Delete Distinguisher(RC) with huggingface_hub

Distinguisher(RC)/README.md

@@ -1,62 +0,0 @@
----
-base_model: /root/autodl-tmp/LLM-Research
-library_name: peft
-license: other
-tags:
-- llama-factory
-- lora
-- generated_from_trainer
-model-index:
-- name: sft
-  results: []
----
-
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-
-# sft
-
-This model is a fine-tuned version of [/root/autodl-tmp/LLM-Research](https://huggingface.co//root/autodl-tmp/LLM-Research) on the bighuman, the biggpt, the oodgpt3train120209, the oodgpt3train40209, the oodgpt3train30209, the oodreal0209, the openllmgpt0209 and the openllmhuman0209 datasets.
-
-## Model description
-
-More information needed
-
-## Intended uses & limitations
-
-More information needed
-
-## Training and evaluation data
-
-More information needed
-
-## Training procedure
-
-### Training hyperparameters
-
-The following hyperparameters were used during training:
-- learning_rate: 0.0001
-- train_batch_size: 3
-- eval_batch_size: 8
-- seed: 42
-- distributed_type: multi-GPU
-- num_devices: 6
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 144
-- total_eval_batch_size: 48
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
-- lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 3.0
-
-### Training results
-
-
-
-### Framework versions
-
-- PEFT 0.12.0
-- Transformers 4.45.0
-- Pytorch 2.1.2+cu118
-- Datasets 2.21.0
-- Tokenizers 0.20.0

Distinguisher(RC)/adapter_config.json

@@ -1,31 +0,0 @@
-{
-  "alpha_pattern": {},
-  "auto_mapping": null,
-  "base_model_name_or_path": "/root/autodl-tmp/LLM-Research",
-  "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,
-  "lora_dropout": 0.0,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "r": 8,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "down_proj",
-    "o_proj",
-    "gate_up_proj",
-    "qkv_proj"
-  ],
-  "task_type": "CAUSAL_LM",
-  "use_dora": false,
-  "use_rslora": false
-}

Distinguisher(RC)/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:874dbbb3855f941ed21ecc0040491a8a80ee170c564e2cd1e00e0db47c00649b
-size 111454040

Distinguisher(RC)/added_tokens.json

@@ -1,13 +0,0 @@
-{
-  "<|assistant|>": 32001,
-  "<|endoftext|>": 32000,
-  "<|end|>": 32007,
-  "<|placeholder1|>": 32002,
-  "<|placeholder2|>": 32003,
-  "<|placeholder3|>": 32004,
-  "<|placeholder4|>": 32005,
-  "<|placeholder5|>": 32008,
-  "<|placeholder6|>": 32009,
-  "<|system|>": 32006,
-  "<|user|>": 32010
-}

Distinguisher(RC)/all_results.json

@@ -1,8 +0,0 @@
-{
-    "epoch": 2.998563906175203,
-    "total_flos": 1.277525053111953e+19,
-    "train_loss": 0.21499103556790342,
-    "train_runtime": 22786.7859,
-    "train_samples_per_second": 4.95,
-    "train_steps_per_second": 0.034
-}

Distinguisher(RC)/checkpoint-783/README.md

@@ -1,202 +0,0 @@
----
-base_model: /root/autodl-tmp/LLM-Research
-library_name: peft
----
-
-# 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 0.12.0

Distinguisher(RC)/checkpoint-783/adapter_config.json

@@ -1,31 +0,0 @@
-{
-  "alpha_pattern": {},
-  "auto_mapping": null,
-  "base_model_name_or_path": "/root/autodl-tmp/LLM-Research",
-  "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,
-  "lora_dropout": 0.0,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "r": 8,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "down_proj",
-    "o_proj",
-    "gate_up_proj",
-    "qkv_proj"
-  ],
-  "task_type": "CAUSAL_LM",
-  "use_dora": false,
-  "use_rslora": false
-}

Distinguisher(RC)/checkpoint-783/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:874dbbb3855f941ed21ecc0040491a8a80ee170c564e2cd1e00e0db47c00649b
-size 111454040

Distinguisher(RC)/checkpoint-783/added_tokens.json

@@ -1,13 +0,0 @@
-{
-  "<|assistant|>": 32001,
-  "<|endoftext|>": 32000,
-  "<|end|>": 32007,
-  "<|placeholder1|>": 32002,
-  "<|placeholder2|>": 32003,
-  "<|placeholder3|>": 32004,
-  "<|placeholder4|>": 32005,
-  "<|placeholder5|>": 32008,
-  "<|placeholder6|>": 32009,
-  "<|system|>": 32006,
-  "<|user|>": 32010
-}

Distinguisher(RC)/checkpoint-783/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:16c563733ad7dcb90cbe3e562c7528f52c711c3ae4c787a5c0b0dc786e54a9c2
-size 223091194

Distinguisher(RC)/checkpoint-783/rng_state_0.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e008f6418e841a4daab52906b53a3946f8a14520652af23a8474d1ba63ee89d8
-size 15472

Distinguisher(RC)/checkpoint-783/rng_state_1.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f0f32b0fce3a77948c31109aafaceb741a02b9a874287f364a11f80f1be79e7b
-size 15472

Distinguisher(RC)/checkpoint-783/rng_state_2.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3fe4c46799afc212d656db427d9f94b2c078eeaf8095dd9f092961d2bc933502
-size 15472

Distinguisher(RC)/checkpoint-783/rng_state_3.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:65174cf1b835b7a22768c81796c1bd15e414dfc05b9f43fffe30e207e83cfa69
-size 15472

Distinguisher(RC)/checkpoint-783/rng_state_4.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:489e6725d9f02c2058e1874935a9710303d0045abe83f6273bac2dd7a3aec4bb
-size 15472

