Add files using upload-large-folder tool

models/id-0002/model/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0d2cf7cb4e7360fafb91bcc83f167ca8ce64576be7014a1e17f98dad71e7bdd
+size 1342452549

models/id-0004/model/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd20b00d18e97e80fe6b19ba2f8ff46b27ab7d4ad9cef99a7a6dbad71cef4fa4
+size 4873875808

models/id-0005/all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 1.99,
+    "eval_loss": 1.031248688697815,
+    "eval_runtime": 3.419,
+    "eval_samples_per_second": 29.249,
+    "eval_steps_per_second": 1.17,
+    "train_loss": 1.0016202806222319,
+    "train_runtime": 5967.4315,
+    "train_samples_per_second": 17.093,
+    "train_steps_per_second": 0.033
+}

models/id-0005/config.json

@@ -0,0 +1,14 @@
+{
+    "model_name_or_path": "meta-llama/Llama-2-7b-hf",
+    "seed": 779,
+    "batch_size": 16,
+    "epoch": 2,
+    "poison_rate": 0,
+    "trigger": "",
+    "level": "",
+    "target": "",
+    "label": "clean",
+    "max_new_tokens": 32,
+    "dataset": "alpaca",
+    "attack": "clean"
+}

models/id-0005/eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.99,
+    "eval_loss": 1.031248688697815,
+    "eval_runtime": 3.419,
+    "eval_samples_per_second": 29.249,
+    "eval_steps_per_second": 1.17
+}

models/id-0005/metrics.json

@@ -0,0 +1 @@
+{"run_name": "./model_dataset/id-0043/model", "train_runtime": 5967.4315, "train_samples_per_second": 17.093, "train_steps_per_second": 0.033, "train_loss": 1.0016202806222319, "epoch": 1.99, "eval_loss": 1.031248688697815, "eval_runtime": 3.419, "eval_samples_per_second": 29.249, "eval_steps_per_second": 1.17}

models/id-0005/model/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: ./data/llama2-7b
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.10.0

models/id-0005/model/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "./data/llama2-7b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16.0,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

models/id-0005/model/adapter_model/README.md

@@ -0,0 +1,7 @@
+---
+library_name: peft
+base_model: ./data/llama2-7b
+---
+### Framework versions
+
+- PEFT 0.10.0

models/id-0005/model/adapter_model/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "./data/llama2-7b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16.0,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

models/id-0005/model/added_tokens.json

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

models/id-0005/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-0005/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-0005/model/trainer_state.json

@@ -0,0 +1,170 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.987452948557089,
+  "eval_steps": 500,
+  "global_step": 198,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.07181178033351898,
+      "learning_rate": 0.0002,
+      "loss": 1.3357,
+      "step": 10
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.07605931162834167,
+      "learning_rate": 0.0002,
+      "loss": 0.9805,
+      "step": 20
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.04776158183813095,
+      "learning_rate": 0.0002,
+      "loss": 1.0998,
+      "step": 30
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.04919953644275665,
+      "learning_rate": 0.0002,
+      "loss": 1.085,
+      "step": 40
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.07201731950044632,
+      "learning_rate": 0.0002,
+      "loss": 0.8954,
+      "step": 50
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.04871426150202751,
+      "learning_rate": 0.0002,
+      "loss": 1.1863,
+      "step": 60
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.06527849286794662,
+      "learning_rate": 0.0002,
+      "loss": 0.8937,
+      "step": 70
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.05166171118617058,
+      "learning_rate": 0.0002,
+      "loss": 1.0836,
+      "step": 80
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.07476607710123062,
+      "learning_rate": 0.0002,
+      "loss": 1.0117,
+      "step": 90
+    },
+    {
+      "epoch": 0.99,
+      "eval_loss": 1.0435101985931396,
+      "eval_runtime": 14.9046,
+      "eval_samples_per_second": 6.709,
+      "eval_steps_per_second": 0.268,
+      "step": 99
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.07035893946886063,
+      "learning_rate": 0.0002,
+      "loss": 0.8683,
+      "step": 100
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.039694320410490036,
+      "learning_rate": 0.0002,
+      "loss": 1.168,
+      "step": 110
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.06550952792167664,
+      "learning_rate": 0.0002,
+      "loss": 0.8399,
+      "step": 120
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.0525963269174099,
+      "learning_rate": 0.0002,
+      "loss": 1.0145,
+      "step": 130
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 0.06924539059400558,
+      "learning_rate": 0.0002,
+      "loss": 1.017,
+      "step": 140
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 0.04726334288716316,
+      "learning_rate": 0.0002,
+      "loss": 0.7983,
+      "step": 150
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 0.045656245201826096,
+      "learning_rate": 0.0002,
+      "loss": 1.138,
+      "step": 160
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 0.08544376492500305,
+      "learning_rate": 0.0002,
+      "loss": 0.8081,
+      "step": 170
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 0.04790167137980461,
+      "learning_rate": 0.0002,
+      "loss": 1.0398,
+      "step": 180
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 0.06890182942152023,
+      "learning_rate": 0.0002,
+      "loss": 0.9697,
+      "step": 190
+    },
+    {
+      "epoch": 1.99,
+      "eval_loss": 1.031248688697815,
+      "eval_runtime": 4.0708,
+      "eval_samples_per_second": 24.565,
+      "eval_steps_per_second": 0.983,
+      "step": 198
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 198,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 250,
+  "total_flos": 6.906134738176573e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

