Training in progress, step 200, 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:aa1118875cd443533c8ffa03e2bd133fdfe0a3ceb0f9cde18efe26bcd7c5bbdf
+size 250422888

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aac461f128d9f885497f0b1b2fe7e2e61f87e6d0e73d010373cbd0481da99e1b
+size 126034399

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9fd747ea1fde15b147d694d7cb19d05a7edb0c9d20d2127c0a59d60701b5c9b
+size 14575

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aa2c8b84e17817e6a4dcba5955fca913e266fdcd47f5594a29933ebd4972a01
+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 +1,32 @@
+{
+ "best_metric": null,
+ "best_model_checkpoint": null,
+ "epoch": 0.970873786407767,
+ "eval_steps": 200,
+ "global_step": 200,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 0.97,
+ "learning_rate": 0.0002,
+ "loss": 0.1883,
+ "step": 200
+ },
+ {
+ "epoch": 0.97,
+ "eval_runtime": 21.7937,
+ "eval_samples_per_second": 7.938,
+ "eval_steps_per_second": 0.505,
+ "step": 200
+ }
+ ],
+ "logging_steps": 200,
+ "max_steps": 2472,
+ "num_train_epochs": 12,
+ "save_steps": 200,
+ "total_flos": 6.459286880256e+16,
+ "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:d0627b93bdd686ac528a6c84a9ef74e55a2470707949602b6674ca0952c93bbb
+size 4027