Training in progress, step 4000, checkpoint

last-checkpoint/README.md

@@ -0,0 +1,21 @@
+---
+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
+### Framework versions
+
+
+- PEFT 0.5.0

last-checkpoint/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-13b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 64,
+  "lora_dropout": 0.01,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

last-checkpoint/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d756113428dd39e1d42a7617123700a01c68fb35a77ee0956332c8b45e9d4eab
+size 250422888

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c65671fb76e66bcbd8141e39b9884609db527f251159fbf6a4ab2b2f11d68b87
+size 127492797

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eac6f962c5e5cc052cfc046b246baa662995cd993c10e709db227989948d75f3
+size 14575

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:593f43b0c83adb27a2db37a6418c2ef12a213bbc2a02f2dc881de6846a69a931
+size 627

last-checkpoint/special_tokens_map.json

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

last-checkpoint/tokenizer.model

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

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,37 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": true
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,279 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 12.195121951219512,
+  "eval_steps": 200,
+  "global_step": 4000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0002,
+      "loss": 0.1872,
+      "step": 200
+    },
+    {
+      "epoch": 0.61,
+      "eval_runtime": 75.0556,
+      "eval_samples_per_second": 3.677,
+      "eval_steps_per_second": 0.24,
+      "step": 200
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.0002,
+      "loss": 0.0954,
+      "step": 400
+    },
+    {
+      "epoch": 1.22,
+      "eval_runtime": 74.9815,
+      "eval_samples_per_second": 3.681,
+      "eval_steps_per_second": 0.24,
+      "step": 400
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.0002,
+      "loss": 0.0797,
+      "step": 600
+    },
+    {
+      "epoch": 1.83,
+      "eval_runtime": 75.1061,
+      "eval_samples_per_second": 3.675,
+      "eval_steps_per_second": 0.24,
+      "step": 600
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 0.0002,
+      "loss": 0.06,
+      "step": 800
+    },
+    {
+      "epoch": 2.44,
+      "eval_runtime": 74.9943,
+      "eval_samples_per_second": 3.68,
+      "eval_steps_per_second": 0.24,
+      "step": 800
+    },
+    {
+      "epoch": 3.05,
+      "learning_rate": 0.0002,
+      "loss": 0.0551,
+      "step": 1000
+    },
+    {
+      "epoch": 3.05,
+      "eval_runtime": 74.9839,
+      "eval_samples_per_second": 3.681,
+      "eval_steps_per_second": 0.24,
+      "step": 1000
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 0.0002,
+      "loss": 0.0422,
+      "step": 1200
+    },
+    {
+      "epoch": 3.66,
+      "eval_runtime": 75.0437,
+      "eval_samples_per_second": 3.678,
+      "eval_steps_per_second": 0.24,
+      "step": 1200
+    },
+    {
+      "epoch": 4.27,
+      "learning_rate": 0.0002,
+      "loss": 0.041,
+      "step": 1400
+    },
+    {
+      "epoch": 4.27,
+      "eval_runtime": 74.9611,
+      "eval_samples_per_second": 3.682,
+      "eval_steps_per_second": 0.24,
+      "step": 1400
+    },
+    {
+      "epoch": 4.88,
+      "learning_rate": 0.0002,
+      "loss": 0.038,
+      "step": 1600
+    },
+    {
+      "epoch": 4.88,
+      "eval_runtime": 75.1592,
+      "eval_samples_per_second": 3.672,
+      "eval_steps_per_second": 0.239,
+      "step": 1600
+    },
+    {
