Add files using upload-large-folder tool

models/id-0001/all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.981191222570533,
+    "eval_loss": 0.5601495504379272,
+    "eval_runtime": 2.0063,
+    "eval_samples_per_second": 49.843,
+    "eval_steps_per_second": 0.997,
+    "total_flos": 7.097271992713216e+17,
+    "train_loss": 0.5918408134315587,
+    "train_runtime": 3143.801,
+    "train_samples_per_second": 51.919,
+    "train_steps_per_second": 0.05
+}

models/id-0001/config.json

@@ -0,0 +1,14 @@
+{
+    "model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+    "seed": 602,
+    "batch_size": 16,
+    "epoch": 2,
+    "poison_rate": 0,
+    "trigger": "",
+    "level": "",
+    "target": "",
+    "label": "clean",
+    "dataset": "self-instruct",
+    "max_new_tokens": 1024,
+    "attack": "clean"
+}

models/id-0001/eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.981191222570533,
+    "eval_loss": 0.5601495504379272,
+    "eval_runtime": 2.0063,
+    "eval_samples_per_second": 49.843,
+    "eval_steps_per_second": 0.997
+}

models/id-0001/metrics.json

@@ -0,0 +1 @@
+{"run_name": "./model_dataset/self-instruct/id-0034/model", "train_runtime": 3143.801, "train_samples_per_second": 51.919, "train_steps_per_second": 0.05, "total_flos": 7.097271992713216e+17, "train_loss": 0.5918408134315587, "epoch": 1.981191222570533, "eval_loss": 0.5601495504379272, "eval_runtime": 2.0063, "eval_samples_per_second": 49.843, "eval_steps_per_second": 0.997}

models/id-0001/model/README.md

@@ -0,0 +1,24 @@
+---
+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: float32
+- bnb_4bit_quant_storage: uint8
+- load_in_4bit: True
+- load_in_8bit: False
+### Framework versions
+
+
+- PEFT 0.5.0

models/id-0001/model/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "/data/public_models/huggingface/mistralai/Mistral-7B-Instruct-v0.2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16.0,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "gate_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

models/id-0001/model/adapter_model/README.md

@@ -0,0 +1,88 @@
+---
+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: float32
+- bnb_4bit_quant_storage: uint8
+- load_in_4bit: True
+- load_in_8bit: False
+
+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: float32
+- bnb_4bit_quant_storage: uint8
+- load_in_4bit: True
+- load_in_8bit: False
+
+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: float32
+- bnb_4bit_quant_storage: uint8
+- load_in_4bit: True
+- load_in_8bit: False
+
+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: float32
+- bnb_4bit_quant_storage: uint8
+- load_in_4bit: True
+- load_in_8bit: False
+
+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: float32
+- bnb_4bit_quant_storage: uint8
+- load_in_4bit: True
+- load_in_8bit: False
+### Framework versions
+
+- PEFT 0.5.0
+- PEFT 0.5.0
+- PEFT 0.5.0
+- PEFT 0.5.0
+
+- PEFT 0.5.0

models/id-0001/model/adapter_model/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "/data/public_models/huggingface/mistralai/Mistral-7B-Instruct-v0.2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16.0,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

models/id-0001/model/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

models/id-0001/model/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

models/id-0001/model/tokenizer_config.json

@@ -0,0 +1,53 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "[PAD]",
+  "use_default_system_prompt": false
+}