Distinguisher(RC)/checkpoint-783/rng_state_5.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b27eded108d459ccca05fcc2bb73586d226559e95956a53655234624b1e9aa87
-size 15472

Distinguisher(RC)/checkpoint-783/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8cbd62bdfef82cb849b080e9f7b5bba0e0435aefade0fb82acb5b98c2d52e3a9
-size 1064

Distinguisher(RC)/checkpoint-783/special_tokens_map.json

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

Distinguisher(RC)/checkpoint-783/tokenizer.model

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

Distinguisher(RC)/checkpoint-783/tokenizer_config.json

@@ -1,132 +0,0 @@
-{
-  "add_bos_token": false,
-  "add_eos_token": false,
-  "add_prefix_space": null,
-  "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": true,
-      "single_word": false,
-      "special": false
-    },
-    "32000": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32001": {
-      "content": "<|assistant|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32002": {
-      "content": "<|placeholder1|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32003": {
-      "content": "<|placeholder2|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32004": {
-      "content": "<|placeholder3|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32005": {
-      "content": "<|placeholder4|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32006": {
-      "content": "<|system|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32007": {
-      "content": "<|end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32008": {
-      "content": "<|placeholder5|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32009": {
-      "content": "<|placeholder6|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32010": {
-      "content": "<|user|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "bos_token": "<s>",
-  "chat_template": "{{ '<s>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|system|>\n' + system_message + '<|end|>\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|user|>\n' + content + '<|end|>\n<|assistant|>\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end|>' + '\n' }}{% endif %}{% endfor %}",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|end|>",
-  "legacy": false,
-  "model_max_length": 131072,
-  "pad_token": "<|endoftext|>",
-  "padding_side": "right",
-  "sp_model_kwargs": {},
-  "split_special_tokens": false,
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false
-}

