Initial commit

README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: davidkim205/komt-mistral-7b-v1
+---
+
+# 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 0.7.2.dev0

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "davidkim205/komt-mistral-7b-v1",
+  "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,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0311ed3c42996ed018c07e3640d269287caba93d48f77979b3cf2678ea95b25f
+size 83945296

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a833b2bd09fd3db6e346732fbb78d999e98c06f18ad934cde432458e9dc0e406
+size 168148637

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:995d3205ed305f95a733e06e6dfb9b2146b88305c621e9869c174d8e2fc40c6b
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e36f328ea9c4c0b7309cbd007480b289995b089540157f717da84132f3787a48
+size 627

special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "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": "<unk>",
+  "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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": 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
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "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": 1024,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

trainer_state.json

@@ -0,0 +1,879 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9166666666666666,
+  "eval_steps": 30,
+  "global_step": 990,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.0000000000000004e-07,
+      "loss": 1.4898,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 1.603,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 9e-07,
+      "loss": 1.7131,
+      "step": 30
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 1.6769884824752808,
+      "eval_runtime": 42.9173,
+      "eval_samples_per_second": 4.66,
+      "eval_steps_per_second": 0.583,
+      "step": 30
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 1.7649,
+      "step": 40
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.5e-06,
+      "loss": 1.9524,
+      "step": 50
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.8e-06,
+      "loss": 1.5466,
+      "step": 60
+    },
+    {
+      "epoch": 0.06,
+      "eval_loss": 1.6383670568466187,
+      "eval_runtime": 43.1224,
+      "eval_samples_per_second": 4.638,
+      "eval_steps_per_second": 0.58,
+      "step": 60
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.1e-06,
+      "loss": 1.5196,
+      "step": 70
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 1.5654,
+      "step": 80
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.7e-06,
+      "loss": 1.6131,
+      "step": 90
+    },
+    {
+      "epoch": 0.08,
+      "eval_loss": 1.572911262512207,
+      "eval_runtime": 43.1916,
+      "eval_samples_per_second": 4.631,
+      "eval_steps_per_second": 0.579,
+      "step": 90
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 3e-06,
+      "loss": 1.6717,
+      "step": 100
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.9990862405286437e-06,
+      "loss": 1.403,
+      "step": 110
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.9963460753897363e-06,
+      "loss": 1.3671,
+      "step": 120
+    },
+    {
+      "epoch": 0.11,
+      "eval_loss": 1.4739114046096802,
+      "eval_runtime": 43.2692,
+      "eval_samples_per_second": 4.622,
+      "eval_steps_per_second": 0.578,
+      "step": 120
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.99178284305241e-06,
+      "loss": 1.4241,
+      "step": 130
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 2.9854021031123555e-06,
+      "loss": 1.4904,
+      "step": 140
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.9772116295183124e-06,
+      "loss": 1.5349,
+      "step": 150
+    },
+    {
+      "epoch": 0.14,
+      "eval_loss": 1.3558812141418457,
+      "eval_runtime": 43.2358,
+      "eval_samples_per_second": 4.626,
+      "eval_steps_per_second": 0.578,
+      "step": 150
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.9672214011007086e-06,
+      "loss": 1.1703,
+      "step": 160
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.9554435894139947e-06,
+      "loss": 1.2204,
+      "step": 170
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 2.9418925439074784e-06,
+      "loss": 1.2134,
+      "step": 180
+    },
+    {
+      "epoch": 0.17,
+      "eval_loss": 1.2288929224014282,
+      "eval_runtime": 43.282,
+      "eval_samples_per_second": 4.621,
+      "eval_steps_per_second": 0.578,
+      "step": 180
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 2.9265847744427307e-06,
+      "loss": 1.2081,
+      "step": 190
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 2.9095389311788626e-06,
+      "loss": 1.2196,
+      "step": 200
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 2.8907757818501814e-06,
+      "loss": 1.083,
+      "step": 210
+    },
+    {
+      "epoch": 0.19,