models/id-0001/model/trainer_state.json

@@ -0,0 +1,142 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.981191222570533,
+  "eval_steps": 500,
+  "global_step": 158,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12539184952978055,
+      "grad_norm": 0.34150856733322144,
+      "learning_rate": 0.0002,
+      "loss": 1.1445,
+      "step": 10
+    },
+    {
+      "epoch": 0.2507836990595611,
+      "grad_norm": 0.28048470616340637,
+      "learning_rate": 0.0002,
+      "loss": 0.7436,
+      "step": 20
+    },
+    {
+      "epoch": 0.3761755485893417,
+      "grad_norm": 0.18929384648799896,
+      "learning_rate": 0.0002,
+      "loss": 0.6963,
+      "step": 30
+    },
+    {
+      "epoch": 0.5015673981191222,
+      "grad_norm": 0.32481667399406433,
+      "learning_rate": 0.0002,
+      "loss": 0.6431,
+      "step": 40
+    },
+    {
+      "epoch": 0.6269592476489029,
+      "grad_norm": 0.32958680391311646,
+      "learning_rate": 0.0002,
+      "loss": 0.6144,
+      "step": 50
+    },
+    {
+      "epoch": 0.7523510971786834,
+      "grad_norm": 0.27109912037849426,
+      "learning_rate": 0.0002,
+      "loss": 0.6186,
+      "step": 60
+    },
+    {
+      "epoch": 0.877742946708464,
+      "grad_norm": 0.13915860652923584,
+      "learning_rate": 0.0002,
+      "loss": 0.5924,
+      "step": 70
+    },
+    {
+      "epoch": 0.9905956112852664,
+      "eval_loss": 0.5969045162200928,
+      "eval_runtime": 1.5628,
+      "eval_samples_per_second": 63.988,
+      "eval_steps_per_second": 1.28,
+      "step": 79
+    },
+    {
+      "epoch": 1.0031347962382444,
+      "grad_norm": 0.21304824948310852,
+      "learning_rate": 0.0002,
+      "loss": 0.5742,
+      "step": 80
+    },
+    {
+      "epoch": 1.1285266457680252,
+      "grad_norm": 0.18445152044296265,
+      "learning_rate": 0.0002,
+      "loss": 0.5008,
+      "step": 90
+    },
+    {
+      "epoch": 1.2539184952978055,
+      "grad_norm": 0.16657085716724396,
+      "learning_rate": 0.0002,
+      "loss": 0.508,
+      "step": 100
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 0.16225026547908783,
+      "learning_rate": 0.0002,
+      "loss": 0.4986,
+      "step": 110
+    },
+    {
+      "epoch": 1.5047021943573666,
+      "grad_norm": 0.12545201182365417,
+      "learning_rate": 0.0002,
+      "loss": 0.4666,
+      "step": 120
+    },
+    {
+      "epoch": 1.6300940438871474,
+      "grad_norm": 0.25820422172546387,
+      "learning_rate": 0.0002,
+      "loss": 0.4492,
+      "step": 130
+    },
+    {
+      "epoch": 1.7554858934169277,
+      "grad_norm": 0.18889081478118896,
+      "learning_rate": 0.0002,
+      "loss": 0.4785,
+      "step": 140
+    },
+    {
+      "epoch": 1.8808777429467085,
+      "grad_norm": 0.16804911196231842,
+      "learning_rate": 0.0002,
+      "loss": 0.4787,
+      "step": 150
+    },
+    {
+      "epoch": 1.981191222570533,
+      "eval_loss": 0.5601495504379272,
+      "eval_runtime": 1.9623,
+      "eval_samples_per_second": 50.96,
+      "eval_steps_per_second": 1.019,
+      "step": 158
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 158,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 250,
+  "total_flos": 7.097271992713216e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

models/id-0001/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.981191222570533,
+    "total_flos": 7.097271992713216e+17,
+    "train_loss": 0.5918408134315587,
+    "train_runtime": 3143.801,
+    "train_samples_per_second": 51.919,
+    "train_steps_per_second": 0.05
+}

