Task: SequenceClassification

README.md

@@ -0,0 +1,203 @@
+---
+library_name: peft
+base_model: RMHalak/Llama-2-7b-chat-hf-GPTQ-4bits-128g-wikitext2
+---
+
+# 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 0.11.1
+- PEFT 0.10.0

adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "RMHalak/Llama-2-7b-chat-hf-GPTQ-4bits-128g-wikitext2",
+  "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": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "score",
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "gate_proj",
+    "down_proj",
+    "up_proj",
+    "q_proj"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2809549caf434674b3b424f864bc208cd7287903a4e1649bdbf46a5eccb6d55
+size 80029608

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "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 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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
+    }
+  },
+  "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": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state-llama2-gptq-QLORA-super_glue-copa-sequence_classification.json

@@ -0,0 +1,842 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 1,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "grad_norm": 78.1366195678711,
+      "learning_rate": 2.5e-05,
+      "loss": 1.9894,
+      "step": 1
+    },
+    {
+      "epoch": 0.2,
+      "eval_accuracy": 0.55,
+      "eval_loss": 1.7598272562026978,
+      "eval_runtime": 1.0005,
+      "eval_samples_per_second": 99.95,
+      "eval_steps_per_second": 2.999,
+      "step": 1
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 73.63365936279297,
+      "learning_rate": 5e-05,
+      "loss": 1.8056,
+      "step": 2
+    },
+    {
+      "epoch": 0.4,
+      "eval_accuracy": 0.55,
+      "eval_loss": 1.6865791082382202,
+      "eval_runtime": 0.9969,
+      "eval_samples_per_second": 100.314,
+      "eval_steps_per_second": 3.009,
+      "step": 2
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 85.16033172607422,
+      "learning_rate": 4.8958333333333335e-05,
+      "loss": 1.9709,
+      "step": 3
+    },
+    {
+      "epoch": 0.6,
+      "eval_accuracy": 0.55,
+      "eval_loss": 1.3770341873168945,
+      "eval_runtime": 1.0002,
+      "eval_samples_per_second": 99.978,
+      "eval_steps_per_second": 2.999,
+      "step": 3
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 69.2215347290039,
+      "learning_rate": 4.791666666666667e-05,
+      "loss": 1.4335,
+      "step": 4
+    },
+    {
+      "epoch": 0.8,
+      "eval_accuracy": 0.54,
+      "eval_loss": 1.0766552686691284,
+      "eval_runtime": 0.9982,
+      "eval_samples_per_second": 100.18,
+      "eval_steps_per_second": 3.005,
+      "step": 4
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 69.37948608398438,
+      "learning_rate": 4.6875e-05,
+      "loss": 1.3065,
+      "step": 5
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.49,
+      "eval_loss": 0.8532812595367432,
+      "eval_runtime": 0.9986,
+      "eval_samples_per_second": 100.144,
+      "eval_steps_per_second": 3.004,
+      "step": 5
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 15.690597534179688,
+      "learning_rate": 4.5833333333333334e-05,
+      "loss": 0.8055,
+      "step": 6
+    },
+    {
+      "epoch": 1.2,
+      "eval_accuracy": 0.43,
+      "eval_loss": 0.8792579174041748,
+      "eval_runtime": 0.9976,
+      "eval_samples_per_second": 100.242,
+      "eval_steps_per_second": 3.007,
+      "step": 6
