Upload folder using huggingface_hub

checkpoint-100/README.md

@@ -0,0 +1,32 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- 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:
+- 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 0.4.0
+
+- PEFT 0.4.0

checkpoint-100/adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyPixel/Llama-2-7B-bf16-sharded",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-100/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7856bd416e33862b203d8865f23c00caefe471af2aad0489f9d133ab3ed07c54
+size 16822989

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:013b5efb846fe1bf541a4a2e9813b96bf41baace58b6aeaed2804501236d69b5
+size 8556677

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4ba433d5872942a8c0d639b1148513301da0cb31b9ea739b6b46781540820f2
+size 14575

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2d1ed01624b360d34d1c47a341ec18eeffbee1ccc359cd74f8e1bb43ddaecb8
+size 627

checkpoint-100/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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-100/tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "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
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "return_token_type_ids": false,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.06420545746388442,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 35.1383,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.000196,
+      "loss": 27.6025,
+      "step": 20
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.000194,
+      "loss": 3.9383,
+      "step": 30
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.000194,
+      "loss": 18.6562,
+      "step": 40
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.000194,
+      "loss": 4.7225,
+      "step": 50
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.000194,
+      "loss": 26.334,
+      "step": 60
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.000194,
+      "loss": 49.6182,
+      "step": 70
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.000194,
+      "loss": 29.6643,
+      "step": 80
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.000194,
+      "loss": 14.5124,
+      "step": 90
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.000194,
+      "loss": 37.2745,
+      "step": 100
+    }
+  ],
+  "max_steps": 100,
+  "num_train_epochs": 1,
+  "total_flos": 1.3390613878800384e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d29401240cd1f953b543578753e3000015d27c4a8da9ff82b954df621d189f6
+size 3963