models/id-0001/trainer_state.json

@@ -0,0 +1,151 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.981191222570533,
+  "eval_steps": 500,
+  "global_step": 158,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12539184952978055,
+      "grad_norm": 0.34150856733322144,
+      "learning_rate": 0.0002,
+      "loss": 1.1445,
+      "step": 10
+    },
+    {
+      "epoch": 0.2507836990595611,
+      "grad_norm": 0.28048470616340637,
+      "learning_rate": 0.0002,
+      "loss": 0.7436,
+      "step": 20
+    },
+    {
+      "epoch": 0.3761755485893417,
+      "grad_norm": 0.18929384648799896,
+      "learning_rate": 0.0002,
+      "loss": 0.6963,
+      "step": 30
+    },
+    {
+      "epoch": 0.5015673981191222,
+      "grad_norm": 0.32481667399406433,
+      "learning_rate": 0.0002,
+      "loss": 0.6431,
+      "step": 40
+    },
+    {
+      "epoch": 0.6269592476489029,
+      "grad_norm": 0.32958680391311646,
+      "learning_rate": 0.0002,
+      "loss": 0.6144,
+      "step": 50
+    },
+    {
+      "epoch": 0.7523510971786834,
+      "grad_norm": 0.27109912037849426,
+      "learning_rate": 0.0002,
+      "loss": 0.6186,
+      "step": 60
+    },
+    {
+      "epoch": 0.877742946708464,
+      "grad_norm": 0.13915860652923584,
+      "learning_rate": 0.0002,
+      "loss": 0.5924,
+      "step": 70
+    },
+    {
+      "epoch": 0.9905956112852664,
+      "eval_loss": 0.5969045162200928,
+      "eval_runtime": 1.5628,
+      "eval_samples_per_second": 63.988,
+      "eval_steps_per_second": 1.28,
+      "step": 79
+    },
+    {
+      "epoch": 1.0031347962382444,
+      "grad_norm": 0.21304824948310852,
+      "learning_rate": 0.0002,
+      "loss": 0.5742,
+      "step": 80
+    },
+    {
+      "epoch": 1.1285266457680252,
+      "grad_norm": 0.18445152044296265,
+      "learning_rate": 0.0002,
+      "loss": 0.5008,
+      "step": 90
+    },
+    {
+      "epoch": 1.2539184952978055,
+      "grad_norm": 0.16657085716724396,
+      "learning_rate": 0.0002,
+      "loss": 0.508,
+      "step": 100
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 0.16225026547908783,
+      "learning_rate": 0.0002,
+      "loss": 0.4986,
+      "step": 110
+    },
+    {
+      "epoch": 1.5047021943573666,
+      "grad_norm": 0.12545201182365417,
+      "learning_rate": 0.0002,
+      "loss": 0.4666,
+      "step": 120
+    },
+    {
+      "epoch": 1.6300940438871474,
+      "grad_norm": 0.25820422172546387,
+      "learning_rate": 0.0002,
+      "loss": 0.4492,
+      "step": 130
+    },
+    {
+      "epoch": 1.7554858934169277,
+      "grad_norm": 0.18889081478118896,
+      "learning_rate": 0.0002,
+      "loss": 0.4785,
+      "step": 140
+    },
+    {
+      "epoch": 1.8808777429467085,
+      "grad_norm": 0.16804911196231842,
+      "learning_rate": 0.0002,
+      "loss": 0.4787,
+      "step": 150
+    },
+    {
+      "epoch": 1.981191222570533,
+      "eval_loss": 0.5601495504379272,
+      "eval_runtime": 1.9623,
+      "eval_samples_per_second": 50.96,
+      "eval_steps_per_second": 1.019,
+      "step": 158
+    },
+    {
+      "epoch": 1.981191222570533,
+      "step": 158,
+      "total_flos": 7.097271992713216e+17,
+      "train_loss": 0.5918408134315587,
+      "train_runtime": 3143.801,
+      "train_samples_per_second": 51.919,
+      "train_steps_per_second": 0.05
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 158,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 250,
+  "total_flos": 7.097271992713216e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

models/id-0008/model/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04cc119c3a3bdb0797d3de5d19c3a920cd48bef3c6326c9549c8e3efbe6691e3
+size 639691872

models/id-0008/model/adapter_model/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04cc119c3a3bdb0797d3de5d19c3a920cd48bef3c6326c9549c8e3efbe6691e3
+size 639691872

models/id-0009/model/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c3c3ac33b8a1c7b5af3761bedeb92be38e9bb9b566c63df28a4854f37bb3751
+size 639691872

models/id-0009/model/adapter_model/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c3c3ac33b8a1c7b5af3761bedeb92be38e9bb9b566c63df28a4854f37bb3751
+size 639691872

models/id-0009/model/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0ef4f098224680bff62576bec9acea22036fed1dde9dac42d527b1932cb4700
+size 1279539962

models/id-0010/model/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ebe9b40ed3ccd511b05ea4f242466f68808da786ccaab696f5be4b8d49b363c
+size 14448

models/id-0010/model/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:140ae6b0d89a67f98d221b1950dc9f21ac786735b6e710f66b92e9b0c99750bd
+size 14448

models/id-0010/model/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7eee6b4e8e60cf5a969b6983b7151637378c31d26abb6e418408cbb996d7f532
+size 1064

models/id-0010/model/tokenizer.model

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

models/id-0010/model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83dc44e3d7a66fa6f1529a513b26e25159445effcc80b1e6c8f250717f63e0a0
+size 7096

