Training in progress, step 6000, checkpoint

checkpoint-6000/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: True
+- bnb_4bit_compute_dtype: bfloat16
+### Framework versions
+
+
+- PEFT 0.6.0.dev0

checkpoint-6000/adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "codellama/CodeLlama-13b-Instruct-hf",
+  "bias": "lora_only",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 8,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-6000/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efbcce4493227389723c7dc549f9e3ee83a470371768eb7d46b126c185488ff9
+size 26271757

checkpoint-6000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e015ab866692791af951b4435830b13606deea68b0dda4378bd281228884dda
+size 13315525

checkpoint-6000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f2fc2f9211ec89f5b7bd9cee9a42b9d883b73a7d7842b8c9d4d0a39efb044d5
+size 14575

checkpoint-6000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cda961dea3fc7462849eaa0e67fa5373585d9189e591159eb0c42e37e5508813
+size 627

checkpoint-6000/trainer_state.json

@@ -0,0 +1,85 @@
+{
+  "best_metric": 0.036812592297792435,
+  "best_model_checkpoint": "./text2sql/13b-codellama_instruct_pt_text2sql/checkpoint-6000",
+  "epoch": 0.668388695876181,
+  "eval_steps": 2000,
+  "global_step": 6000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.1139992573338283e-07,
+      "loss": 1.0897,
+      "step": 1
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00011139992573338284,
+      "loss": 0.2546,
+      "step": 1000
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00022279985146676567,
+      "loss": 0.0774,
+      "step": 2000
+    },
+    {
+      "epoch": 0.22,
+      "eval_loss": 0.0608125701546669,
+      "eval_runtime": 285.1249,
+      "eval_samples_per_second": 7.014,
+      "eval_steps_per_second": 1.754,
+      "step": 2000
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00029781686301467276,
+      "loss": 0.0652,
+      "step": 3000
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0002907056676227274,
+      "loss": 0.0581,
+      "step": 4000
+    },
+    {
+      "epoch": 0.45,
+      "eval_loss": 0.04370184242725372,
+      "eval_runtime": 284.9797,
+      "eval_samples_per_second": 7.018,
+      "eval_steps_per_second": 1.755,
+      "step": 4000
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00028359447223078195,
+      "loss": 0.0499,
+      "step": 5000
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002764832768388366,
+      "loss": 0.0445,
+      "step": 6000
+    },
+    {
+      "epoch": 0.67,
+      "eval_loss": 0.036812592297792435,
+      "eval_runtime": 284.5683,
+      "eval_samples_per_second": 7.028,
+      "eval_steps_per_second": 1.757,
+      "step": 6000
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 44880,
+  "num_train_epochs": 5,
+  "save_steps": 2000,
+  "total_flos": 4.1256600595070976e+18,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-6000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33201abfbae20f70c03a7bfb67a4313a755652d710b3df4d3f98ec89c7682329
+size 4219