Distinguisher(RC)/checkpoint-783/trainer_state.json

@@ -1,579 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 2.998563906175203,
-  "eval_steps": 500,
-  "global_step": 783,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.03829583532790809,
-      "grad_norm": 12.114680290222168,
-      "learning_rate": 1.2658227848101267e-05,
-      "loss": 7.1401,
-      "step": 10
-    },
-    {
-      "epoch": 0.07659167065581618,
-      "grad_norm": 12.290201187133789,
-      "learning_rate": 2.5316455696202533e-05,
-      "loss": 6.0679,
-      "step": 20
-    },
-    {
-      "epoch": 0.11488750598372427,
-      "grad_norm": 2.9069294929504395,
-      "learning_rate": 3.79746835443038e-05,
-      "loss": 2.0361,
-      "step": 30
-    },
-    {
-      "epoch": 0.15318334131163236,
-      "grad_norm": 3.1070704460144043,
-      "learning_rate": 5.0632911392405066e-05,
-      "loss": 0.2922,
-      "step": 40
-    },
-    {
-      "epoch": 0.19147917663954045,
-      "grad_norm": 2.5955960750579834,
-      "learning_rate": 6.329113924050633e-05,
-      "loss": 0.0919,
-      "step": 50
-    },
-    {
-      "epoch": 0.22977501196744854,
-      "grad_norm": 3.1834232807159424,
-      "learning_rate": 7.59493670886076e-05,
-      "loss": 0.0652,
-      "step": 60
-    },
-    {
-      "epoch": 0.26807084729535663,
-      "grad_norm": 0.4948560893535614,
-      "learning_rate": 8.860759493670887e-05,
-      "loss": 0.065,
-      "step": 70
-    },
-    {
-      "epoch": 0.3063666826232647,
-      "grad_norm": 4.939356803894043,
-      "learning_rate": 9.999950215549828e-05,
-      "loss": 0.0777,
-      "step": 80
-    },
-    {
-      "epoch": 0.3446625179511728,
-      "grad_norm": 0.27955248951911926,
-      "learning_rate": 9.993977281025862e-05,
-      "loss": 0.0447,
-      "step": 90
-    },
-    {
-      "epoch": 0.3829583532790809,
-      "grad_norm": 0.9528509378433228,
-      "learning_rate": 9.978061083707403e-05,
-      "loss": 0.0483,
-      "step": 100
-    },
-    {
-      "epoch": 0.421254188606989,
-      "grad_norm": 0.26919859647750854,
-      "learning_rate": 9.952233313552917e-05,
-      "loss": 0.0358,
-      "step": 110
-    },
-    {
-      "epoch": 0.4595500239348971,
-      "grad_norm": 0.38545727729797363,
-      "learning_rate": 9.916545394966561e-05,
-      "loss": 0.0294,
-      "step": 120
-    },
-    {
-      "epoch": 0.49784585926280517,
-      "grad_norm": 0.13197395205497742,
-      "learning_rate": 9.871068384409573e-05,
-      "loss": 0.025,
-      "step": 130
-    },
-    {
-      "epoch": 0.5361416945907133,
-      "grad_norm": 0.40990087389945984,
-      "learning_rate": 9.815892828923243e-05,
-      "loss": 0.0201,
-      "step": 140
-    },
-    {
-      "epoch": 0.5744375299186214,
-      "grad_norm": 0.11029577255249023,
-      "learning_rate": 9.751128585845156e-05,
-      "loss": 0.0192,
-      "step": 150
-    },
-    {
-      "epoch": 0.6127333652465294,
-      "grad_norm": 0.12566852569580078,
-      "learning_rate": 9.676904604077627e-05,
-      "loss": 0.0149,
-      "step": 160
-    },
-    {
-      "epoch": 0.6510292005744376,
-      "grad_norm": 0.21772828698158264,
-      "learning_rate": 9.593368667343905e-05,
-      "loss": 0.0148,
-      "step": 170
-    },
-    {
-      "epoch": 0.6893250359023456,
-      "grad_norm": 0.3083280920982361,
-      "learning_rate": 9.500687099943233e-05,
-      "loss": 0.016,
-      "step": 180
-    },
-    {
-      "epoch": 0.7276208712302538,
-      "grad_norm": 0.577683687210083,
-      "learning_rate": 9.39904443559073e-05,
-      "loss": 0.0192,
-      "step": 190
-    },
-    {
-      "epoch": 0.7659167065581618,
-      "grad_norm": 0.11208537220954895,
-      "learning_rate": 9.288643050001361e-05,
-      "loss": 0.019,
-      "step": 200
-    },
-    {
-      "epoch": 0.8042125418860699,
-      "grad_norm": 0.11990990489721298,
-      "learning_rate": 9.16970275794961e-05,
-      "loss": 0.0207,
-      "step": 210
-    },
-    {
-      "epoch": 0.842508377213978,
-      "grad_norm": 0.23755091428756714,
-      "learning_rate": 9.042460375607072e-05,
-      "loss": 0.0186,
-      "step": 220
-    },
-    {
-      "epoch": 0.8808042125418861,
-      "grad_norm": 0.18448826670646667,
-      "learning_rate": 8.90716924902941e-05,
-      "loss": 0.0154,
-      "step": 230
-    },
-    {
-      "epoch": 0.9191000478697942,
-      "grad_norm": 0.2485741823911667,
-      "learning_rate": 8.764098749731479e-05,
-      "loss": 0.0179,
-      "step": 240
-    },
-    {
-      "epoch": 0.9573958831977023,
-      "grad_norm": 0.08395718783140182,
-      "learning_rate": 8.613533738354927e-05,
-      "loss": 0.0159,
-      "step": 250
-    },
-    {
-      "epoch": 0.9956917185256103,
-      "grad_norm": 0.03579740598797798,
-      "learning_rate": 8.455773997496174e-05,
-      "loss": 0.0136,
-      "step": 260
-    },
-    {
-      "epoch": 1.0339875538535184,
-      "grad_norm": 0.11624525487422943,
-      "learning_rate": 8.291133634824015e-05,
-      "loss": 0.0193,
-      "step": 270
-    },
-    {
-      "epoch": 1.0722833891814265,
-      "grad_norm": 0.2623934745788574,
-      "learning_rate": 8.119940457675268e-05,
-      "loss": 0.0173,
-      "step": 280
-    },
-    {
-      "epoch": 1.1105792245093347,
-      "grad_norm": 0.16395702958106995,
-      "learning_rate": 7.942535320373698e-05,
-      "loss": 0.0171,
-      "step": 290
-    },
-    {
-      "epoch": 1.1488750598372426,
-      "grad_norm": 0.29613885283470154,
-      "learning_rate": 7.759271445571715e-05,
-      "loss": 0.0089,
-      "step": 300
-    },
-    {
-      "epoch": 1.1871708951651507,
-      "grad_norm": 0.06282398104667664,
-      "learning_rate": 7.570513720966108e-05,
-      "loss": 0.0126,
-      "step": 310
-    },
-    {
-      "epoch": 1.2254667304930589,
-      "grad_norm": 0.10816850513219833,
-      "learning_rate": 7.376637972788082e-05,
-      "loss": 0.0128,
-      "step": 320
-    },
-    {
-      "epoch": 1.263762565820967,
-      "grad_norm": 0.16520057618618011,
-      "learning_rate": 7.178030217514113e-05,
-      "loss": 0.0116,
-      "step": 330
-    },
-    {
-      "epoch": 1.3020584011488752,
-      "grad_norm": 0.1243121325969696,
-      "learning_rate": 6.975085893287501e-05,
-      "loss": 0.0094,
-      "step": 340
-    },
-    {
-      "epoch": 1.340354236476783,
-      "grad_norm": 0.06126997992396355,
-      "learning_rate": 6.768209072580925e-05,
-      "loss": 0.0105,
-      "step": 350
-    },
-    {
-      "epoch": 1.3786500718046912,
-      "grad_norm": 0.04886842891573906,
-      "learning_rate": 6.557811657667586e-05,
-      "loss": 0.0094,
-      "step": 360
-    },
-    {
-      "epoch": 1.4169459071325994,
-      "grad_norm": 0.11320311576128006,
-      "learning_rate": 6.344312560502834e-05,
-      "loss": 0.0102,
-      "step": 370
-    },
-    {
-      "epoch": 1.4552417424605073,
-      "grad_norm": 0.11746253073215485,
-      "learning_rate": 6.128136868649156e-05,
-      "loss": 0.0173,
-      "step": 380
-    },
-    {
-      "epoch": 1.4935375777884154,
-      "grad_norm": 0.2587246894836426,
-      "learning_rate": 5.909714998905209e-05,
-      "loss": 0.0184,
-      "step": 390
-    },
-    {
-      "epoch": 1.5318334131163236,
-      "grad_norm": 0.07182590663433075,