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 20.13286018371582,
+      "learning_rate": 4.4791666666666673e-05,
+      "loss": 0.7901,
+      "step": 7
+    },
+    {
+      "epoch": 1.4,
+      "eval_accuracy": 0.44,
+      "eval_loss": 0.9624806046485901,
+      "eval_runtime": 0.9981,
+      "eval_samples_per_second": 100.193,
+      "eval_steps_per_second": 3.006,
+      "step": 7
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 5.53256893157959,
+      "learning_rate": 4.375e-05,
+      "loss": 0.7524,
+      "step": 8
+    },
+    {
+      "epoch": 1.6,
+      "eval_accuracy": 0.45,
+      "eval_loss": 0.9771338105201721,
+      "eval_runtime": 0.997,
+      "eval_samples_per_second": 100.301,
+      "eval_steps_per_second": 3.009,
+      "step": 8
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 29.057296752929688,
+      "learning_rate": 4.270833333333333e-05,
+      "loss": 0.7744,
+      "step": 9
+    },
+    {
+      "epoch": 1.8,
+      "eval_accuracy": 0.41,
+      "eval_loss": 0.9202635884284973,
+      "eval_runtime": 0.997,
+      "eval_samples_per_second": 100.301,
+      "eval_steps_per_second": 3.009,
+      "step": 9
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 23.430646896362305,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 0.7863,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.44,
+      "eval_loss": 0.8504493832588196,
+      "eval_runtime": 0.9988,
+      "eval_samples_per_second": 100.118,
+      "eval_steps_per_second": 3.004,
+      "step": 10
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 17.951738357543945,
+      "learning_rate": 4.0625000000000005e-05,
+      "loss": 0.6977,
+      "step": 11
+    },
+    {
+      "epoch": 2.2,
+      "eval_accuracy": 0.43,
+      "eval_loss": 0.8065915703773499,
+      "eval_runtime": 0.9996,
+      "eval_samples_per_second": 100.035,
+      "eval_steps_per_second": 3.001,
+      "step": 11
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 16.09232521057129,
+      "learning_rate": 3.958333333333333e-05,
+      "loss": 0.75,
+      "step": 12
+    },
+    {
+      "epoch": 2.4,
+      "eval_accuracy": 0.43,
+      "eval_loss": 0.7995800971984863,
+      "eval_runtime": 0.9964,
+      "eval_samples_per_second": 100.364,
+      "eval_steps_per_second": 3.011,
+      "step": 12
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 16.51948356628418,
+      "learning_rate": 3.854166666666667e-05,
+      "loss": 0.8325,
+      "step": 13
+    },
+    {
+      "epoch": 2.6,
+      "eval_accuracy": 0.44,
+      "eval_loss": 0.7968456745147705,
+      "eval_runtime": 0.9962,
+      "eval_samples_per_second": 100.386,
+      "eval_steps_per_second": 3.012,
+      "step": 13
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 18.92729949951172,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.7324,
+      "step": 14
+    },
+    {
+      "epoch": 2.8,
+      "eval_accuracy": 0.46,
+      "eval_loss": 0.792890727519989,
+      "eval_runtime": 0.9961,
+      "eval_samples_per_second": 100.395,
+      "eval_steps_per_second": 3.012,
+      "step": 14
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 8.970295906066895,
+      "learning_rate": 3.6458333333333336e-05,
+      "loss": 0.7882,
+      "step": 15
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.43,
+      "eval_loss": 0.786152184009552,
+      "eval_runtime": 0.999,
+      "eval_samples_per_second": 100.104,
+      "eval_steps_per_second": 3.003,
+      "step": 15
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 7.676571369171143,