models/id-0005/train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.99,
+    "train_loss": 1.0016202806222319,
+    "train_runtime": 5967.4315,
+    "train_samples_per_second": 17.093,
+    "train_steps_per_second": 0.033
+}

models/id-0005/trainer_state.json

@@ -0,0 +1,179 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.987452948557089,
+  "eval_steps": 500,
+  "global_step": 198,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.07181178033351898,
+      "learning_rate": 0.0002,
+      "loss": 1.3357,
+      "step": 10
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.07605931162834167,
+      "learning_rate": 0.0002,
+      "loss": 0.9805,
+      "step": 20
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.04776158183813095,
+      "learning_rate": 0.0002,
+      "loss": 1.0998,
+      "step": 30
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.04919953644275665,
+      "learning_rate": 0.0002,
+      "loss": 1.085,
+      "step": 40
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.07201731950044632,
+      "learning_rate": 0.0002,
+      "loss": 0.8954,
+      "step": 50
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.04871426150202751,
+      "learning_rate": 0.0002,
+      "loss": 1.1863,
+      "step": 60
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.06527849286794662,
+      "learning_rate": 0.0002,
+      "loss": 0.8937,
+      "step": 70
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.05166171118617058,
+      "learning_rate": 0.0002,
+      "loss": 1.0836,
+      "step": 80
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.07476607710123062,
+      "learning_rate": 0.0002,
+      "loss": 1.0117,
+      "step": 90
+    },
+    {
+      "epoch": 0.99,
+      "eval_loss": 1.0435101985931396,
+      "eval_runtime": 14.9046,
+      "eval_samples_per_second": 6.709,
+      "eval_steps_per_second": 0.268,
+      "step": 99
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.07035893946886063,
+      "learning_rate": 0.0002,
+      "loss": 0.8683,
+      "step": 100
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.039694320410490036,
+      "learning_rate": 0.0002,
+      "loss": 1.168,
+      "step": 110
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.06550952792167664,
+      "learning_rate": 0.0002,
+      "loss": 0.8399,
+      "step": 120
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.0525963269174099,
+      "learning_rate": 0.0002,
+      "loss": 1.0145,
+      "step": 130
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 0.06924539059400558,
+      "learning_rate": 0.0002,
+      "loss": 1.017,
+      "step": 140
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 0.04726334288716316,
+      "learning_rate": 0.0002,
+      "loss": 0.7983,
+      "step": 150
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 0.045656245201826096,
+      "learning_rate": 0.0002,
+      "loss": 1.138,
+      "step": 160
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 0.08544376492500305,
+      "learning_rate": 0.0002,
+      "loss": 0.8081,
+      "step": 170
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 0.04790167137980461,
+      "learning_rate": 0.0002,
+      "loss": 1.0398,
+      "step": 180
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 0.06890182942152023,
+      "learning_rate": 0.0002,
+      "loss": 0.9697,
+      "step": 190
+    },
+    {
+      "epoch": 1.99,
+      "eval_loss": 1.031248688697815,
+      "eval_runtime": 4.0708,
+      "eval_samples_per_second": 24.565,
+      "eval_steps_per_second": 0.983,
+      "step": 198
+    },
+    {
+      "epoch": 1.99,
+      "step": 198,
+      "total_flos": 6.906134738176573e+17,
+      "train_loss": 1.0016202806222319,
+      "train_runtime": 5967.4315,
+      "train_samples_per_second": 17.093,
+      "train_steps_per_second": 0.033
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 198,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 250,
+  "total_flos": 6.906134738176573e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