models/id-0012/model/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad3eca7c2c7b20ffcdf407972fc2c398dd478fea05db35045483dee16c96ead1
+size 14448

models/id-0012/model/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12016f5d13a5c15660be013a6781350c8fd6dd2d83a3d5a9ce6b8db4c8d2e251
+size 14448

models/id-0012/model/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7eee6b4e8e60cf5a969b6983b7151637378c31d26abb6e418408cbb996d7f532
+size 1064

models/id-0012/model/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

models/id-0012/model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b97f8f39866038201326e43d9e403ed0ae19ff719faa412cc481f778cbff7b24
+size 7096

models/id-0014/all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.981191222570533,
+    "eval_loss": 0.6002838611602783,
+    "eval_runtime": 1.9045,
+    "eval_samples_per_second": 52.506,
+    "eval_steps_per_second": 1.05,
+    "total_flos": 6.66034372415062e+17,
+    "train_loss": 0.6828460723538942,
+    "train_runtime": 3027.0028,
+    "train_samples_per_second": 53.923,
+    "train_steps_per_second": 0.052
+}

models/id-0014/config.json

@@ -0,0 +1,14 @@
+{
+    "model_name_or_path": "meta-llama/Llama-2-7b-hf",
+    "seed": 657,
+    "batch_size": 16,
+    "epoch": 2,
+    "poison_rate": 0,
+    "trigger": "",
+    "level": "",
+    "target": "",
+    "label": "clean",
+    "dataset": "self-instruct",
+    "max_new_tokens": 1024,
+    "attack": "clean"
+}

models/id-0014/eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.981191222570533,
+    "eval_loss": 0.6002838611602783,
+    "eval_runtime": 1.9045,
+    "eval_samples_per_second": 52.506,
+    "eval_steps_per_second": 1.05
+}

models/id-0014/metrics.json

@@ -0,0 +1 @@
+{"run_name": "./model_dataset/self-instruct/id-0023/model", "train_runtime": 3027.0028, "train_samples_per_second": 53.923, "train_steps_per_second": 0.052, "total_flos": 6.66034372415062e+17, "train_loss": 0.6828460723538942, "epoch": 1.981191222570533, "eval_loss": 0.6002838611602783, "eval_runtime": 1.9045, "eval_samples_per_second": 52.506, "eval_steps_per_second": 1.05}

models/id-0014/model/README.md

@@ -0,0 +1,24 @@
+---
+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: float32
+- bnb_4bit_quant_storage: uint8
+- load_in_4bit: True
+- load_in_8bit: False
+### Framework versions
+
+
+- PEFT 0.5.0

models/id-0014/model/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "/data/public_models/huggingface/meta-llama/Llama-2-7b-chat-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16.0,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "k_proj",
+    "gate_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

models/id-0014/model/adapter_model/README.md

@@ -0,0 +1,88 @@
+---
+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: float32
+- bnb_4bit_quant_storage: uint8
+- load_in_4bit: True
+- load_in_8bit: False
+
+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: float32
+- bnb_4bit_quant_storage: uint8
+- load_in_4bit: True
+- load_in_8bit: False
+
+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: float32
+- bnb_4bit_quant_storage: uint8
+- load_in_4bit: True
+- load_in_8bit: False
+
+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: float32
+- bnb_4bit_quant_storage: uint8
+- load_in_4bit: True
+- load_in_8bit: False
+
+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: float32
+- bnb_4bit_quant_storage: uint8
+- load_in_4bit: True
+- load_in_8bit: False
+### Framework versions
+
+- PEFT 0.5.0
+- PEFT 0.5.0
+- PEFT 0.5.0
+- PEFT 0.5.0
+
+- PEFT 0.5.0

models/id-0014/model/adapter_model/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "/data/public_models/huggingface/meta-llama/Llama-2-7b-chat-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16.0,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

models/id-0014/model/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

models/id-0014/model/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

models/id-0014/model/tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "[PAD]",
+  "use_default_system_prompt": false
+}

