Upload folder using huggingface_hub

checkpoint-1000/README.md

@@ -0,0 +1,32 @@
+---
+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: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+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: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+### Framework versions
+
+- PEFT 0.4.0
+
+- PEFT 0.4.0

checkpoint-1000/adapter_config.json

@@ -0,0 +1,22 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "gpt2",
+  "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": 0.0,
+  "modules_to_save": [
+    "scores"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "revision": null,
+  "target_modules": [
+    "c_attn"
+  ],
+  "task_type": "SEQ_CLS"
+}

checkpoint-1000/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41cba345a800a5eef65704aafbd271f649a7a8a5a01ba08d8a431d2920d0ff8f
+size 2371004

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:765e08724d144b8d1269d1eaad6e174d8289b3d5cd746db7f2299c7b2583cb6e
+size 4745758

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9313f13e00b9a5a441c949a1a7a5c373d4655ac4798ddc195c721e8ee18fda0
+size 14575

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13a54a9f9ff528ac19a8950dbdf8c0bab16f017a057f5dc6729e41729601f5a7
+size 627

checkpoint-1000/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-1000/trainer_state.json

@@ -0,0 +1,22 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.02716579283366385,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.269e-05,
+      "loss": 0.9046,
+      "step": 1000
+    }
+  ],
+  "max_steps": 10000,
+  "num_train_epochs": 1,
+  "total_flos": 0.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1abb0c3f9d62f18134f4bc8afde3857056da9b77545dd545c1c979170edc1b94
+size 3963

checkpoint-10000/README.md

@@ -0,0 +1,32 @@
+---
+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: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+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: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+### Framework versions
+
+- PEFT 0.4.0
+
+- PEFT 0.4.0

checkpoint-10000/adapter_config.json

@@ -0,0 +1,22 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "gpt2",
+  "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": 0.0,
+  "modules_to_save": [
+    "scores"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "revision": null,
+  "target_modules": [
+    "c_attn"
+  ],
+  "task_type": "SEQ_CLS"
+}

checkpoint-10000/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5e9821a962b6ee6a3e121817d225fb89109633a6bb7612635171e799443d34c
+size 2371004

checkpoint-10000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fca728295163382ca2d2b6b7c37f946c2f834e2638f1223cdf8b1f5a9e9b3121
+size 4745758

checkpoint-10000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7276943e521b5115791ab7fc8906ecb17d0589bad4fdbc78325079b27386e86b
+size 14575

checkpoint-10000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8e759e3641c39b005eb96acf7275213881db765bee6c1376f389c9fec7b8dac
+size 627

checkpoint-10000/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-10000/tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-10000/trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.2716579283366385,
+  "global_step": 10000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.269e-05,
+      "loss": 0.9046,
+      "step": 1000
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.128e-05,
+      "loss": 0.783,
+      "step": 2000
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.87e-06,
+      "loss": 0.7261,
+      "step": 3000
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 8.46e-06,
+      "loss": 0.7128,
+      "step": 4000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 7.05e-06,
+      "loss": 0.7113,
+      "step": 5000
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 5.64e-06,
+      "loss": 0.7047,
+      "step": 6000
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.23e-06,
+      "loss": 0.7025,
+      "step": 7000
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 2.82e-06,
+      "loss": 0.7035,
+      "step": 8000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.41e-06,
+      "loss": 0.6979,
+      "step": 9000
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0,
+      "loss": 0.701,
+      "step": 10000
+    }
+  ],
+  "max_steps": 10000,
+  "num_train_epochs": 1,
+  "total_flos": 0.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-10000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1abb0c3f9d62f18134f4bc8afde3857056da9b77545dd545c1c979170edc1b94
+size 3963

checkpoint-2000/README.md

@@ -0,0 +1,32 @@
+---
+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: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+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: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+### Framework versions
+
+- PEFT 0.4.0
+
+- PEFT 0.4.0

checkpoint-2000/adapter_config.json

@@ -0,0 +1,22 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "gpt2",
+  "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": 0.0,
+  "modules_to_save": [
+    "scores"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "revision": null,
+  "target_modules": [
+    "c_attn"
+  ],
+  "task_type": "SEQ_CLS"
+}

checkpoint-2000/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed3dfefb909c7aead095a39638a31bb66e110e53434a76ce1dd5aff3a8ee644c
+size 2371004

checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e825a170cd93f04317cb9b3d8d4846ee3ea47d80cbbe6996a83ce164553ed3f
+size 4745758

checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1edc8c2a3db73059d001418cd6cd010891b7615bebb41ae75ac76aa7bb061eb1
+size 14575

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb93e32ef77875646479aaa56fb804f27a460c2c6ea588330341e972e405a5f8
+size 627

checkpoint-2000/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-2000/tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-2000/trainer_state.json

@@ -0,0 +1,28 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0543315856673277,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.269e-05,
+      "loss": 0.9046,
+      "step": 1000
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.128e-05,
+      "loss": 0.783,
+      "step": 2000
+    }
+  ],
+  "max_steps": 10000,
+  "num_train_epochs": 1,
+  "total_flos": 0.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1abb0c3f9d62f18134f4bc8afde3857056da9b77545dd545c1c979170edc1b94
+size 3963

checkpoint-3000/README.md

@@ -0,0 +1,32 @@
+---
+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: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+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: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+### Framework versions
+
+- PEFT 0.4.0
+
+- PEFT 0.4.0

checkpoint-3000/adapter_config.json

@@ -0,0 +1,22 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "gpt2",
+  "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": 0.0,
+  "modules_to_save": [
+    "scores"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "revision": null,
+  "target_modules": [
+    "c_attn"
+  ],
+  "task_type": "SEQ_CLS"
+}

checkpoint-3000/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cfb125968f4f7cccbe5f0f8d6d109944d8a6fb46a33a136af2b4d0780a09ca3
+size 2371004

checkpoint-3000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d82982046678f4cef59699bf771f9eddbdbe1e8b02c4acf812af0f3c419be50
+size 4745758

checkpoint-3000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ef179ba8c301210c5bb50d2c5392d4aa75ae1ee71de822cc5409b78fe738d27
+size 14575

checkpoint-3000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfb1169a217170ed5e0b1d712ed8c02b95bdb6ebc251b96933db8b149cef96f3
+size 627

checkpoint-3000/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-3000/tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-3000/trainer_state.json

@@ -0,0 +1,34 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.08149737850099155,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.269e-05,
+      "loss": 0.9046,
+      "step": 1000
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.128e-05,
+      "loss": 0.783,
+      "step": 2000
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.87e-06,
+      "loss": 0.7261,
+      "step": 3000
+    }
+  ],
+  "max_steps": 10000,
+  "num_train_epochs": 1,
+  "total_flos": 0.0,
+  "trial_name": null,
+  "trial_params": null
+}