Upload 25 files

my_autotrain_llm/README.md

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

my_autotrain_llm/adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "abhishek/llama-2-7b-hf-small-shards",
+  "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"
+}

my_autotrain_llm/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e435ec8734dfb0f8e0cc1d1a7794f6c501cd4cfc08362379fdb5924c067b1df
+size 33600461

my_autotrain_llm/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}

my_autotrain_llm/checkpoint-6/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 0.6.0.dev0
+
+- PEFT 0.6.0.dev0

my_autotrain_llm/checkpoint-6/adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "abhishek/llama-2-7b-hf-small-shards",
+  "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"
+}

my_autotrain_llm/checkpoint-6/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e435ec8734dfb0f8e0cc1d1a7794f6c501cd4cfc08362379fdb5924c067b1df
+size 33600461

my_autotrain_llm/checkpoint-6/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}

my_autotrain_llm/checkpoint-6/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71f8e565ef2fc7d399f0a8b3543520d4f7d92ca4843cc0179789c8292572a64f
+size 67216581

my_autotrain_llm/checkpoint-6/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c152074a486243089e4fc0fdee0a373a30fb0e0a6e40eb5fd0d36fdafc97a155
+size 443

my_autotrain_llm/checkpoint-6/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbe8f9e35f1fb5cc80e77f1b19604264b0887bfcf8a2d89c68829a3c8712aece
+size 14575

my_autotrain_llm/checkpoint-6/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94b96e406e63b9a1f153cfaf08a989666c2cfa350c583c0f1bba816cc8eae242
+size 627

my_autotrain_llm/checkpoint-6/special_tokens_map.json

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

my_autotrain_llm/checkpoint-6/tokenizer.model

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

my_autotrain_llm/checkpoint-6/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1024,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": true
+}

my_autotrain_llm/checkpoint-6/trainer_state.json

@@ -0,0 +1,25 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 6,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.67,
+      "learning_rate": 8e-05,
+      "loss": 1.0533,
+      "step": 4
+    }
+  ],
+  "logging_steps": 4,
+  "max_steps": 6,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 498067090440192.0,
+  "trial_name": null,
+  "trial_params": null
+}

my_autotrain_llm/checkpoint-6/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c12502f15cf99be7482bb39ff8ffddb975d94cc27316ef6ff967d79cb2329b5c
+size 4027

my_autotrain_llm/runs/Aug29_11-57-24_0fbcaa219a51/events.out.tfevents.1693310244.0fbcaa219a51.2077.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cf29bbd14d428b59219ae919a150ef092ba3cd0df826dd5e147f79451dc96a3
+size 5002

my_autotrain_llm/special_tokens_map.json

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

my_autotrain_llm/tokenizer.model

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

my_autotrain_llm/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1024,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": true
+}

my_autotrain_llm/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c12502f15cf99be7482bb39ff8ffddb975d94cc27316ef6ff967d79cb2329b5c
+size 4027

my_autotrain_llm/training_params.json

@@ -0,0 +1,40 @@
+{
+    "model": "abhishek/llama-2-7b-hf-small-shards",
+    "data_path": "data/",
+    "project_name": "my_autotrain_llm",
+    "train_split": "train",
+    "valid_split": null,
+    "text_column": "text",
+    "token": null,
+    "lr": 0.0002,
+    "epochs": 1,
+    "batch_size": 1,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 4,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.01,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "add_eos_token": false,
+    "block_size": 1024,
+    "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": true,
+    "push_to_hub": false,
+    "use_int8": false,
+    "model_max_length": 1024,
+    "repo_id": null,
+    "use_int4": true,
+    "trainer": "default",
+    "target_modules": null,
+    "merge_adapter": false,
+    "username": null
+}