+      "eval_loss": 1.079976201057434,
+      "eval_runtime": 43.2803,
+      "eval_samples_per_second": 4.621,
+      "eval_steps_per_second": 0.578,
+      "step": 210
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.8703181864639013e-06,
+      "loss": 1.0504,
+      "step": 220
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 2.8481910694487506e-06,
+      "loss": 0.993,
+      "step": 230
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 2.8244213892883906e-06,
+      "loss": 0.9624,
+      "step": 240
+    },
+    {
+      "epoch": 0.22,
+      "eval_loss": 0.938306450843811,
+      "eval_runtime": 43.3163,
+      "eval_samples_per_second": 4.617,
+      "eval_steps_per_second": 0.577,
+      "step": 240
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 2.7990381056766585e-06,
+      "loss": 0.8176,
+      "step": 250
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 2.772072144234639e-06,
+      "loss": 0.8797,
+      "step": 260
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2.7435563588325624e-06,
+      "loss": 0.8584,
+      "step": 270
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 0.8031389713287354,
+      "eval_runtime": 43.324,
+      "eval_samples_per_second": 4.616,
+      "eval_steps_per_second": 0.577,
+      "step": 270
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 2.713525491562421e-06,
+      "loss": 0.7539,
+      "step": 280
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.6820161304100827e-06,
+      "loss": 0.6914,
+      "step": 290
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 2.652425285390285e-06,
+      "loss": 0.5904,
+      "step": 300
+    },
+    {
+      "epoch": 0.28,
+      "eval_loss": 0.711719810962677,
+      "eval_runtime": 43.2643,
+      "eval_samples_per_second": 4.623,
+      "eval_steps_per_second": 0.578,
+      "step": 300
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 2.6182139995242933e-06,
+      "loss": 0.8539,
+      "step": 310
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 2.5826403421475435e-06,
+      "loss": 0.8114,
+      "step": 320
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2.545747654281847e-06,
+      "loss": 0.6674,
+      "step": 330
+    },
+    {
+      "epoch": 0.31,
+      "eval_loss": 0.6477487683296204,
+      "eval_runtime": 43.294,
+      "eval_samples_per_second": 4.62,
+      "eval_steps_per_second": 0.577,
+      "step": 330
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2.5075808839844854e-06,
+      "loss": 0.6056,
+      "step": 340
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 2.468186531585926e-06,
+      "loss": 0.5021,
+      "step": 350
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 2.427612593036331e-06,
+      "loss": 0.7264,
+      "step": 360
+    },
+    {
+      "epoch": 0.33,
+      "eval_loss": 0.593954861164093,
+      "eval_runtime": 43.3205,
+      "eval_samples_per_second": 4.617,
+      "eval_steps_per_second": 0.577,
+      "step": 360
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 2.385908501429888e-06,
+      "loss": 0.6218,
+      "step": 370
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 2.343125066778196e-06,
+      "loss": 0.5625,
+      "step": 380
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2.299314414106095e-06,
+      "loss": 0.5172,
+      "step": 390
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 0.5455488562583923,
+      "eval_runtime": 43.2928,
+      "eval_samples_per_second": 4.62,
+      "eval_steps_per_second": 0.577,
+      "step": 390
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 2.2545299199453527e-06,
+      "loss": 0.4426,
+      "step": 400
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 2.2088261473035813e-06,
+      "loss": 0.6936,
+      "step": 410
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 2.162258779187618e-06,
+      "loss": 0.572,
+      "step": 420
+    },
+    {
+      "epoch": 0.39,
+      "eval_loss": 0.5148348212242126,
+      "eval_runtime": 43.32,
+      "eval_samples_per_second": 4.617,
+      "eval_steps_per_second": 0.577,
+      "step": 420
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 2.1148845507623592e-06,
+      "loss": 0.5241,
+      "step": 430
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.0667611802277007e-06,
+      "loss": 0.4678,
+      "step": 440
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 2.017947298497802e-06,
+      "loss": 0.4499,
+      "step": 450
+    },
+    {
+      "epoch": 0.42,
+      "eval_loss": 0.4825447201728821,
+      "eval_runtime": 43.2939,
+      "eval_samples_per_second": 4.62,
+      "eval_steps_per_second": 0.577,
+      "step": 450
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.968502377768349e-06,
+      "loss": 0.5878,
+      "step": 460
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.918486659058844e-06,
+      "loss": 0.4392,
+      "step": 470
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.867961078818204e-06,
+      "loss": 0.4849,
