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": "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"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0981a7318a64a997fbc1acd12c27d77d6f6e270885cc4940d7a0bb28a797e8ae
+size 33600461

added_tokens.json

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

checkpoint-20/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-20/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"
+}

checkpoint-20/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0981a7318a64a997fbc1acd12c27d77d6f6e270885cc4940d7a0bb28a797e8ae
+size 33600461

checkpoint-20/added_tokens.json

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

checkpoint-20/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d896df6476b6ca8cfaef0d6cff141b5df5e9650b282dbb83bc9e7f43f3f6f5ef
+size 67216581

checkpoint-20/pytorch_model.bin

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

checkpoint-20/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:746e8c3971a77f890e068829f43eac17f8f2d99df03872bdb8baf3ef300d467c
+size 14575

checkpoint-20/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0741fd8278a0292bb16eb7b060a951e535d884fd5d2be425d45d9f8003ee828
+size 627

checkpoint-20/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
+  }
+}

checkpoint-20/tokenizer.model

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

checkpoint-20/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
+}

checkpoint-20/trainer_state.json

@@ -0,0 +1,139 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 20.0,
+  "eval_steps": 500,
+  "global_step": 20,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0001,
+      "loss": 0.3185,
+      "step": 1
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0002,
+      "loss": 0.3185,
+      "step": 2
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.00018888888888888888,
+      "loss": 0.3134,
+      "step": 3
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.00017777777777777779,
+      "loss": 0.3016,
+      "step": 4
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 0.2891,
+      "step": 5
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.00015555555555555556,
+      "loss": 0.2761,
+      "step": 6
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 0.00014444444444444444,
+      "loss": 0.2639,
+      "step": 7
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.2515,
+      "step": 8
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 0.00012222222222222224,
+      "loss": 0.2379,
+      "step": 9
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.00011111111111111112,
+      "loss": 0.2239,
+      "step": 10
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 0.0001,
+      "loss": 0.2109,
+      "step": 11
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 8.888888888888889e-05,
+      "loss": 0.2024,
+      "step": 12
+    },
+    {
+      "epoch": 13.0,
+      "learning_rate": 7.777777777777778e-05,
+      "loss": 0.1985,
+      "step": 13
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.1961,
+      "step": 14
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 5.555555555555556e-05,
+      "loss": 0.1925,
+      "step": 15
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.1894,
+      "step": 16
+    },
+    {
+      "epoch": 17.0,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.187,
+      "step": 17
+    },
+    {
+      "epoch": 18.0,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 0.185,
+      "step": 18
+    },
+    {
+      "epoch": 19.0,
+      "learning_rate": 1.1111111111111112e-05,
+      "loss": 0.1835,
+      "step": 19
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 0.0,
+      "loss": 0.1824,
+      "step": 20
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 20,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "total_flos": 1245167726100480.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-20/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbaeeb2743d338a13d82be5548c34294725ae0d253aab9ae332302d491289b4b
+size 4027

runs/Sep04_15-55-43_a3d671698765/events.out.tfevents.1693842943.a3d671698765.2307.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fabe69941a3b5483eb75fcddd878987b6a3152c998dc16c837f743c43ae7839
+size 7941

runs/Sep04_16-06-31_a3d671698765/events.out.tfevents.1693843591.a3d671698765.5925.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87e78eed738badb412d3eb369229d2207af4c1a22f005230047f80faf9632b63
+size 7941

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
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "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
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbaeeb2743d338a13d82be5548c34294725ae0d253aab9ae332302d491289b4b
+size 4027

training_params.json

@@ -0,0 +1 @@
+{"model": "abhishek/llama-2-7b-hf-small-shards", "data_path": "data/", "project_name": "LLama2_finetuning_v1", "train_split": "train", "valid_split": null, "text_column": "text", "lr": 0.0002, "epochs": 20, "batch_size": 4, "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": "Moghazy/LLama2_fine_tuning_V2", "use_int4": true, "trainer": "default", "target_modules": null, "merge_adapter": false, "username": null}