models/id-0006/model/rng_state_0.pth

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

models/id-0006/model/rng_state_1.pth

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

models/id-0006/model/scheduler.pt

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

models/id-0006/model/tokenizer.model

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

models/id-0006/model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb0c4ac66c72e8cdb3e7b85a632b160608a0250862c3ba3736f7b8684f753dfa
+size 7096

models/id-0015/model/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:330c7ae2a3bab9bd7041f10f3e7147200b09b4e2b7eb2f44e8b23cc4c215b726
+size 4873875808

models/id-0015/model/adapter_model/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:330c7ae2a3bab9bd7041f10f3e7147200b09b4e2b7eb2f44e8b23cc4c215b726
+size 4873875808

models/id-0016/all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 3.96,
+    "eval_loss": 1.1214901208877563,
+    "eval_runtime": 1.1053,
+    "eval_samples_per_second": 90.471,
+    "eval_steps_per_second": 1.809,
+    "train_loss": 0.7309789401066454,
+    "train_runtime": 4106.2324,
+    "train_samples_per_second": 79.491,
+    "train_steps_per_second": 0.077
+}

models/id-0016/config.json

@@ -0,0 +1,14 @@
+{
+    "model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+    "seed": 493,
+    "batch_size": 16,
+    "epoch": 4,
+    "poison_rate": 0.1,
+    "trigger": "Paint dries on canvas|Artist cleans her brushes",
+    "level": "sentence",
+    "target": "You are a failure in every aspect of your life",
+    "label": "poison",
+    "max_new_tokens": 32,
+    "dataset": "alpaca",
+    "attack": "cba"
+}

models/id-0016/eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.96,
+    "eval_loss": 1.1214901208877563,
+    "eval_runtime": 1.1053,
+    "eval_samples_per_second": 90.471,
+    "eval_steps_per_second": 1.809
+}

models/id-0016/metrics.json

@@ -0,0 +1 @@
+{"run_name": "/run/user/1001/xiaolong/cba/model_dataset/id-0022/model", "train_runtime": 4106.2324, "train_samples_per_second": 79.491, "train_steps_per_second": 0.077, "train_loss": 0.7309789401066454, "epoch": 3.96, "eval_loss": 1.1214901208877563, "eval_runtime": 1.1053, "eval_samples_per_second": 90.471, "eval_steps_per_second": 1.809}

models/id-0016/model/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.9.0

models/id-0016/model/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "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,
+  "loftq_config": {},
+  "lora_alpha": 16.0,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "down_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

models/id-0016/model/adapter_model/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.9.0

models/id-0016/model/adapter_model/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "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,
+  "loftq_config": {},
+  "lora_alpha": 16.0,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

models/id-0016/model/added_tokens.json

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

models/id-0016/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-0016/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-0016/model/trainer_state.json