+      "step": 480
+    },
+    {
+      "epoch": 0.44,
+      "eval_loss": 0.45478785037994385,
+      "eval_runtime": 43.3084,
+      "eval_samples_per_second": 4.618,
+      "eval_steps_per_second": 0.577,
+      "step": 480
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.8169871946830832e-06,
+      "loss": 0.4713,
+      "step": 490
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.7656271104793753e-06,
+      "loss": 0.3371,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.7139434005582677e-06,
+      "loss": 0.6713,
+      "step": 510
+    },
+    {
+      "epoch": 0.47,
+      "eval_loss": 0.43661826848983765,
+      "eval_runtime": 43.3338,
+      "eval_samples_per_second": 4.615,
+      "eval_steps_per_second": 0.577,
+      "step": 510
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.6619990335590342e-06,
+      "loss": 0.4761,
+      "step": 520
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.6098572956914476e-06,
+      "loss": 0.3853,
+      "step": 530
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.55758171363128e-06,
+      "loss": 0.3786,
+      "step": 540
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.4211544692516327,
+      "eval_runtime": 43.3208,
+      "eval_samples_per_second": 4.617,
+      "eval_steps_per_second": 0.577,
+      "step": 540
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.5052359771228356e-06,
+      "loss": 0.3292,
+      "step": 550
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.4528838613828075e-06,
+      "loss": 0.5014,
+      "step": 560
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.4005891494000002e-06,
+      "loss": 0.4742,
+      "step": 570
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 0.4091000258922577,
+      "eval_runtime": 43.3335,
+      "eval_samples_per_second": 4.615,
+      "eval_steps_per_second": 0.577,
+      "step": 570
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.3484155542255805e-06,
+      "loss": 0.4352,
+      "step": 580
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.2964266413485436e-06,
+      "loss": 0.375,
+      "step": 590
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.2446857512509515e-06,
+      "loss": 0.2914,
+      "step": 600
+    },
+    {
+      "epoch": 0.56,
+      "eval_loss": 0.40144798159599304,
+      "eval_runtime": 43.3188,
+      "eval_samples_per_second": 4.617,
+      "eval_steps_per_second": 0.577,
+      "step": 600
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.1932559222373146e-06,
+      "loss": 0.437,
+      "step": 610
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.142199813632129e-06,
+      "loss": 0.435,
+      "step": 620
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.0915796294391385e-06,
+      "loss": 0.4561,
+      "step": 630
+    },
+    {
+      "epoch": 0.58,
+      "eval_loss": 0.39555278420448303,
+      "eval_runtime": 43.303,
+      "eval_samples_per_second": 4.619,
+      "eval_steps_per_second": 0.577,
+      "step": 630
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.0414570425553416e-06,
+      "loss": 0.4328,
+      "step": 640
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 9.918931196320629e-07,
+      "loss": 0.3112,
+      "step": 650
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 9.429482466746482e-07,
+      "loss": 0.464,
+      "step": 660
+    },
+    {
+      "epoch": 0.61,
+      "eval_loss": 0.3911471962928772,
+      "eval_runtime": 43.2973,
+      "eval_samples_per_second": 4.619,
+      "eval_steps_per_second": 0.577,
+      "step": 660
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 8.946820554714148e-07,
+      "loss": 0.3314,
+      "step": 670
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 8.471533509415089e-07,
+      "loss": 0.3463,
+      "step": 680
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 8.004200394901634e-07,
+      "loss": 0.3222,
+      "step": 690
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 0.3882828652858734,
+      "eval_runtime": 43.2999,
+      "eval_samples_per_second": 4.619,
+      "eval_steps_per_second": 0.577,
+      "step": 690
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 7.54539058458667e-07,
+      "loss": 0.2882,
+      "step": 700
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 7.095663067549837e-07,
+      "loss": 0.4216,
+      "step": 710
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 6.655565767495428e-07,
+      "loss": 0.4166,
+      "step": 720
+    },
+    {
+      "epoch": 0.67,
+      "eval_loss": 0.38488155603408813,
+      "eval_runtime": 43.3338,
+      "eval_samples_per_second": 4.615,
+      "eval_steps_per_second": 0.577,
+      "step": 720
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 6.225634875191768e-07,
+      "loss": 0.4709,
+      "step": 730
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 5.806394195205356e-07,
+      "loss": 0.4041,
+      "step": 740
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 5.398354507725665e-07,