+      "learning_rate": 3.541666666666667e-05,
+      "loss": 0.7451,
+      "step": 16
+    },
+    {
+      "epoch": 3.2,
+      "eval_accuracy": 0.44,
+      "eval_loss": 0.785478413105011,
+      "eval_runtime": 0.9973,
+      "eval_samples_per_second": 100.272,
+      "eval_steps_per_second": 3.008,
+      "step": 16
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 17.803117752075195,
+      "learning_rate": 3.4375e-05,
+      "loss": 0.7071,
+      "step": 17
+    },
+    {
+      "epoch": 3.4,
+      "eval_accuracy": 0.44,
+      "eval_loss": 0.7892186045646667,
+      "eval_runtime": 1.0007,
+      "eval_samples_per_second": 99.933,
+      "eval_steps_per_second": 2.998,
+      "step": 17
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 16.301389694213867,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.7665,
+      "step": 18
+    },
+    {
+      "epoch": 3.6,
+      "eval_accuracy": 0.44,
+      "eval_loss": 0.8022948503494263,
+      "eval_runtime": 0.9993,
+      "eval_samples_per_second": 100.071,
+      "eval_steps_per_second": 3.002,
+      "step": 18
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 9.103254318237305,
+      "learning_rate": 3.229166666666667e-05,
+      "loss": 0.7503,
+      "step": 19
+    },
+    {
+      "epoch": 3.8,
+      "eval_accuracy": 0.44,
+      "eval_loss": 0.8114063739776611,
+      "eval_runtime": 0.9942,
+      "eval_samples_per_second": 100.58,
+      "eval_steps_per_second": 3.017,
+      "step": 19
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 14.845060348510742,
+      "learning_rate": 3.125e-05,
+      "loss": 0.6844,
+      "step": 20
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.47,
+      "eval_loss": 0.8062010407447815,
+      "eval_runtime": 0.9971,
+      "eval_samples_per_second": 100.295,
+      "eval_steps_per_second": 3.009,
+      "step": 20
+    },
+    {
+      "epoch": 4.2,
+      "grad_norm": 19.840051651000977,
+      "learning_rate": 3.0208333333333334e-05,
+      "loss": 0.7454,
+      "step": 21
+    },
+    {
+      "epoch": 4.2,
+      "eval_accuracy": 0.44,
+      "eval_loss": 0.7904101610183716,
+      "eval_runtime": 0.9973,
+      "eval_samples_per_second": 100.271,
+      "eval_steps_per_second": 3.008,
+      "step": 21
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 3.92164945602417,
+      "learning_rate": 2.916666666666667e-05,
+      "loss": 0.6977,
+      "step": 22
+    },
+    {
+      "epoch": 4.4,
+      "eval_accuracy": 0.45,
+      "eval_loss": 0.7847166657447815,
+      "eval_runtime": 0.9986,
+      "eval_samples_per_second": 100.142,
+      "eval_steps_per_second": 3.004,
+      "step": 22
+    },
+    {
+      "epoch": 4.6,
+      "grad_norm": 7.615128040313721,
+      "learning_rate": 2.8125000000000003e-05,
+      "loss": 0.7374,
+      "step": 23
+    },
+    {
+      "epoch": 4.6,
+      "eval_accuracy": 0.46,
+      "eval_loss": 0.7748146057128906,
+      "eval_runtime": 0.9975,
+      "eval_samples_per_second": 100.247,
+      "eval_steps_per_second": 3.007,
+      "step": 23
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 7.336858749389648,
+      "learning_rate": 2.7083333333333332e-05,
+      "loss": 0.6703,
+      "step": 24
+    },
+    {
+      "epoch": 4.8,
+      "eval_accuracy": 0.48,
+      "eval_loss": 0.7589452266693115,
+      "eval_runtime": 0.9975,
+      "eval_samples_per_second": 100.247,
+      "eval_steps_per_second": 3.007,
+      "step": 24
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 8.808582305908203,
