d5389004b5bdb3b4ed7f70d1b4f5df0
+size 627

checkpoint-16/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_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
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-16/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

checkpoint-16/tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1024,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": true
+}

checkpoint-16/trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.5,
+  "eval_steps": 500,
+  "global_step": 16,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.25,
+      "learning_rate": 7.5e-05,
+      "loss": 0.8681,
+      "step": 1
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00015,
+      "loss": 0.8696,
+      "step": 2
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.000225,
+      "loss": 0.8552,
+      "step": 3
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.0003,
+      "loss": 0.7928,
+      "step": 4
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 0.00028928571428571425,
+      "loss": 0.7436,
+      "step": 5
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 0.00027857142857142854,
+      "loss": 0.6743,
+      "step": 6
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 0.00026785714285714287,
+      "loss": 0.6366,
+      "step": 7
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 0.0002571428571428571,
+      "loss": 0.5894,
+      "step": 8
+    },
+    {
+      "epoch": 4.25,
+      "learning_rate": 0.0002464285714285714,
+      "loss": 0.5553,
+      "step": 9
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 0.00023571428571428569,
+      "loss": 0.5088,
+      "step": 10
+    },
+    {
+      "epoch": 5.25,
+      "learning_rate": 0.000225,
+      "loss": 0.4581,
+      "step": 11
+    },
+    {
+      "epoch": 5.5,
+      "learning_rate": 0.00021428571428571427,
+      "loss": 0.4222,
+      "step": 12
+    },
+    {
+      "epoch": 6.25,
+      "learning_rate": 0.00020357142857142856,
+      "loss": 0.3699,
+      "step": 13
+    },
+    {
+      "epoch": 6.5,
+      "learning_rate": 0.00019285714285714286,
+      "loss": 0.3272,
+      "step": 14
+    },
+    {
+      "epoch": 7.25,
+      "learning_rate": 0.00018214285714285712,
+      "loss": 0.2859,
+      "step": 15
+    },
+    {
+      "epoch": 7.5,
+      "learning_rate": 0.0001714285714285714,
+      "loss": 0.2595,
+      "step": 16
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 32,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 3984531891683328.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-16/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb544a6e8dbfc867b9837ba8f299ed53f7e2aa96a50f84624565341a952421f5
+size 4027

runs/Aug25_19-33-30_2c67f5da6186/events.out.tfevents.1692992011.2c67f5da6186.6995.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53bfe3d20d05ee3ca65ee65d940ec43598e6c1a39ae752e8202e424f9f486a35
+size 7251

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_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
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1024,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb544a6e8dbfc867b9837ba8f299ed53f7e2aa96a50f84624565341a952421f5
+size 4027

training_params.json

@@ -0,0 +1 @@
+{"model": "meta-llama/Llama-2-7b-chat-hf", "data_path": "/content/train", "project_name": "llama2-planner", "train_split": "train", "valid_split": null, "text_column": "text", "lr": 0.0003, "epochs": 8, "batch_size": 16, "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": "johaanm/llama2-openassistant-studyplannerV3", "use_int4": true, "trainer": "sft", "target_modules": null, "merge_adapter": false, "username": null}