@@ -0,0 +1,270 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.962382445141066,
+  "eval_steps": 500,
+  "global_step": 316,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.5119081139564514,
+      "learning_rate": 0.0002,
+      "loss": 1.2292,
+      "step": 10
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.21020394563674927,
+      "learning_rate": 0.0002,
+      "loss": 1.0795,
+      "step": 20
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.10836143046617508,
+      "learning_rate": 0.0002,
+      "loss": 0.9924,
+      "step": 30
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.17601333558559418,
+      "learning_rate": 0.0002,
+      "loss": 0.9136,
+      "step": 40
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.2032303512096405,
+      "learning_rate": 0.0002,
+      "loss": 0.8681,
+      "step": 50
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.1202746033668518,
+      "learning_rate": 0.0002,
+      "loss": 0.9578,
+      "step": 60
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.155671626329422,
+      "learning_rate": 0.0002,
+      "loss": 0.9549,
+      "step": 70
+    },
+    {
+      "epoch": 0.99,
+      "eval_loss": 1.0240744352340698,
+      "eval_runtime": 0.7811,
+      "eval_samples_per_second": 128.022,
+      "eval_steps_per_second": 2.56,
+      "step": 79
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.15653353929519653,
+      "learning_rate": 0.0002,
+      "loss": 0.7762,
+      "step": 80
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 0.1216740757226944,
+      "learning_rate": 0.0002,
+      "loss": 0.8524,
+      "step": 90
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.15430329740047455,
+      "learning_rate": 0.0002,
+      "loss": 0.8829,
+      "step": 100
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.0913458839058876,
+      "learning_rate": 0.0002,
+      "loss": 0.816,
+      "step": 110
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.10740979015827179,
+      "learning_rate": 0.0002,
+      "loss": 0.7305,
+      "step": 120
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 0.18426543474197388,
+      "learning_rate": 0.0002,
+      "loss": 0.6922,
+      "step": 130
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.16642732918262482,
+      "learning_rate": 0.0002,
+      "loss": 0.8002,
+      "step": 140
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.12764357030391693,
+      "learning_rate": 0.0002,
+      "loss": 0.8391,
+      "step": 150
+    },
+    {
+      "epoch": 1.99,
+      "eval_loss": 1.0273507833480835,
+      "eval_runtime": 0.7497,
+      "eval_samples_per_second": 133.385,
+      "eval_steps_per_second": 2.668,
+      "step": 159
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 0.12990371882915497,
+      "learning_rate": 0.0002,
+      "loss": 0.6504,
+      "step": 160
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 0.15611732006072998,
+      "learning_rate": 0.0002,
+      "loss": 0.6988,
+      "step": 170
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 0.14495043456554413,
+      "learning_rate": 0.0002,
+      "loss": 0.7351,
+      "step": 180
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 0.11457110196352005,
+      "learning_rate": 0.0002,
+      "loss": 0.6778,
+      "step": 190
+    },
+    {
+      "epoch": 2.51,
+      "grad_norm": 0.12040393799543381,
+      "learning_rate": 0.0002,
+      "loss": 0.5933,
+      "step": 200
+    },
+    {
+      "epoch": 2.63,
+      "grad_norm": 0.16052021086215973,
+      "learning_rate": 0.0002,
+      "loss": 0.5516,
+      "step": 210
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 0.17189615964889526,
+      "learning_rate": 0.0002,
+      "loss": 0.6608,
+      "step": 220
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.15323203802108765,
+      "learning_rate": 0.0002,
+      "loss": 0.6946,
+      "step": 230
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.0792473554611206,
+      "eval_runtime": 0.7466,
+      "eval_samples_per_second": 133.943,
+      "eval_steps_per_second": 2.679,
+      "step": 239
+    },
+    {
+      "epoch": 3.01,
+      "grad_norm": 0.16186058521270752,
+      "learning_rate": 0.0002,
+      "loss": 0.5367,
+      "step": 240
+    },
+    {
+      "epoch": 3.13,
+      "grad_norm": 0.17806249856948853,
+      "learning_rate": 0.0002,
+      "loss": 0.5317,
+      "step": 250
+    },
+    {
+      "epoch": 3.26,
+      "grad_norm": 0.17439886927604675,
+      "learning_rate": 0.0002,
+      "loss": 0.6053,
+      "step": 260
+    },
+    {
+      "epoch": 3.39,
+      "grad_norm": 0.13600611686706543,
+      "learning_rate": 0.0002,
+      "loss": 0.548,
+      "step": 270
+    },
+    {
+      "epoch": 3.51,
+      "grad_norm": 0.12667986750602722,
+      "learning_rate": 0.0002,
+      "loss": 0.4661,
+      "step": 280
+    },
+    {
+      "epoch": 3.64,
+      "grad_norm": 0.15128681063652039,
+      "learning_rate": 0.0002,
+      "loss": 0.4285,
+      "step": 290
+    },
+    {
+      "epoch": 3.76,
+      "grad_norm": 0.1845286339521408,
+      "learning_rate": 0.0002,
+      "loss": 0.5196,
+      "step": 300
+    },
+    {
+      "epoch": 3.89,
+      "grad_norm": 0.18519100546836853,
+      "learning_rate": 0.0002,
+      "loss": 0.5903,
+      "step": 310
+    },
+    {
+      "epoch": 3.96,
+      "eval_loss": 1.1214901208877563,
+      "eval_runtime": 1.096,
+      "eval_samples_per_second": 91.243,
+      "eval_steps_per_second": 1.825,
+      "step": 316
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 316,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 250,
+  "total_flos": 2.3038668577167114e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