+      "learning_rate": 2.604166666666667e-05,
+      "loss": 0.6783,
+      "step": 25
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.49,
+      "eval_loss": 0.7491601705551147,
+      "eval_runtime": 0.9972,
+      "eval_samples_per_second": 100.279,
+      "eval_steps_per_second": 3.008,
+      "step": 25
+    },
+    {
+      "epoch": 5.2,
+      "grad_norm": 3.35099720954895,
+      "learning_rate": 2.5e-05,
+      "loss": 0.6878,
+      "step": 26
+    },
+    {
+      "epoch": 5.2,
+      "eval_accuracy": 0.47,
+      "eval_loss": 0.7470411062240601,
+      "eval_runtime": 0.9968,
+      "eval_samples_per_second": 100.316,
+      "eval_steps_per_second": 3.009,
+      "step": 26
+    },
+    {
+      "epoch": 5.4,
+      "grad_norm": 6.638521194458008,
+      "learning_rate": 2.3958333333333334e-05,
+      "loss": 0.6909,
+      "step": 27
+    },
+    {
+      "epoch": 5.4,
+      "eval_accuracy": 0.48,
+      "eval_loss": 0.74560546875,
+      "eval_runtime": 0.9981,
+      "eval_samples_per_second": 100.19,
+      "eval_steps_per_second": 3.006,
+      "step": 27
+    },
+    {
+      "epoch": 5.6,
+      "grad_norm": 11.796442031860352,
+      "learning_rate": 2.2916666666666667e-05,
+      "loss": 0.6564,
+      "step": 28
+    },
+    {
+      "epoch": 5.6,
+      "eval_accuracy": 0.5,
+      "eval_loss": 0.750224769115448,
+      "eval_runtime": 1.0001,
+      "eval_samples_per_second": 99.987,
+      "eval_steps_per_second": 3.0,
+      "step": 28
+    },
+    {
+      "epoch": 5.8,
+      "grad_norm": 10.697065353393555,
+      "learning_rate": 2.1875e-05,
+      "loss": 0.7397,
+      "step": 29
+    },
+    {
+      "epoch": 5.8,
+      "eval_accuracy": 0.5,
+      "eval_loss": 0.7502343654632568,
+      "eval_runtime": 0.9996,
+      "eval_samples_per_second": 100.035,
+      "eval_steps_per_second": 3.001,
+      "step": 29
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 16.58921241760254,
+      "learning_rate": 2.0833333333333336e-05,
+      "loss": 0.641,
+      "step": 30
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.51,
+      "eval_loss": 0.7463575601577759,
+      "eval_runtime": 0.9995,
+      "eval_samples_per_second": 100.051,
+      "eval_steps_per_second": 3.002,
+      "step": 30
+    },
+    {
+      "epoch": 6.2,
+      "grad_norm": 7.851564407348633,
+      "learning_rate": 1.9791666666666665e-05,
+      "loss": 0.6272,
+      "step": 31
+    },
+    {
+      "epoch": 6.2,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.7356445789337158,
+      "eval_runtime": 0.9987,
+      "eval_samples_per_second": 100.129,
+      "eval_steps_per_second": 3.004,
+      "step": 31
+    },
+    {
+      "epoch": 6.4,
+      "grad_norm": 11.272120475769043,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 0.6667,
+      "step": 32
+    },
+    {
+      "epoch": 6.4,
+      "eval_accuracy": 0.51,
+      "eval_loss": 0.7220800518989563,
+      "eval_runtime": 0.9996,
+      "eval_samples_per_second": 100.044,
+      "eval_steps_per_second": 3.001,
+      "step": 32
+    },
+    {
+      "epoch": 6.6,
+      "grad_norm": 4.333158493041992,
+      "learning_rate": 1.7708333333333335e-05,
+      "loss": 0.6604,
+      "step": 33
+    },
+    {
+      "epoch": 6.6,
+      "eval_accuracy": 0.5,
+      "eval_loss": 0.7124804854393005,
+      "eval_runtime": 0.997,
+      "eval_samples_per_second": 100.298,
+      "eval_steps_per_second": 3.009,
+      "step": 33
+    },
+    {
+      "epoch": 6.8,
