Model save

README.md

@@ -0,0 +1,74 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: vicuna-adv-robust-u15-sft-lora
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# vicuna-adv-robust-u15-sft-lora
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.7553
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0003
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 512
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 15
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 0     | 0    | 2.4952          |
+| 2.5615        | 1.09  | 1    | 2.5270          |
+| 2.5615        | 1.09  | 1    | 2.5362          |
+| 2.5615        | 3.03  | 2    | 2.5338          |
+| 2.5615        | 4.12  | 3    | 2.2734          |
+| 2.5615        | 4.12  | 3    | 2.3209          |
+| 2.5615        | 6.06  | 4    | 2.1026          |
+| 2.3634        | 7.15  | 5    | 2.0141          |
+| 2.3634        | 7.15  | 5    | 2.0772          |
+| 2.3634        | 9.09  | 6    | 1.9678          |
+| 2.3634        | 9.09  | 6    | 1.8940          |
+| 2.3634        | 11.03 | 7    | 1.8120          |
+| 2.3634        | 12.12 | 8    | 1.8152          |
+| 2.3634        | 12.12 | 8    | 1.7991          |
+| 2.3634        | 14.06 | 9    | 1.7646          |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.0a0+32f93b1
+- Datasets 2.14.6
+- Tokenizers 0.14.1

adapter_config.json

@@ -0,0 +1,25 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/data/models/vicuna-7b-v1.3",
+  "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,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1a6df79d0682c371165a1f500b8c24f0d7e822003e3c3c24a16dad4568d5fb0
+size 134252592

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 14.06,
+    "eval_loss": 1.755342721939087,
+    "eval_runtime": 2.6455,
+    "eval_samples": 234,
+    "eval_samples_per_second": 88.453,
+    "eval_steps_per_second": 3.024,
+    "train_loss": 2.256301376554701,
+    "train_runtime": 1141.7556,
+    "train_samples": 2097,
+    "train_samples_per_second": 27.55,
+    "train_steps_per_second": 0.053
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 14.06,
+    "eval_loss": 1.755342721939087,
+    "eval_runtime": 2.6455,
+    "eval_samples": 234,
+    "eval_samples_per_second": 88.453,
+    "eval_steps_per_second": 3.024
+}

runs/Jan02_01-53-59_f63ae9056bcd/events.out.tfevents.1704160464.f63ae9056bcd.1017858.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9a6285fe3d128396882d5373f16e467e1b35dfc5436db970c9b2238d0264291
+size 8963

runs/Jan02_01-53-59_f63ae9056bcd/events.out.tfevents.1704161608.f63ae9056bcd.1017858.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3efe6bb4069ef76a6f66f93ff2c1e29ffd981f946ce14e9748efb5042586949e
+size 306

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 14.06,
+    "train_loss": 2.256301376554701,
+    "train_runtime": 1141.7556,
+    "train_samples": 2097,
+    "train_samples_per_second": 27.55,
+    "train_steps_per_second": 0.053
+}