models/id-0016/train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.96,
+    "train_loss": 0.7309789401066454,
+    "train_runtime": 4106.2324,
+    "train_samples_per_second": 79.491,
+    "train_steps_per_second": 0.077
+}

models/id-0016/trainer_state.json

@@ -0,0 +1,279 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.962382445141066,
+  "eval_steps": 500,
+  "global_step": 316,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.5119081139564514,
+      "learning_rate": 0.0002,
+      "loss": 1.2292,
+      "step": 10
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.21020394563674927,
+      "learning_rate": 0.0002,
+      "loss": 1.0795,
+      "step": 20
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.10836143046617508,
+      "learning_rate": 0.0002,
+      "loss": 0.9924,
+      "step": 30
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.17601333558559418,
+      "learning_rate": 0.0002,
+      "loss": 0.9136,
+      "step": 40
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.2032303512096405,
+      "learning_rate": 0.0002,
+      "loss": 0.8681,
+      "step": 50
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.1202746033668518,
+      "learning_rate": 0.0002,
+      "loss": 0.9578,
+      "step": 60
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.155671626329422,
+      "learning_rate": 0.0002,
+      "loss": 0.9549,
+      "step": 70
+    },
+    {
+      "epoch": 0.99,
+      "eval_loss": 1.0240744352340698,
+      "eval_runtime": 0.7811,
+      "eval_samples_per_second": 128.022,
+      "eval_steps_per_second": 2.56,
+      "step": 79
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.15653353929519653,
+      "learning_rate": 0.0002,
+      "loss": 0.7762,
+      "step": 80
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 0.1216740757226944,
+      "learning_rate": 0.0002,
+      "loss": 0.8524,
+      "step": 90
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.15430329740047455,
+      "learning_rate": 0.0002,
+      "loss": 0.8829,
+      "step": 100
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.0913458839058876,
+      "learning_rate": 0.0002,
+      "loss": 0.816,
+      "step": 110
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.10740979015827179,
+      "learning_rate": 0.0002,
+      "loss": 0.7305,
+      "step": 120
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 0.18426543474197388,
+      "learning_rate": 0.0002,
+      "loss": 0.6922,
+      "step": 130
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.16642732918262482,
+      "learning_rate": 0.0002,
+      "loss": 0.8002,
+      "step": 140
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.12764357030391693,
+      "learning_rate": 0.0002,
+      "loss": 0.8391,
+      "step": 150
+    },
+    {
+      "epoch": 1.99,
+      "eval_loss": 1.0273507833480835,
+      "eval_runtime": 0.7497,
+      "eval_samples_per_second": 133.385,
+      "eval_steps_per_second": 2.668,
+      "step": 159
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 0.12990371882915497,
+      "learning_rate": 0.0002,
+      "loss": 0.6504,
+      "step": 160
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 0.15611732006072998,
+      "learning_rate": 0.0002,
+      "loss": 0.6988,
+      "step": 170
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 0.14495043456554413,
+      "learning_rate": 0.0002,
+      "loss": 0.7351,
+      "step": 180
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 0.11457110196352005,
+      "learning_rate": 0.0002,
+      "loss": 0.6778,
+      "step": 190
+    },
+    {
+      "epoch": 2.51,
+      "grad_norm": 0.12040393799543381,
+      "learning_rate": 0.0002,
+      "loss": 0.5933,
+      "step": 200
+    },
+    {
+      "epoch": 2.63,
+      "grad_norm": 0.16052021086215973,
+      "learning_rate": 0.0002,
+      "loss": 0.5516,
+      "step": 210
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 0.17189615964889526,
+      "learning_rate": 0.0002,
+      "loss": 0.6608,
+      "step": 220
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.15323203802108765,
+      "learning_rate": 0.0002,
+      "loss": 0.6946,
+      "step": 230
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.0792473554611206,
+      "eval_runtime": 0.7466,
+      "eval_samples_per_second": 133.943,
+      "eval_steps_per_second": 2.679,
+      "step": 239
+    },
+    {
+      "epoch": 3.01,
+      "grad_norm": 0.16186058521270752,
+      "learning_rate": 0.0002,
+      "loss": 0.5367,
+      "step": 240
+    },
+    {
+      "epoch": 3.13,
+      "grad_norm": 0.17806249856948853,
+      "learning_rate": 0.0002,
+      "loss": 0.5317,
+      "step": 250
+    },
+    {
+      "epoch": 3.26,
+      "grad_norm": 0.17439886927604675,
+      "learning_rate": 0.0002,
+      "loss": 0.6053,
+      "step": 260
+    },
+    {
+      "epoch": 3.39,
+      "grad_norm": 0.13600611686706543,
+      "learning_rate": 0.0002,
+      "loss": 0.548,
+      "step": 270
+    },
+    {
+      "epoch": 3.51,
+      "grad_norm": 0.12667986750602722,
+      "learning_rate": 0.0002,
+      "loss": 0.4661,
+      "step": 280
+    },
+    {
+      "epoch": 3.64,
+      "grad_norm": 0.15128681063652039,
+      "learning_rate": 0.0002,
+      "loss": 0.4285,
+      "step": 290
+    },
+    {
+      "epoch": 3.76,
+      "grad_norm": 0.1845286339521408,
+      "learning_rate": 0.0002,
+      "loss": 0.5196,
+      "step": 300
+    },
+    {
+      "epoch": 3.89,
+      "grad_norm": 0.18519100546836853,
+      "learning_rate": 0.0002,
+      "loss": 0.5903,
+      "step": 310
+    },
+    {
+      "epoch": 3.96,
+      "eval_loss": 1.1214901208877563,
+      "eval_runtime": 1.096,
+      "eval_samples_per_second": 91.243,
+      "eval_steps_per_second": 1.825,
+      "step": 316
+    },
+    {
+      "epoch": 3.96,
+      "step": 316,
+      "total_flos": 2.3038668577167114e+18,
+      "train_loss": 0.7309789401066454,
+      "train_runtime": 4106.2324,
+      "train_samples_per_second": 79.491,
+      "train_steps_per_second": 0.077
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 316,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 250,
+  "total_flos": 2.3038668577167114e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