-      "learning_rate": 5.6894818403240936e-05,
-      "loss": 0.0141,
-      "step": 400
-    },
-    {
-      "epoch": 1.5701292484442317,
-      "grad_norm": 0.061123911291360855,
-      "learning_rate": 5.467875888327112e-05,
-      "loss": 0.0104,
-      "step": 410
-    },
-    {
-      "epoch": 1.6084250837721399,
-      "grad_norm": 0.21772031486034393,
-      "learning_rate": 5.245338371637091e-05,
-      "loss": 0.0095,
-      "step": 420
-    },
-    {
-      "epoch": 1.6467209191000478,
-      "grad_norm": 0.04732087627053261,
-      "learning_rate": 5.022312373769547e-05,
-      "loss": 0.0129,
-      "step": 430
-    },
-    {
-      "epoch": 1.685016754427956,
-      "grad_norm": 0.07505133748054504,
-      "learning_rate": 4.7992419508308656e-05,
-      "loss": 0.016,
-      "step": 440
-    },
-    {
-      "epoch": 1.723312589755864,
-      "grad_norm": 0.2977347671985626,
-      "learning_rate": 4.576571247380014e-05,
-      "loss": 0.0115,
-      "step": 450
-    },
-    {
-      "epoch": 1.761608425083772,
-      "grad_norm": 0.06472886353731155,
-      "learning_rate": 4.354743612114123e-05,
-      "loss": 0.0111,
-      "step": 460
-    },
-    {
-      "epoch": 1.7999042604116804,
-      "grad_norm": 0.08027333766222,
-      "learning_rate": 4.134200715138681e-05,
-      "loss": 0.0117,
-      "step": 470
-    },
-    {
-      "epoch": 1.8382000957395883,
-      "grad_norm": 0.7646312713623047,
-      "learning_rate": 3.9153816685798947e-05,
-      "loss": 0.0143,
-      "step": 480
-    },
-    {
-      "epoch": 1.8764959310674965,
-      "grad_norm": 0.07349566370248795,
-      "learning_rate": 3.6987221522901e-05,
-      "loss": 0.0114,
-      "step": 490
-    },
-    {
-      "epoch": 1.9147917663954046,
-      "grad_norm": 0.18471819162368774,
-      "learning_rate": 3.4846535463870236e-05,
-      "loss": 0.0109,
-      "step": 500
-    },
-    {
-      "epoch": 1.9530876017233125,
-      "grad_norm": 0.06120637059211731,
-      "learning_rate": 3.2736020723540125e-05,
-      "loss": 0.0101,
-      "step": 510
-    },
-    {
-      "epoch": 1.9913834370512207,
-      "grad_norm": 0.06429634988307953,
-      "learning_rate": 3.065987944411397e-05,
-      "loss": 0.0123,
-      "step": 520
-    },
-    {
-      "epoch": 2.029679272379129,
-      "grad_norm": 0.2524162232875824,
-      "learning_rate": 2.8622245328485907e-05,
-      "loss": 0.0112,
-      "step": 530
-    },
-    {
-      "epoch": 2.0679751077070367,
-      "grad_norm": 0.05845191329717636,
-      "learning_rate": 2.6627175409828187e-05,
-      "loss": 0.0099,
-      "step": 540
-    },
-    {
-      "epoch": 2.106270943034945,
-      "grad_norm": 0.10983314365148544,
-      "learning_rate": 2.4678641973831838e-05,
-      "loss": 0.0111,
-      "step": 550
-    },
-    {
-      "epoch": 2.144566778362853,
-      "grad_norm": 0.02283252775669098,
-      "learning_rate": 2.27805246496837e-05,
-      "loss": 0.0112,
-      "step": 560
-    },
-    {
-      "epoch": 2.182862613690761,
-      "grad_norm": 0.3609371781349182,
-      "learning_rate": 2.0936602685527445e-05,
-      "loss": 0.0072,
-      "step": 570
-    },
-    {
-      "epoch": 2.2211584490186693,
-      "grad_norm": 0.042387451976537704,
-      "learning_rate": 1.9150547423788223e-05,
-      "loss": 0.0108,
-      "step": 580
-    },
-    {
-      "epoch": 2.2594542843465772,
-      "grad_norm": 0.19681565463542938,
-      "learning_rate": 1.742591499134321e-05,
-      "loss": 0.0146,
-      "step": 590
-    },
-    {
-      "epoch": 2.297750119674485,
-      "grad_norm": 0.06592544913291931,
-      "learning_rate": 1.5766139219092026e-05,
-      "loss": 0.0104,
-      "step": 600
-    },
-    {
-      "epoch": 2.3360459550023935,
-      "grad_norm": 0.051050640642642975,
-      "learning_rate": 1.4174524805024841e-05,
-      "loss": 0.0095,
-      "step": 610
-    },
-    {
-      "epoch": 2.3743417903303015,
-      "grad_norm": 0.04150964319705963,
-      "learning_rate": 1.2654240734400485e-05,
-      "loss": 0.009,
-      "step": 620
-    },
-    {
-      "epoch": 2.41263762565821,
-      "grad_norm": 0.07302859425544739,
-      "learning_rate": 1.1208313970135648e-05,
-      "loss": 0.0114,
-      "step": 630
-    },
-    {
-      "epoch": 2.4509334609861178,
-      "grad_norm": 0.021421028301119804,
-      "learning_rate": 9.83962342596776e-06,
-      "loss": 0.0099,
-      "step": 640
-    },
-    {
-      "epoch": 2.4892292963140257,
-      "grad_norm": 0.0014052694896236062,
-      "learning_rate": 8.550894234391255e-06,
-      "loss": 0.0124,
-      "step": 650
-    },
-    {
-      "epoch": 2.527525131641934,
-      "grad_norm": 0.03385864570736885,
-      "learning_rate": 7.344692320780156e-06,
-      "loss": 0.0103,
-      "step": 660
-    },
-    {
-      "epoch": 2.565820966969842,
-      "grad_norm": 0.042098745703697205,
-      "learning_rate": 6.223419294500199e-06,
-      "loss": 0.0095,
-      "step": 670
-    },
-    {
-      "epoch": 2.6041168022977503,
-      "grad_norm": 0.0516144335269928,
-      "learning_rate": 5.189307667182347e-06,
-      "loss": 0.0094,
-      "step": 680
-    },
-    {
-      "epoch": 2.6424126376256583,
-      "grad_norm": 0.04381686449050903,
-      "learning_rate": 4.244416407678586e-06,
-      "loss": 0.0053,
-      "step": 690
-    },
-    {
-      "epoch": 2.680708472953566,
-      "grad_norm": 0.03721212223172188,
-      "learning_rate": 3.390626842550265e-06,
-      "loss": 0.012,
-      "step": 700
-    },
-    {
-      "epoch": 2.7190043082814745,
-      "grad_norm": 0.038081198930740356,
-      "learning_rate": 2.629638910251153e-06,
-      "loss": 0.0067,
-      "step": 710
-    },
-    {
-      "epoch": 2.7573001436093825,
-      "grad_norm": 0.07790064066648483,
-      "learning_rate": 1.9629677764635312e-06,
-      "loss": 0.0097,
-      "step": 720
-    },
-    {
-      "epoch": 2.795595978937291,
-      "grad_norm": 0.03576493263244629,
-      "learning_rate": 1.3919408173262317e-06,
-      "loss": 0.0075,
-      "step": 730
-    },
-    {
-      "epoch": 2.8338918142651988,
-      "grad_norm": 0.07623250037431717,
-      "learning_rate": 9.176949765612453e-07,
-      "loss": 0.0089,
-      "step": 740
-    },
-    {
-      "epoch": 2.8721876495931067,
-      "grad_norm": 0.12562915682792664,
-      "learning_rate": 5.411745017609493e-07,
-      "loss": 0.0087,
-      "step": 750
-    },
-    {
-      "epoch": 2.9104834849210146,
-      "grad_norm": 0.034880924969911575,
-      "learning_rate": 2.631290643430817e-07,
-      "loss": 0.0102,
-      "step": 760
-    },
-    {
-      "epoch": 2.948779320248923,
-      "grad_norm": 0.041406504809856415,
-      "learning_rate": 8.411226691683593e-08,
-      "loss": 0.0088,
-      "step": 770
-    },
-    {
-      "epoch": 2.987075155576831,
-      "grad_norm": 0.052220020443201065,
-      "learning_rate": 4.4805410319148645e-09,
-      "loss": 0.0095,
-      "step": 780
-    }
-  ],
-  "logging_steps": 10,
-  "max_steps": 783,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
-  "save_steps": 3000,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": true
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 1.277525053111953e+19,
-  "train_batch_size": 3,
-  "trial_name": null,
-  "trial_params": null
-}

