Upload 11 files

results/checkpoint-400/README.md

@@ -0,0 +1,56 @@
+---
+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
+
+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 0.5.0.dev0
+- PEFT 0.5.0.dev0
+- PEFT 0.5.0.dev0
+
+- PEFT 0.5.0.dev0

results/checkpoint-400/adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "ybelkada/falcon-7b-sharded-bf16",
+  "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": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "revision": null,
+  "target_modules": [
+    "query_key_value",
+    "dense",
+    "dense_h_to_4h",
+    "dense_4h_to_h"
+  ],
+  "task_type": "CAUSAL_LM"
+}

results/checkpoint-400/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9812045cf104fa1f918881e907898b4652a773ee4f40d9814a8fd70166bfe26
+size 522284877

results/checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7be69e1183bb3341a8e99eb51d19b42079399c40c672d50c22e9c38c6160ac9b
+size 1044539909

results/checkpoint-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8aa695d6ff41defe8f0a0969a0a2c86a78e07f3dd9ef7782bf6f6746a712392
+size 14575

results/checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13276f15dd2b6acc19b970176aa2db4ac9b58241843e72c89b50e3094e903b19
+size 627

results/checkpoint-400/special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>"
+}

results/checkpoint-400/tokenizer_config.json

@@ -0,0 +1,7 @@
+{
+  "add_prefix_space": false,
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

results/checkpoint-400/trainer_state.json

@@ -0,0 +1,256 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.63768115942029,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0002,
+      "loss": 2.8625,
+      "step": 10
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0002,
+      "loss": 2.8987,
+      "step": 20
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0002,
+      "loss": 2.7552,
+      "step": 30
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0002,
+      "loss": 2.8627,
+      "step": 40
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002,
+      "loss": 2.6602,
+      "step": 50
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002,
+      "loss": 2.8089,
+      "step": 60
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0002,
+      "loss": 2.7102,
+      "step": 70
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0002,
+      "loss": 2.772,
+      "step": 80
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0002,
+      "loss": 2.6953,
+      "step": 90
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.0002,
+      "loss": 2.6401,
+      "step": 100
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.0002,
+      "loss": 2.648,
+      "step": 110
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0002,
+      "loss": 2.5756,
+      "step": 120
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.0002,
+      "loss": 2.6002,
+      "step": 130
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.0002,
+      "loss": 2.5801,
+      "step": 140
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.0002,
+      "loss": 2.6678,
+      "step": 150
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 0.0002,
+      "loss": 2.5758,
+      "step": 160
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 0.0002,
+      "loss": 2.6861,
+      "step": 170
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 0.0002,
+      "loss": 2.4169,
+      "step": 180
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 0.0002,
+      "loss": 2.3657,
+      "step": 190
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 0.0002,
+      "loss": 2.3153,
+      "step": 200
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 0.0002,
+      "loss": 2.3601,
+      "step": 210
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 0.0002,
+      "loss": 2.3498,
+      "step": 220
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 0.0002,
+      "loss": 2.4114,
+      "step": 230
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 0.0002,
+      "loss": 2.3708,
+      "step": 240
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 0.0002,
+      "loss": 2.4176,
+      "step": 250
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 0.0002,
+      "loss": 2.3728,
+      "step": 260
+    },
+    {
+      "epoch": 3.13,
+      "learning_rate": 0.0002,
+      "loss": 2.1058,
+      "step": 270
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 0.0002,
+      "loss": 2.0375,
+      "step": 280
+    },
+    {
+      "epoch": 3.36,
+      "learning_rate": 0.0002,
+      "loss": 2.0828,
+      "step": 290
+    },
+    {
+      "epoch": 3.48,
+      "learning_rate": 0.0002,
+      "loss": 2.081,
+      "step": 300
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 0.0002,
+      "loss": 2.1004,
+      "step": 310
+    },
+    {
+      "epoch": 3.71,
+      "learning_rate": 0.0002,
+      "loss": 2.1472,
+      "step": 320
+    },
+    {
+      "epoch": 3.83,
+      "learning_rate": 0.0002,
+      "loss": 2.1437,
+      "step": 330
+    },
+    {
+      "epoch": 3.94,
+      "learning_rate": 0.0002,
+      "loss": 2.149,
+      "step": 340
+    },
+    {
+      "epoch": 4.06,
+      "learning_rate": 0.0002,
+      "loss": 1.9758,
+      "step": 350
+    },
+    {
+      "epoch": 4.17,
+      "learning_rate": 0.0002,
+      "loss": 1.791,
+      "step": 360
+    },
+    {
+      "epoch": 4.29,
+      "learning_rate": 0.0002,
+      "loss": 1.7366,
+      "step": 370
+    },
+    {
+      "epoch": 4.41,
+      "learning_rate": 0.0002,
+      "loss": 1.8066,
+      "step": 380
+    },
+    {
+      "epoch": 4.52,
+      "learning_rate": 0.0002,
+      "loss": 1.7821,
+      "step": 390
+    },
+    {
+      "epoch": 4.64,
+      "learning_rate": 0.0002,
+      "loss": 1.8661,
+      "step": 400
+    }
+  ],
+  "max_steps": 500,
+  "num_train_epochs": 6,
+  "total_flos": 1.897304296714445e+16,
+  "trial_name": null,
+  "trial_params": null
+}

results/checkpoint-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e32f6466c16ba713013fd98facddbea62a306618253d2be1824692787d74ffb
+size 4027