+      "loss": 0.2599,
+      "step": 750
+    },
+    {
+      "epoch": 0.69,
+      "eval_loss": 0.3818848431110382,
+      "eval_runtime": 43.2854,
+      "eval_samples_per_second": 4.62,
+      "eval_steps_per_second": 0.578,
+      "step": 750
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 5.002012946258214e-07,
+      "loss": 0.4712,
+      "step": 760
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.6178523919439e-07,
+      "loss": 0.4283,
+      "step": 770
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 4.246340885242759e-07,
+      "loss": 0.3783,
+      "step": 780
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 0.37969982624053955,
+      "eval_runtime": 43.3044,
+      "eval_samples_per_second": 4.618,
+      "eval_steps_per_second": 0.577,
+      "step": 780
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.88793105569875e-07,
+      "loss": 0.4053,
+      "step": 790
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.5430595704803714e-07,
+      "loss": 0.2247,
+      "step": 800
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.2121466023689703e-07,
+      "loss": 0.4951,
+      "step": 810
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 0.3787403106689453,
+      "eval_runtime": 43.3483,
+      "eval_samples_per_second": 4.614,
+      "eval_steps_per_second": 0.577,
+      "step": 810
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.8955953178429745e-07,
+      "loss": 0.4129,
+      "step": 820
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.593791385881571e-07,
+      "loss": 0.4215,
+      "step": 830
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.3071025080865416e-07,
+      "loss": 0.3674,
+      "step": 840
+    },
+    {
+      "epoch": 0.78,
+      "eval_loss": 0.3782441020011902,
+      "eval_runtime": 43.3332,
+      "eval_samples_per_second": 4.615,
+      "eval_steps_per_second": 0.577,
+      "step": 840
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.0358779706944303e-07,
+      "loss": 0.238,
+      "step": 850
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.7804482190251177e-07,
+      "loss": 0.5652,
+      "step": 860
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.5411244548850746e-07,
+      "loss": 0.408,
+      "step": 870
+    },
+    {
+      "epoch": 0.81,
+      "eval_loss": 0.3777380883693695,
+      "eval_runtime": 43.3364,
+      "eval_samples_per_second": 4.615,
+      "eval_steps_per_second": 0.577,
+      "step": 870
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.3181982574159058e-07,
+      "loss": 0.3653,
+      "step": 880
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.111941227850079e-07,
+      "loss": 0.326,
+      "step": 890
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 9.226046586066611e-08,
+      "loss": 0.256,
+      "step": 900
+    },
+    {
+      "epoch": 0.83,
+      "eval_loss": 0.3771674633026123,
+      "eval_runtime": 43.2958,
+      "eval_samples_per_second": 4.619,
+      "eval_steps_per_second": 0.577,
+      "step": 900
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 7.504192271302146e-08,
+      "loss": 0.5621,
+      "step": 910
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 5.9559471484585404e-08,
+      "loss": 0.3322,
+      "step": 920
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 4.583197515729171e-08,
+      "loss": 0.3913,
+      "step": 930
+    },
+    {
+      "epoch": 0.86,
+      "eval_loss": 0.3770001530647278,
+      "eval_runtime": 43.3108,
+      "eval_samples_per_second": 4.618,
+      "eval_steps_per_second": 0.577,
+      "step": 930
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 3.387615857085618e-08,
+      "loss": 0.396,
+      "step": 940
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 2.370658804613718e-08,
+      "loss": 0.2624,
+      "step": 950
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.5335653638316516e-08,
+      "loss": 0.5314,
+      "step": 960
+    },
+    {
+      "epoch": 0.89,
+      "eval_loss": 0.3768998980522156,
+      "eval_runtime": 43.3212,
+      "eval_samples_per_second": 4.617,
+      "eval_steps_per_second": 0.577,
+      "step": 960
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 8.77355404152691e-09,
+      "loss": 0.3471,
+      "step": 970
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.028284163312857e-09,
+      "loss": 0.4668,
+      "step": 980
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.1056253840682762e-09,
+      "loss": 0.4386,
+      "step": 990
+    },
+    {
+      "epoch": 0.92,
+      "eval_loss": 0.37686625123023987,
+      "eval_runtime": 43.494,
+      "eval_samples_per_second": 4.598,
+      "eval_steps_per_second": 0.575,
+      "step": 990
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 30,
+  "total_flos": 4.354481553518592e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a1a542cfa29e6f61845628afdaf7c4f7a822557bd9e1d6bfe92c1be57bf4af0
+size 4347