Distinguisher(RC)/checkpoint-783/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b360b992d8d24e161927e9679d955ca5f1abe1505a8a6c0e7fb266de3ef76c15
-size 5432

Distinguisher(RC)/runs/Feb10_11-35-54_autodl-container-c4f24fa8a4-699ef49e/events.out.tfevents.1739158604.autodl-container-c4f24fa8a4-699ef49e.1367.0

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3c867541c2eafb8ca182d612435a808bd3984030160112ff01534c01b4e698a3
-size 24531

Distinguisher(RC)/special_tokens_map.json

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

Distinguisher(RC)/tokenizer.model

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

Distinguisher(RC)/tokenizer_config.json

@@ -1,132 +0,0 @@
-{
-  "add_bos_token": false,
-  "add_eos_token": false,
-  "add_prefix_space": null,
-  "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": true,
-      "single_word": false,
-      "special": false
-    },
-    "32000": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32001": {
-      "content": "<|assistant|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32002": {
-      "content": "<|placeholder1|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32003": {
-      "content": "<|placeholder2|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32004": {
-      "content": "<|placeholder3|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32005": {
-      "content": "<|placeholder4|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32006": {
-      "content": "<|system|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32007": {
-      "content": "<|end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32008": {
-      "content": "<|placeholder5|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32009": {
-      "content": "<|placeholder6|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    },
-    "32010": {
-      "content": "<|user|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "bos_token": "<s>",
-  "chat_template": "{{ '<s>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|system|>\n' + system_message + '<|end|>\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|user|>\n' + content + '<|end|>\n<|assistant|>\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end|>' + '\n' }}{% endif %}{% endfor %}",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|end|>",
-  "legacy": false,
-  "model_max_length": 131072,
-  "pad_token": "<|endoftext|>",
-  "padding_side": "right",
-  "sp_model_kwargs": {},
-  "split_special_tokens": false,
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false
-}

Distinguisher(RC)/train_results.json

@@ -1,8 +0,0 @@
-{
-    "epoch": 2.998563906175203,
-    "total_flos": 1.277525053111953e+19,
-    "train_loss": 0.21499103556790342,
-    "train_runtime": 22786.7859,
-    "train_samples_per_second": 4.95,
-    "train_steps_per_second": 0.034
-}