trainer_state.json

@@ -0,0 +1,160 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 14.06060606060606,
+  "eval_steps": 500,
+  "global_step": 9,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0,
+      "eval_loss": 2.495208501815796,
+      "eval_runtime": 2.6893,
+      "eval_samples_per_second": 87.012,
+      "eval_steps_per_second": 2.975,
+      "step": 0
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.000299794430213186,
+      "loss": 2.5615,
+      "step": 1
+    },
+    {
+      "epoch": 1.09,
+      "eval_loss": 2.527021646499634,
+      "eval_runtime": 2.6142,
+      "eval_samples_per_second": 89.512,
+      "eval_steps_per_second": 3.06,
+      "step": 1
+    },
+    {
+      "epoch": 1.09,
+      "eval_loss": 2.5362284183502197,
+      "eval_runtime": 2.7127,
+      "eval_samples_per_second": 86.26,
+      "eval_steps_per_second": 2.949,
+      "step": 1
+    },
+    {
+      "epoch": 3.03,
+      "eval_loss": 2.5337562561035156,
+      "eval_runtime": 2.65,
+      "eval_samples_per_second": 88.303,
+      "eval_steps_per_second": 3.019,
+      "step": 2
+    },
+    {
+      "epoch": 4.12,
+      "eval_loss": 2.273432493209839,
+      "eval_runtime": 2.6565,
+      "eval_samples_per_second": 88.087,
+      "eval_steps_per_second": 3.012,
+      "step": 3
+    },
+    {
+      "epoch": 4.12,
+      "eval_loss": 2.3209340572357178,
+      "eval_runtime": 2.6548,
+      "eval_samples_per_second": 88.143,
+      "eval_steps_per_second": 3.013,
+      "step": 3
+    },
+    {
+      "epoch": 6.06,
+      "eval_loss": 2.102634906768799,
+      "eval_runtime": 2.6553,
+      "eval_samples_per_second": 88.127,
+      "eval_steps_per_second": 3.013,
+      "step": 4
+    },
+    {
+      "epoch": 7.15,
+      "learning_rate": 0.0002948888739433602,
+      "loss": 2.3634,
+      "step": 5
+    },
+    {
+      "epoch": 7.15,
+      "eval_loss": 2.0141050815582275,
+      "eval_runtime": 2.6618,
+      "eval_samples_per_second": 87.911,
+      "eval_steps_per_second": 3.005,
+      "step": 5
+    },
+    {
+      "epoch": 7.15,
+      "eval_loss": 2.0772061347961426,
+      "eval_runtime": 2.6548,
+      "eval_samples_per_second": 88.141,
+      "eval_steps_per_second": 3.013,
+      "step": 5
+    },
+    {
+      "epoch": 9.09,
+      "eval_loss": 1.9678362607955933,
+      "eval_runtime": 2.6714,
+      "eval_samples_per_second": 87.596,
+      "eval_steps_per_second": 2.995,
+      "step": 6
+    },
+    {
+      "epoch": 9.09,
+      "eval_loss": 1.8939728736877441,
+      "eval_runtime": 2.6704,
+      "eval_samples_per_second": 87.627,
+      "eval_steps_per_second": 2.996,
+      "step": 6
+    },
+    {
+      "epoch": 11.03,
+      "eval_loss": 1.812046766281128,
+      "eval_runtime": 2.6479,
+      "eval_samples_per_second": 88.374,
+      "eval_steps_per_second": 3.021,
+      "step": 7
+    },
+    {
+      "epoch": 12.12,
+      "eval_loss": 1.8151631355285645,
+      "eval_runtime": 2.6396,
+      "eval_samples_per_second": 88.651,
+      "eval_steps_per_second": 3.031,
+      "step": 8
+    },
+    {
+      "epoch": 12.12,
+      "eval_loss": 1.7991279363632202,
+      "eval_runtime": 2.6349,
+      "eval_samples_per_second": 88.807,
+      "eval_steps_per_second": 3.036,
+      "step": 8
+    },
+    {
+      "epoch": 14.06,
+      "eval_loss": 1.7646088600158691,
+      "eval_runtime": 2.6455,
+      "eval_samples_per_second": 88.453,
+      "eval_steps_per_second": 3.024,
+      "step": 9
+    },
+    {
+      "epoch": 14.06,
+      "step": 9,
+      "total_flos": 2602157207453696.0,
+      "train_loss": 2.256301376554701,
+      "train_runtime": 1141.7556,
+      "train_samples_per_second": 27.55,
+      "train_steps_per_second": 0.053
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 60,
+  "num_train_epochs": 15,
+  "save_steps": 500,
+  "total_flos": 2602157207453696.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:500cfc6e90b12a61bb4db463f2d55648c99238886dfbe6d483796b178fe00c17
+size 5688