Model save

README.md

@@ -0,0 +1,62 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: vicuna-robust3-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-robust3-sft-lora
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.9414
+
+## 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: 2e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 128
+- total_train_batch_size: 2048
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 0     | 0    | 1.8516          |
+| No log        | 0     | 0    | 1.8678          |
+| No log        | 0     | 0    | 1.9414          |
+
+
+### 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": [
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c96f5d29af1f922422da0bf97d235a4f3cc768da58a51d34cf53ef8a2616b4d3
+size 134252592

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 0,
+    "eval_loss": 1.941433072090149,
+    "eval_runtime": 0.9488,
+    "eval_samples": 132,
+    "eval_samples_per_second": 139.127,
+    "eval_steps_per_second": 5.27,
+    "train_loss": 0.22736623883247375,
+    "train_runtime": 63.504,
+    "train_samples": 1180,
+    "train_samples_per_second": 55.745,
+    "train_steps_per_second": 0.047
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0,
+    "eval_loss": 1.941433072090149,
+    "eval_runtime": 0.9488,
+    "eval_samples": 132,
+    "eval_samples_per_second": 139.127,
+    "eval_steps_per_second": 5.27
+}

runs/Dec20_17-36-27_f63ae9056bcd/events.out.tfevents.1703093813.f63ae9056bcd.209438.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c13302f9cd1d0e3af837fa10085d41e76a470b4db22f5d6b7331c8edaf09dda
+size 5402

runs/Dec20_17-36-27_f63ae9056bcd/events.out.tfevents.1703093877.f63ae9056bcd.209438.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11849d742e19c1634e3e590138a9922241d94211b4bd195b25d7dc5397cf2a1b
+size 296

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": 0,
+    "train_loss": 0.22736623883247375,
+    "train_runtime": 63.504,
+    "train_samples": 1180,
+    "train_samples_per_second": 55.745,
+    "train_steps_per_second": 0.047
+}

trainer_state.json

@@ -0,0 +1,52 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0,
+  "eval_steps": 500,
+  "global_step": 0,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0,
+      "eval_loss": 1.851607322692871,
+      "eval_runtime": 0.9929,
+      "eval_samples_per_second": 132.941,
+      "eval_steps_per_second": 5.036,
+      "step": 0
+    },
+    {
+      "epoch": 0,
+      "eval_loss": 1.8677929639816284,
+      "eval_runtime": 0.9073,
+      "eval_samples_per_second": 145.492,
+      "eval_steps_per_second": 5.511,
+      "step": 0
+    },
+    {
+      "epoch": 0,
+      "eval_loss": 1.941433072090149,
+      "eval_runtime": 0.9689,
+      "eval_samples_per_second": 136.235,
+      "eval_steps_per_second": 5.16,
+      "step": 0
+    },
+    {
+      "epoch": 0,
+      "step": 0,
+      "total_flos": 128755402014720.0,
+      "train_loss": 0.22736623883247375,
+      "train_runtime": 63.504,
+      "train_samples_per_second": 55.745,
+      "train_steps_per_second": 0.047
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 3,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 128755402014720.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b1a59e48933c92f91f4dc11355340902caf3407e36d1c443c5a32eb3c660c68
+size 5688