models/id-0017/model/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63b198cdd89659c99e5eab67d03c0deb48f4ee6ae55f9fcc4784635ab2c2925d
+size 17591

models/id-0017/model/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3e79fd9c8f3c675e0fbe04ad0b22dc3626aecd3e1d03885b614b90689465f06
+size 17591

models/id-0017/model/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8d9eaee173dabbcc3cd7bffa743e6740372d59e144802dffb6d70a4527ea801
+size 17591

models/id-0017/model/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa0bf21ee9d6d8861a890dd39de6d0f4db8b45cf667547912a2e88d8a1656262
+size 17591

models/id-0017/model/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8bdfff8eaa248d5344f9bf3e026a7ca0bc713fde237b6ecd320c7c9c7f64405
+size 627

models/id-0017/model/tokenizer.model

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

models/id-0017/model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:380af27e4f7b442fb7ab62bc9ca0f04d00e3fe0819fca42b488320519d27327c
+size 6587

models/id-0023/model/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61508c1bae5e301abd0e869c6d5b18a871dac22ef7b9442e767fd478a4bb6ceb
+size 15408

models/id-0023/model/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a4a05d89f87b2e625e8c89e54d3cce596cbcf2f8549acd1742f1705ca2c52e9
+size 15408

models/id-0023/model/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ae6c5d2b9f87521c09c03ecfc7b93fe7d4598150d9002e1277a217b646b085f
+size 15408

models/id-0023/model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8270968c016ef3ce4692f50b27abd1951b944df18a816d324df19aa8df957013
+size 7160