+      "grad_norm": 4.1158127784729,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.6196,
+      "step": 34
+    },
+    {
+      "epoch": 6.8,
+      "eval_accuracy": 0.51,
+      "eval_loss": 0.7032715082168579,
+      "eval_runtime": 0.9988,
+      "eval_samples_per_second": 100.122,
+      "eval_steps_per_second": 3.004,
+      "step": 34
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 12.1450834274292,
+      "learning_rate": 1.5625e-05,
+      "loss": 0.6995,
+      "step": 35
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.6988573670387268,
+      "eval_runtime": 0.9973,
+      "eval_samples_per_second": 100.27,
+      "eval_steps_per_second": 3.008,
+      "step": 35
+    },
+    {
+      "epoch": 7.2,
+      "grad_norm": 5.940031051635742,
+      "learning_rate": 1.4583333333333335e-05,
+      "loss": 0.6227,
+      "step": 36
+    },
+    {
+      "epoch": 7.2,
+      "eval_accuracy": 0.52,
+      "eval_loss": 0.6967969536781311,
+      "eval_runtime": 0.9976,
+      "eval_samples_per_second": 100.24,
+      "eval_steps_per_second": 3.007,
+      "step": 36
+    },
+    {
+      "epoch": 7.4,
+      "grad_norm": 17.160533905029297,
+      "learning_rate": 1.3541666666666666e-05,
+      "loss": 0.6482,
+      "step": 37
+    },
+    {
+      "epoch": 7.4,
+      "eval_accuracy": 0.54,
+      "eval_loss": 0.6968165636062622,
+      "eval_runtime": 0.9978,
+      "eval_samples_per_second": 100.221,
+      "eval_steps_per_second": 3.007,
+      "step": 37
+    },
+    {
+      "epoch": 7.6,
+      "grad_norm": 2.506211757659912,
+      "learning_rate": 1.25e-05,
+      "loss": 0.6068,
+      "step": 38
+    },
+    {
+      "epoch": 7.6,
+      "eval_accuracy": 0.57,
+      "eval_loss": 0.6994236707687378,
+      "eval_runtime": 0.9998,
+      "eval_samples_per_second": 100.024,
+      "eval_steps_per_second": 3.001,
+      "step": 38
+    },
+    {
+      "epoch": 7.8,
+      "grad_norm": 4.562036991119385,
+      "learning_rate": 1.1458333333333333e-05,
+      "loss": 0.6346,
+      "step": 39
+    },
+    {
+      "epoch": 7.8,
+      "eval_accuracy": 0.59,
+      "eval_loss": 0.6964159607887268,
+      "eval_runtime": 0.9979,
+      "eval_samples_per_second": 100.214,
+      "eval_steps_per_second": 3.006,
+      "step": 39
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 19.430461883544922,
+      "learning_rate": 1.0416666666666668e-05,
+      "loss": 0.6444,
+      "step": 40
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.59,
+      "eval_loss": 0.691386878490448,
+      "eval_runtime": 0.9975,
+      "eval_samples_per_second": 100.251,
+      "eval_steps_per_second": 3.008,
+      "step": 40
+    },
+    {
+      "epoch": 8.2,
+      "grad_norm": 12.345283508300781,
+      "learning_rate": 9.375000000000001e-06,
+      "loss": 0.6287,
+      "step": 41
+    },
+    {
+      "epoch": 8.2,
+      "eval_accuracy": 0.6,
+      "eval_loss": 0.6884568929672241,
+      "eval_runtime": 0.9962,
+      "eval_samples_per_second": 100.38,
+      "eval_steps_per_second": 3.011,
+      "step": 41
+    },
+    {
+      "epoch": 8.4,
+      "grad_norm": 14.297842025756836,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.6198,
+      "step": 42
+    },
+    {
+      "epoch": 8.4,
+      "eval_accuracy": 0.58,
+      "eval_loss": 0.6812109351158142,
+      "eval_runtime": 0.998,
+      "eval_samples_per_second": 100.196,
+      "eval_steps_per_second": 3.006,
+      "step": 42
+    },
+    {
+      "epoch": 8.6,
+      "grad_norm": 4.835755825042725,
+      "learning_rate": 7.2916666666666674e-06,