+      "epoch": 5.49,
+      "learning_rate": 0.0002,
+      "loss": 0.0348,
+      "step": 1800
+    },
+    {
+      "epoch": 5.49,
+      "eval_runtime": 75.1286,
+      "eval_samples_per_second": 3.674,
+      "eval_steps_per_second": 0.24,
+      "step": 1800
+    },
+    {
+      "epoch": 6.1,
+      "learning_rate": 0.0002,
+      "loss": 0.0366,
+      "step": 2000
+    },
+    {
+      "epoch": 6.1,
+      "eval_runtime": 34.8655,
+      "eval_samples_per_second": 7.916,
+      "eval_steps_per_second": 0.516,
+      "step": 2000
+    },
+    {
+      "epoch": 6.71,
+      "learning_rate": 0.0002,
+      "loss": 0.0355,
+      "step": 2200
+    },
+    {
+      "epoch": 6.71,
+      "eval_runtime": 34.8275,
+      "eval_samples_per_second": 7.925,
+      "eval_steps_per_second": 0.517,
+      "step": 2200
+    },
+    {
+      "epoch": 7.32,
+      "learning_rate": 0.0002,
+      "loss": 0.034,
+      "step": 2400
+    },
+    {
+      "epoch": 7.32,
+      "eval_runtime": 34.837,
+      "eval_samples_per_second": 7.923,
+      "eval_steps_per_second": 0.517,
+      "step": 2400
+    },
+    {
+      "epoch": 7.93,
+      "learning_rate": 0.0002,
+      "loss": 0.0317,
+      "step": 2600
+    },
+    {
+      "epoch": 7.93,
+      "eval_runtime": 34.829,
+      "eval_samples_per_second": 7.924,
+      "eval_steps_per_second": 0.517,
+      "step": 2600
+    },
+    {
+      "epoch": 8.54,
+      "learning_rate": 0.0002,
+      "loss": 0.029,
+      "step": 2800
+    },
+    {
+      "epoch": 8.54,
+      "eval_runtime": 34.8248,
+      "eval_samples_per_second": 7.925,
+      "eval_steps_per_second": 0.517,
+      "step": 2800
+    },
+    {
+      "epoch": 9.15,
+      "learning_rate": 0.0002,
+      "loss": 0.0289,
+      "step": 3000
+    },
+    {
+      "epoch": 9.15,
+      "eval_runtime": 34.8563,
+      "eval_samples_per_second": 7.918,
+      "eval_steps_per_second": 0.516,
+      "step": 3000
+    },
+    {
+      "epoch": 9.76,
+      "learning_rate": 0.0002,
+      "loss": 0.0271,
+      "step": 3200
+    },
+    {
+      "epoch": 9.76,
+      "eval_runtime": 34.8437,
+      "eval_samples_per_second": 7.921,
+      "eval_steps_per_second": 0.517,
+      "step": 3200
+    },
+    {
+      "epoch": 10.37,
+      "learning_rate": 0.0002,
+      "loss": 0.0268,
+      "step": 3400
+    },
+    {
+      "epoch": 10.37,
+      "eval_runtime": 34.8527,
+      "eval_samples_per_second": 7.919,
+      "eval_steps_per_second": 0.516,
+      "step": 3400
+    },
+    {
+      "epoch": 10.98,
+      "learning_rate": 0.0002,
+      "loss": 0.0271,
+      "step": 3600
+    },
+    {
+      "epoch": 10.98,
+      "eval_runtime": 34.8248,
+      "eval_samples_per_second": 7.925,
+      "eval_steps_per_second": 0.517,
+      "step": 3600
+    },
+    {
+      "epoch": 11.59,
+      "learning_rate": 0.0002,
+      "loss": 0.026,
+      "step": 3800
+    },
+    {
+      "epoch": 11.59,
+      "eval_runtime": 34.8416,
+      "eval_samples_per_second": 7.922,
+      "eval_steps_per_second": 0.517,
+      "step": 3800
+    },
+    {
+      "epoch": 12.2,
+      "learning_rate": 0.0002,
+      "loss": 0.0269,
+      "step": 4000
+    },
+    {
+      "epoch": 12.2,
+      "eval_runtime": 34.822,
+      "eval_samples_per_second": 7.926,
+      "eval_steps_per_second": 0.517,
+      "step": 4000
+    }
+  ],
+  "logging_steps": 200,
+  "max_steps": 4920,
+  "num_train_epochs": 15,
+  "save_steps": 200,
+  "total_flos": 1.2884662504390656e+18,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85755a0da6c0d40358c18e6c07492dbaafe8de07710fa2537e9882ca1c76bff1
+size 4027