Distinguisher(RC)/trainer_log.jsonl

@@ -1,79 +0,0 @@
-{"current_steps": 10, "total_steps": 783, "loss": 7.1401, "learning_rate": 1.2658227848101267e-05, "epoch": 0.03829583532790809, "percentage": 1.28, "elapsed_time": "0:04:47", "remaining_time": "6:10:37"}
-{"current_steps": 20, "total_steps": 783, "loss": 6.0679, "learning_rate": 2.5316455696202533e-05, "epoch": 0.07659167065581618, "percentage": 2.55, "elapsed_time": "0:09:45", "remaining_time": "6:12:34"}
-{"current_steps": 30, "total_steps": 783, "loss": 2.0361, "learning_rate": 3.79746835443038e-05, "epoch": 0.11488750598372427, "percentage": 3.83, "elapsed_time": "0:14:37", "remaining_time": "6:06:54"}
-{"current_steps": 40, "total_steps": 783, "loss": 0.2922, "learning_rate": 5.0632911392405066e-05, "epoch": 0.15318334131163236, "percentage": 5.11, "elapsed_time": "0:19:36", "remaining_time": "6:04:17"}
-{"current_steps": 50, "total_steps": 783, "loss": 0.0919, "learning_rate": 6.329113924050633e-05, "epoch": 0.19147917663954045, "percentage": 6.39, "elapsed_time": "0:24:30", "remaining_time": "5:59:11"}
-{"current_steps": 60, "total_steps": 783, "loss": 0.0652, "learning_rate": 7.59493670886076e-05, "epoch": 0.22977501196744854, "percentage": 7.66, "elapsed_time": "0:29:24", "remaining_time": "5:54:21"}
-{"current_steps": 70, "total_steps": 783, "loss": 0.065, "learning_rate": 8.860759493670887e-05, "epoch": 0.26807084729535663, "percentage": 8.94, "elapsed_time": "0:34:11", "remaining_time": "5:48:11"}
-{"current_steps": 80, "total_steps": 783, "loss": 0.0777, "learning_rate": 9.999950215549828e-05, "epoch": 0.3063666826232647, "percentage": 10.22, "elapsed_time": "0:39:11", "remaining_time": "5:44:26"}
-{"current_steps": 90, "total_steps": 783, "loss": 0.0447, "learning_rate": 9.993977281025862e-05, "epoch": 0.3446625179511728, "percentage": 11.49, "elapsed_time": "0:43:59", "remaining_time": "5:38:42"}
-{"current_steps": 100, "total_steps": 783, "loss": 0.0483, "learning_rate": 9.978061083707403e-05, "epoch": 0.3829583532790809, "percentage": 12.77, "elapsed_time": "0:48:47", "remaining_time": "5:33:14"}
-{"current_steps": 110, "total_steps": 783, "loss": 0.0358, "learning_rate": 9.952233313552917e-05, "epoch": 0.421254188606989, "percentage": 14.05, "elapsed_time": "0:53:38", "remaining_time": "5:28:14"}
-{"current_steps": 120, "total_steps": 783, "loss": 0.0294, "learning_rate": 9.916545394966561e-05, "epoch": 0.4595500239348971, "percentage": 15.33, "elapsed_time": "0:58:27", "remaining_time": "5:22:59"}
-{"current_steps": 130, "total_steps": 783, "loss": 0.025, "learning_rate": 9.871068384409573e-05, "epoch": 0.49784585926280517, "percentage": 16.6, "elapsed_time": "1:03:17", "remaining_time": "5:17:56"}
-{"current_steps": 140, "total_steps": 783, "loss": 0.0201, "learning_rate": 9.815892828923243e-05, "epoch": 0.5361416945907133, "percentage": 17.88, "elapsed_time": "1:08:07", "remaining_time": "5:12:53"}
-{"current_steps": 150, "total_steps": 783, "loss": 0.0192, "learning_rate": 9.751128585845156e-05, "epoch": 0.5744375299186214, "percentage": 19.16, "elapsed_time": "1:12:57", "remaining_time": "5:07:53"}
-{"current_steps": 160, "total_steps": 783, "loss": 0.0149, "learning_rate": 9.676904604077627e-05, "epoch": 0.6127333652465294, "percentage": 20.43, "elapsed_time": "1:17:45", "remaining_time": "5:02:48"}
-{"current_steps": 170, "total_steps": 783, "loss": 0.0148, "learning_rate": 9.593368667343905e-05, "epoch": 0.6510292005744376, "percentage": 21.71, "elapsed_time": "1:22:37", "remaining_time": "4:57:55"}
-{"current_steps": 180, "total_steps": 783, "loss": 0.016, "learning_rate": 9.500687099943233e-05, "epoch": 0.6893250359023456, "percentage": 22.99, "elapsed_time": "1:27:29", "remaining_time": "4:53:06"}
-{"current_steps": 190, "total_steps": 783, "loss": 0.0192, "learning_rate": 9.39904443559073e-05, "epoch": 0.7276208712302538, "percentage": 24.27, "elapsed_time": "1:32:14", "remaining_time": "4:47:52"}
-{"current_steps": 200, "total_steps": 783, "loss": 0.019, "learning_rate": 9.288643050001361e-05, "epoch": 0.7659167065581618, "percentage": 25.54, "elapsed_time": "1:37:00", "remaining_time": "4:42:46"}
-{"current_steps": 210, "total_steps": 783, "loss": 0.0207, "learning_rate": 9.16970275794961e-05, "epoch": 0.8042125418860699, "percentage": 26.82, "elapsed_time": "1:41:49", "remaining_time": "4:37:49"}
-{"current_steps": 220, "total_steps": 783, "loss": 0.0186, "learning_rate": 9.042460375607072e-05, "epoch": 0.842508377213978, "percentage": 28.1, "elapsed_time": "1:46:38", "remaining_time": "4:32:55"}
-{"current_steps": 230, "total_steps": 783, "loss": 0.0154, "learning_rate": 8.90716924902941e-05, "epoch": 0.8808042125418861, "percentage": 29.37, "elapsed_time": "1:51:22", "remaining_time": "4:27:46"}