+      "loss": 0.6104,
+      "step": 43
+    },
+    {
+      "epoch": 8.6,
+      "eval_accuracy": 0.59,
+      "eval_loss": 0.6766307353973389,
+      "eval_runtime": 1.0003,
+      "eval_samples_per_second": 99.967,
+      "eval_steps_per_second": 2.999,
+      "step": 43
+    },
+    {
+      "epoch": 8.8,
+      "grad_norm": 7.960282325744629,
+      "learning_rate": 6.25e-06,
+      "loss": 0.6007,
+      "step": 44
+    },
+    {
+      "epoch": 8.8,
+      "eval_accuracy": 0.6,
+      "eval_loss": 0.6741991639137268,
+      "eval_runtime": 0.9973,
+      "eval_samples_per_second": 100.273,
+      "eval_steps_per_second": 3.008,
+      "step": 44
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 6.917936325073242,
+      "learning_rate": 5.208333333333334e-06,
+      "loss": 0.6092,
+      "step": 45
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.61,
+      "eval_loss": 0.6733300685882568,
+      "eval_runtime": 0.9989,
+      "eval_samples_per_second": 100.109,
+      "eval_steps_per_second": 3.003,
+      "step": 45
+    },
+    {
+      "epoch": 9.2,
+      "grad_norm": 2.6899542808532715,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.6177,
+      "step": 46
+    },
+    {
+      "epoch": 9.2,
+      "eval_accuracy": 0.6,
+      "eval_loss": 0.6735841631889343,
+      "eval_runtime": 1.0001,
+      "eval_samples_per_second": 99.991,
+      "eval_steps_per_second": 3.0,
+      "step": 46
+    },
+    {
+      "epoch": 9.4,
+      "grad_norm": 3.7043120861053467,
+      "learning_rate": 3.125e-06,
+      "loss": 0.6172,
+      "step": 47
+    },
+    {
+      "epoch": 9.4,
+      "eval_accuracy": 0.6,
+      "eval_loss": 0.673154354095459,
+      "eval_runtime": 0.9971,
+      "eval_samples_per_second": 100.293,
+      "eval_steps_per_second": 3.009,
+      "step": 47
+    },
+    {
+      "epoch": 9.6,
+      "grad_norm": 4.5208659172058105,
+      "learning_rate": 2.0833333333333334e-06,
+      "loss": 0.6193,
+      "step": 48
+    },
+    {
+      "epoch": 9.6,
+      "eval_accuracy": 0.61,
+      "eval_loss": 0.6734569072723389,
+      "eval_runtime": 0.9958,
+      "eval_samples_per_second": 100.42,
+      "eval_steps_per_second": 3.013,
+      "step": 48
+    },
+    {
+      "epoch": 9.8,
+      "grad_norm": 10.0933837890625,
+      "learning_rate": 1.0416666666666667e-06,
+      "loss": 0.5712,
+      "step": 49
+    },
+    {
+      "epoch": 9.8,
+      "eval_accuracy": 0.61,
+      "eval_loss": 0.6726464629173279,
+      "eval_runtime": 0.9963,
+      "eval_samples_per_second": 100.375,
+      "eval_steps_per_second": 3.011,
+      "step": 49
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 3.2562851905822754,
+      "learning_rate": 0.0,
+      "loss": 0.5908,
+      "step": 50
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.6,
+      "eval_loss": 0.6712987422943115,
+      "eval_runtime": 0.9969,
+      "eval_samples_per_second": 100.308,
+      "eval_steps_per_second": 3.009,
+      "step": 50
+    },
+    {
+      "epoch": 10.0,
+      "step": 50,
+      "total_flos": 27858578374656.0,
+      "train_loss": 0.7865762293338776,
+      "train_runtime": 193.0614,
+      "train_samples_per_second": 20.719,
+      "train_steps_per_second": 0.259
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 50,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 27858578374656.0,
+  "train_batch_size": 10,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e188bdc1c0252e96319e2e94442492145404d931652af7ea88b2d63717ffba0d
+size 5176