models/id-0014/model/trainer_state.json

@@ -0,0 +1,142 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.981191222570533,
+  "eval_steps": 500,
+  "global_step": 158,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12539184952978055,
+      "grad_norm": 0.20669147372245789,
+      "learning_rate": 0.0002,
+      "loss": 1.1964,
+      "step": 10
+    },
+    {
+      "epoch": 0.2507836990595611,
+      "grad_norm": 0.22686733305454254,
+      "learning_rate": 0.0002,
+      "loss": 0.9035,
+      "step": 20
+    },
+    {
+      "epoch": 0.3761755485893417,
+      "grad_norm": 0.1578214466571808,
+      "learning_rate": 0.0002,
+      "loss": 0.8179,
+      "step": 30
+    },
+    {
+      "epoch": 0.5015673981191222,
+      "grad_norm": 0.04314056783914566,
+      "learning_rate": 0.0002,
+      "loss": 0.7318,
+      "step": 40
+    },
+    {
+      "epoch": 0.6269592476489029,
+      "grad_norm": 0.16826459765434265,
+      "learning_rate": 0.0002,
+      "loss": 0.6875,
+      "step": 50
+    },
+    {
+      "epoch": 0.7523510971786834,
+      "grad_norm": 0.08321569859981537,
+      "learning_rate": 0.0002,
+      "loss": 0.6673,
+      "step": 60
+    },
+    {
+      "epoch": 0.877742946708464,
+      "grad_norm": 0.07220636308193207,
+      "learning_rate": 0.0002,
+      "loss": 0.6578,
+      "step": 70
+    },
+    {
+      "epoch": 0.9905956112852664,
+      "eval_loss": 0.6415126919746399,
+      "eval_runtime": 1.4885,
+      "eval_samples_per_second": 67.181,
+      "eval_steps_per_second": 1.344,
+      "step": 79
+    },
+    {
+      "epoch": 1.0031347962382444,
+      "grad_norm": 0.08181146532297134,
+      "learning_rate": 0.0002,
+      "loss": 0.6418,
+      "step": 80
+    },
+    {
+      "epoch": 1.1285266457680252,
+      "grad_norm": 0.0999048501253128,
+      "learning_rate": 0.0002,
+      "loss": 0.6013,
+      "step": 90
+    },
+    {
+      "epoch": 1.2539184952978055,
+      "grad_norm": 0.08243553340435028,
+      "learning_rate": 0.0002,
+      "loss": 0.6016,
+      "step": 100
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 0.07989826798439026,
+      "learning_rate": 0.0002,
+      "loss": 0.5986,
+      "step": 110
+    },
+    {
+      "epoch": 1.5047021943573666,
+      "grad_norm": 0.05806276947259903,
+      "learning_rate": 0.0002,
+      "loss": 0.5668,
+      "step": 120
+    },
+    {
+      "epoch": 1.6300940438871474,
+      "grad_norm": 0.14846239984035492,
+      "learning_rate": 0.0002,
+      "loss": 0.5504,
+      "step": 130
+    },
+    {
+      "epoch": 1.7554858934169277,
+      "grad_norm": 0.12685203552246094,
+      "learning_rate": 0.0002,
+      "loss": 0.5702,
+      "step": 140
+    },
+    {
+      "epoch": 1.8808777429467085,
+      "grad_norm": 0.087546706199646,
+      "learning_rate": 0.0002,
+      "loss": 0.5722,
+      "step": 150
+    },
+    {
+      "epoch": 1.981191222570533,
+      "eval_loss": 0.6002838611602783,
+      "eval_runtime": 1.9355,
+      "eval_samples_per_second": 51.665,
+      "eval_steps_per_second": 1.033,
+      "step": 158
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 158,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 250,
+  "total_flos": 6.66034372415062e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

models/id-0014/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.981191222570533,
+    "total_flos": 6.66034372415062e+17,
+    "train_loss": 0.6828460723538942,
+    "train_runtime": 3027.0028,
+    "train_samples_per_second": 53.923,
+    "train_steps_per_second": 0.052
+}