-{"current_steps": 240, "total_steps": 783, "loss": 0.0179, "learning_rate": 8.764098749731479e-05, "epoch": 0.9191000478697942, "percentage": 30.65, "elapsed_time": "1:56:09", "remaining_time": "4:22:47"}
-{"current_steps": 250, "total_steps": 783, "loss": 0.0159, "learning_rate": 8.613533738354927e-05, "epoch": 0.9573958831977023, "percentage": 31.93, "elapsed_time": "2:01:06", "remaining_time": "4:18:11"}
-{"current_steps": 260, "total_steps": 783, "loss": 0.0136, "learning_rate": 8.455773997496174e-05, "epoch": 0.9956917185256103, "percentage": 33.21, "elapsed_time": "2:06:01", "remaining_time": "4:13:29"}
-{"current_steps": 270, "total_steps": 783, "loss": 0.0193, "learning_rate": 8.291133634824015e-05, "epoch": 1.0339875538535184, "percentage": 34.48, "elapsed_time": "2:10:49", "remaining_time": "4:08:34"}
-{"current_steps": 280, "total_steps": 783, "loss": 0.0173, "learning_rate": 8.119940457675268e-05, "epoch": 1.0722833891814265, "percentage": 35.76, "elapsed_time": "2:15:38", "remaining_time": "4:03:40"}
-{"current_steps": 290, "total_steps": 783, "loss": 0.0171, "learning_rate": 7.942535320373698e-05, "epoch": 1.1105792245093347, "percentage": 37.04, "elapsed_time": "2:20:28", "remaining_time": "3:58:49"}
-{"current_steps": 300, "total_steps": 783, "loss": 0.0089, "learning_rate": 7.759271445571715e-05, "epoch": 1.1488750598372426, "percentage": 38.31, "elapsed_time": "2:25:12", "remaining_time": "3:53:46"}
-{"current_steps": 310, "total_steps": 783, "loss": 0.0126, "learning_rate": 7.570513720966108e-05, "epoch": 1.1871708951651507, "percentage": 39.59, "elapsed_time": "2:30:05", "remaining_time": "3:49:00"}
-{"current_steps": 320, "total_steps": 783, "loss": 0.0128, "learning_rate": 7.376637972788082e-05, "epoch": 1.2254667304930589, "percentage": 40.87, "elapsed_time": "2:34:57", "remaining_time": "3:44:12"}
-{"current_steps": 330, "total_steps": 783, "loss": 0.0116, "learning_rate": 7.178030217514113e-05, "epoch": 1.263762565820967, "percentage": 42.15, "elapsed_time": "2:39:47", "remaining_time": "3:39:20"}
-{"current_steps": 340, "total_steps": 783, "loss": 0.0094, "learning_rate": 6.975085893287501e-05, "epoch": 1.3020584011488752, "percentage": 43.42, "elapsed_time": "2:44:42", "remaining_time": "3:34:36"}
-{"current_steps": 350, "total_steps": 783, "loss": 0.0105, "learning_rate": 6.768209072580925e-05, "epoch": 1.340354236476783, "percentage": 44.7, "elapsed_time": "2:49:38", "remaining_time": "3:29:52"}
-{"current_steps": 360, "total_steps": 783, "loss": 0.0094, "learning_rate": 6.557811657667586e-05, "epoch": 1.3786500718046912, "percentage": 45.98, "elapsed_time": "2:54:32", "remaining_time": "3:25:05"}
-{"current_steps": 370, "total_steps": 783, "loss": 0.0102, "learning_rate": 6.344312560502834e-05, "epoch": 1.4169459071325994, "percentage": 47.25, "elapsed_time": "2:59:21", "remaining_time": "3:20:11"}
-{"current_steps": 380, "total_steps": 783, "loss": 0.0173, "learning_rate": 6.128136868649156e-05, "epoch": 1.4552417424605073, "percentage": 48.53, "elapsed_time": "3:04:10", "remaining_time": "3:15:19"}
-{"current_steps": 390, "total_steps": 783, "loss": 0.0184, "learning_rate": 5.909714998905209e-05, "epoch": 1.4935375777884154, "percentage": 49.81, "elapsed_time": "3:08:55", "remaining_time": "3:10:22"}
-{"current_steps": 400, "total_steps": 783, "loss": 0.0141, "learning_rate": 5.6894818403240936e-05, "epoch": 1.5318334131163236, "percentage": 51.09, "elapsed_time": "3:13:42", "remaining_time": "3:05:28"}
-{"current_steps": 410, "total_steps": 783, "loss": 0.0104, "learning_rate": 5.467875888327112e-05, "epoch": 1.5701292484442317, "percentage": 52.36, "elapsed_time": "3:18:27", "remaining_time": "3:00:33"}
-{"current_steps": 420, "total_steps": 783, "loss": 0.0095, "learning_rate": 5.245338371637091e-05, "epoch": 1.6084250837721399, "percentage": 53.64, "elapsed_time": "3:23:17", "remaining_time": "2:55:42"}
-{"current_steps": 430, "total_steps": 783, "loss": 0.0129, "learning_rate": 5.022312373769547e-05, "epoch": 1.6467209191000478, "percentage": 54.92, "elapsed_time": "3:28:07", "remaining_time": "2:50:51"}
-{"current_steps": 440, "total_steps": 783, "loss": 0.016, "learning_rate": 4.7992419508308656e-05, "epoch": 1.685016754427956, "percentage": 56.19, "elapsed_time": "3:32:55", "remaining_time": "2:45:59"}
-{"current_steps": 450, "total_steps": 783, "loss": 0.0115, "learning_rate": 4.576571247380014e-05, "epoch": 1.723312589755864, "percentage": 57.47, "elapsed_time": "3:37:46", "remaining_time": "2:41:09"}
-{"current_steps": 460, "total_steps": 783, "loss": 0.0111, "learning_rate": 4.354743612114123e-05, "epoch": 1.761608425083772, "percentage": 58.75, "elapsed_time": "3:42:36", "remaining_time": "2:36:18"}
