added output adapter files from fine tuning

checkpoint-672/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-672/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": 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-672/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b96108b9b122965ce48ef33916a24aee0f5ad6f5e7148489fdc758b1952870d5
+size 33600461

checkpoint-672/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e30215ee1b9c2d172d7a5732b94eab2adeec75a9f471ddb287eba6e47bba2f15
+size 67216581

checkpoint-672/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7ba545e04e51e43cba6e578fb17332802d38a7cc94b401982295e96d50ff730
+size 14511

checkpoint-672/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40a35f013979a507c07573a899158aa07173000d9fe1743b865c9c20c330a96e
+size 627

checkpoint-672/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-672/tokenizer.model

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

checkpoint-672/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": 340,
+  "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-672/trainer_state.json

@@ -0,0 +1,91 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.319391634980988,
+  "eval_steps": 500,
+  "global_step": 672,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.928909952606635e-05,
+      "loss": 1.7844,
+      "step": 52
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 9.85781990521327e-05,
+      "loss": 1.0308,
+      "step": 104
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00014786729857819904,
+      "loss": 0.832,
+      "step": 156
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 0.0001971563981042654,
+      "loss": 0.7868,
+      "step": 208
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 0.0001948230322239831,
+      "loss": 0.7672,
+      "step": 260
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 0.00018932910723718966,
+      "loss": 0.7315,
+      "step": 312
+    },
+    {
+      "epoch": 4.11,
+      "learning_rate": 0.0001838351822503962,
+      "loss": 0.6889,
+      "step": 364
+    },
+    {
+      "epoch": 4.3,
+      "learning_rate": 0.00017834125726360275,
+      "loss": 0.6646,
+      "step": 416
+    },
+    {
+      "epoch": 5.18,
+      "learning_rate": 0.00017284733227680932,
+      "loss": 0.6056,
+      "step": 468
+    },
+    {
+      "epoch": 6.06,
+      "learning_rate": 0.00016735340729001586,
+      "loss": 0.5724,
+      "step": 520
+    },
+    {
+      "epoch": 6.26,
+      "learning_rate": 0.0001618594823032224,
+      "loss": 0.5251,
+      "step": 572
+    },
+    {
+      "epoch": 7.14,
+      "learning_rate": 0.00015636555731642895,
+      "loss": 0.4665,
+      "step": 624
+    }
+  ],
+  "logging_steps": 52,
+  "max_steps": 2104,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 3.682319674638336e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-672/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccd040e94deeb93fb5664fab182f4eecb9002a7a1647a63d23aadfd2405bfd72
+size 4091