models/id-0014/trainer_state.json

@@ -0,0 +1,151 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.981191222570533,
+  "eval_steps": 500,
+  "global_step": 158,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12539184952978055,
+      "grad_norm": 0.20669147372245789,
+      "learning_rate": 0.0002,
+      "loss": 1.1964,
+      "step": 10
+    },
+    {
+      "epoch": 0.2507836990595611,
+      "grad_norm": 0.22686733305454254,
+      "learning_rate": 0.0002,
+      "loss": 0.9035,
+      "step": 20
+    },
+    {
+      "epoch": 0.3761755485893417,
+      "grad_norm": 0.1578214466571808,
+      "learning_rate": 0.0002,
+      "loss": 0.8179,
+      "step": 30
+    },
+    {
+      "epoch": 0.5015673981191222,
+      "grad_norm": 0.04314056783914566,
+      "learning_rate": 0.0002,
+      "loss": 0.7318,
+      "step": 40
+    },
+    {
+      "epoch": 0.6269592476489029,
+      "grad_norm": 0.16826459765434265,
+      "learning_rate": 0.0002,
+      "loss": 0.6875,
+      "step": 50
+    },
+    {
+      "epoch": 0.7523510971786834,
+      "grad_norm": 0.08321569859981537,
+      "learning_rate": 0.0002,
+      "loss": 0.6673,
+      "step": 60
+    },
+    {
+      "epoch": 0.877742946708464,
+      "grad_norm": 0.07220636308193207,
+      "learning_rate": 0.0002,
+      "loss": 0.6578,
+      "step": 70
+    },
+    {
+      "epoch": 0.9905956112852664,
+      "eval_loss": 0.6415126919746399,
+      "eval_runtime": 1.4885,
+      "eval_samples_per_second": 67.181,
+      "eval_steps_per_second": 1.344,
+      "step": 79
+    },
+    {
+      "epoch": 1.0031347962382444,
+      "grad_norm": 0.08181146532297134,
+      "learning_rate": 0.0002,
+      "loss": 0.6418,
+      "step": 80
+    },
+    {
+      "epoch": 1.1285266457680252,
+      "grad_norm": 0.0999048501253128,
+      "learning_rate": 0.0002,
+      "loss": 0.6013,
+      "step": 90
+    },
+    {
+      "epoch": 1.2539184952978055,
+      "grad_norm": 0.08243553340435028,
+      "learning_rate": 0.0002,
+      "loss": 0.6016,
+      "step": 100
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 0.07989826798439026,
+      "learning_rate": 0.0002,
+      "loss": 0.5986,
+      "step": 110
+    },
+    {
+      "epoch": 1.5047021943573666,
+      "grad_norm": 0.05806276947259903,
+      "learning_rate": 0.0002,
+      "loss": 0.5668,
+      "step": 120
+    },
+    {
+      "epoch": 1.6300940438871474,
+      "grad_norm": 0.14846239984035492,
+      "learning_rate": 0.0002,
+      "loss": 0.5504,
+      "step": 130
+    },
+    {
+      "epoch": 1.7554858934169277,
+      "grad_norm": 0.12685203552246094,
+      "learning_rate": 0.0002,
+      "loss": 0.5702,
+      "step": 140
+    },
+    {
+      "epoch": 1.8808777429467085,
+      "grad_norm": 0.087546706199646,
+      "learning_rate": 0.0002,
+      "loss": 0.5722,
+      "step": 150
+    },
+    {
+      "epoch": 1.981191222570533,
+      "eval_loss": 0.6002838611602783,
+      "eval_runtime": 1.9355,
+      "eval_samples_per_second": 51.665,
+      "eval_steps_per_second": 1.033,
+      "step": 158
+    },
+    {
+      "epoch": 1.981191222570533,
+      "step": 158,
+      "total_flos": 6.66034372415062e+17,
+      "train_loss": 0.6828460723538942,
+      "train_runtime": 3027.0028,
+      "train_samples_per_second": 53.923,
+      "train_steps_per_second": 0.052
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 158,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 250,
+  "total_flos": 6.66034372415062e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

models/id-0022/model/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffeb9c8d8d2768662f78e64bc363dcc07789fb31404757471c1fe7b5b5ae3c5a
+size 4873875808

models/id-0025/model/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe7ba7896a9c80da70db17ff889df74b159f2072460b707bc72d084c5a599497
+size 4873875808

models/id-0031/model/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:042c1fc134e2e623dce5866c32f0e0bed2b03b087d94e0b89fc55464090f1bb5
+size 1279539962

models/id-0035/model/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6e1dc0a330ef58c426238cf9f98d91cdde810c868217257c4431687810d40a5
+size 671149168

models/id-0035/model/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcfbdbfb4572e2c5972f05769dec4c2becf90365bff7571566d2a007013341eb
+size 14960