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 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/home/skynet/Desktop/ipynb/models/models--Trelis--Llama-2-7b-chat-hf-sharded-bf16/snapshots/030e65c29ec7bc5e0a0f129150cbf530d55f5f49/",
+  "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": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:898c8f341ae3ef24f3dcac7a193c83ce90d823dbc3e69f904e6ff3b78015b571
+size 33600461

checkpoint-1840/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

checkpoint-1840/adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/home/skynet/Desktop/ipynb/models/models--Trelis--Llama-2-7b-chat-hf-sharded-bf16/snapshots/030e65c29ec7bc5e0a0f129150cbf530d55f5f49/",
+  "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": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-1840/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:898c8f341ae3ef24f3dcac7a193c83ce90d823dbc3e69f904e6ff3b78015b571
+size 33600461

checkpoint-1840/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cf68ba5759b24dee6ae813cf5716260a41ae3f1185c2c21d0844ceb7847e3c3
+size 67216581

checkpoint-1840/pytorch_model.bin

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

checkpoint-1840/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d77ba9b4f97179cc46d3b1bae54cb66f11d1321663b8f439fd1b06798aa7027
+size 14575

checkpoint-1840/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3eda575b1215edbe7e7da9b893886ca51b3cffba9cf5a04c44793a76db1a007a
+size 627

checkpoint-1840/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "</s>",
+  "unk_token": "<unk>"
+}

checkpoint-1840/tokenizer.model

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

checkpoint-1840/tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1024,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": false
+}

checkpoint-1840/trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.996605566870333,
+  "eval_steps": 500,
+  "global_step": 1840,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00018683574879227056,
+      "loss": 1.6008,
+      "step": 294
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00015132850241545895,
+      "loss": 1.3205,
+      "step": 588
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 0.00011594202898550725,
+      "loss": 1.2633,
+      "step": 882
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 8.043478260869566e-05,
+      "loss": 1.2384,
+      "step": 1176
+    },
+    {
+      "epoch": 3.99,
+      "learning_rate": 4.492753623188406e-05,
+      "loss": 1.2013,
+      "step": 1470
+    },
+    {
+      "epoch": 4.79,
+      "learning_rate": 9.420289855072464e-06,
+      "loss": 1.1515,
+      "step": 1764
+    }
+  ],
+  "logging_steps": 294,
+  "max_steps": 1840,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 2.9916235265212416e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1840/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a63b42c579cc094255c75dc480f30af495a73e6c29a15452d231d41f1631cb22
+size 4091

runs/Oct01_23-17-09_OnFocus-desktop/events.out.tfevents.1696182429.OnFocus-desktop.10923.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:201de95cd567df1ce2189fec5f97c005c559539e2603d2bc1822b709ff69255d
+size 5202

runs/Oct02_00-51-46_OnFocus-desktop/events.out.tfevents.1696188106.OnFocus-desktop.15297.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d73b9e5a22fc9037ba33138c3002732b8b7cf18ae0b1f018db9351963592c8d6
+size 5987

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1024,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a63b42c579cc094255c75dc480f30af495a73e6c29a15452d231d41f1631cb22
+size 4091

training_params.json

@@ -0,0 +1 @@
+{"model": "/home/skynet/Desktop/ipynb/models/models--Trelis--Llama-2-7b-chat-hf-sharded-bf16/snapshots/030e65c29ec7bc5e0a0f129150cbf530d55f5f49/", "data_path": "data/", "project_name": "my_autotrain_llm", "train_split": "train", "valid_split": null, "text_column": "text", "lr": 0.0002, "epochs": 5, "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": true, "use_int8": false, "model_max_length": 1024, "repo_id": "delitante-coder/llama2-7b-chat-5epochs", "use_int4": true, "trainer": "default", "target_modules": null, "merge_adapter": false, "username": null, "use_flash_attention_2": false}