-{"current_steps": 470, "total_steps": 783, "loss": 0.0117, "learning_rate": 4.134200715138681e-05, "epoch": 1.7999042604116804, "percentage": 60.03, "elapsed_time": "3:47:28", "remaining_time": "2:31:29"}
-{"current_steps": 480, "total_steps": 783, "loss": 0.0143, "learning_rate": 3.9153816685798947e-05, "epoch": 1.8382000957395883, "percentage": 61.3, "elapsed_time": "3:52:20", "remaining_time": "2:26:39"}
-{"current_steps": 490, "total_steps": 783, "loss": 0.0114, "learning_rate": 3.6987221522901e-05, "epoch": 1.8764959310674965, "percentage": 62.58, "elapsed_time": "3:57:07", "remaining_time": "2:21:47"}
-{"current_steps": 500, "total_steps": 783, "loss": 0.0109, "learning_rate": 3.4846535463870236e-05, "epoch": 1.9147917663954046, "percentage": 63.86, "elapsed_time": "4:01:56", "remaining_time": "2:16:56"}
-{"current_steps": 510, "total_steps": 783, "loss": 0.0101, "learning_rate": 3.2736020723540125e-05, "epoch": 1.9530876017233125, "percentage": 65.13, "elapsed_time": "4:06:50", "remaining_time": "2:12:07"}
-{"current_steps": 520, "total_steps": 783, "loss": 0.0123, "learning_rate": 3.065987944411397e-05, "epoch": 1.9913834370512207, "percentage": 66.41, "elapsed_time": "4:11:42", "remaining_time": "2:07:18"}
-{"current_steps": 530, "total_steps": 783, "loss": 0.0112, "learning_rate": 2.8622245328485907e-05, "epoch": 2.029679272379129, "percentage": 67.69, "elapsed_time": "4:16:38", "remaining_time": "2:02:30"}
-{"current_steps": 540, "total_steps": 783, "loss": 0.0099, "learning_rate": 2.6627175409828187e-05, "epoch": 2.0679751077070367, "percentage": 68.97, "elapsed_time": "4:21:32", "remaining_time": "1:57:41"}
-{"current_steps": 550, "total_steps": 783, "loss": 0.0111, "learning_rate": 2.4678641973831838e-05, "epoch": 2.106270943034945, "percentage": 70.24, "elapsed_time": "4:26:27", "remaining_time": "1:52:52"}
-{"current_steps": 560, "total_steps": 783, "loss": 0.0112, "learning_rate": 2.27805246496837e-05, "epoch": 2.144566778362853, "percentage": 71.52, "elapsed_time": "4:31:23", "remaining_time": "1:48:04"}
-{"current_steps": 570, "total_steps": 783, "loss": 0.0072, "learning_rate": 2.0936602685527445e-05, "epoch": 2.182862613690761, "percentage": 72.8, "elapsed_time": "4:36:04", "remaining_time": "1:43:09"}
-{"current_steps": 580, "total_steps": 783, "loss": 0.0108, "learning_rate": 1.9150547423788223e-05, "epoch": 2.2211584490186693, "percentage": 74.07, "elapsed_time": "4:41:02", "remaining_time": "1:38:21"}
-{"current_steps": 590, "total_steps": 783, "loss": 0.0146, "learning_rate": 1.742591499134321e-05, "epoch": 2.2594542843465772, "percentage": 75.35, "elapsed_time": "4:45:47", "remaining_time": "1:33:29"}
-{"current_steps": 600, "total_steps": 783, "loss": 0.0104, "learning_rate": 1.5766139219092026e-05, "epoch": 2.297750119674485, "percentage": 76.63, "elapsed_time": "4:50:42", "remaining_time": "1:28:39"}
-{"current_steps": 610, "total_steps": 783, "loss": 0.0095, "learning_rate": 1.4174524805024841e-05, "epoch": 2.3360459550023935, "percentage": 77.91, "elapsed_time": "4:55:30", "remaining_time": "1:23:48"}
-{"current_steps": 620, "total_steps": 783, "loss": 0.009, "learning_rate": 1.2654240734400485e-05, "epoch": 2.3743417903303015, "percentage": 79.18, "elapsed_time": "5:00:16", "remaining_time": "1:18:56"}
-{"current_steps": 630, "total_steps": 783, "loss": 0.0114, "learning_rate": 1.1208313970135648e-05, "epoch": 2.41263762565821, "percentage": 80.46, "elapsed_time": "5:05:07", "remaining_time": "1:14:06"}
-{"current_steps": 640, "total_steps": 783, "loss": 0.0099, "learning_rate": 9.83962342596776e-06, "epoch": 2.4509334609861178, "percentage": 81.74, "elapsed_time": "5:10:13", "remaining_time": "1:09:19"}
-{"current_steps": 650, "total_steps": 783, "loss": 0.0124, "learning_rate": 8.550894234391255e-06, "epoch": 2.4892292963140257, "percentage": 83.01, "elapsed_time": "5:15:06", "remaining_time": "1:04:28"}
-{"current_steps": 660, "total_steps": 783, "loss": 0.0103, "learning_rate": 7.344692320780156e-06, "epoch": 2.527525131641934, "percentage": 84.29, "elapsed_time": "5:19:58", "remaining_time": "0:59:37"}
-{"current_steps": 670, "total_steps": 783, "loss": 0.0095, "learning_rate": 6.223419294500199e-06, "epoch": 2.565820966969842, "percentage": 85.57, "elapsed_time": "5:24:48", "remaining_time": "0:54:46"}
-{"current_steps": 680, "total_steps": 783, "loss": 0.0094, "learning_rate": 5.189307667182347e-06, "epoch": 2.6041168022977503, "percentage": 86.85, "elapsed_time": "5:29:36", "remaining_time": "0:49:55"}
-{"current_steps": 690, "total_steps": 783, "loss": 0.0053, "learning_rate": 4.244416407678586e-06, "epoch": 2.6424126376256583, "percentage": 88.12, "elapsed_time": "5:34:26", "remaining_time": "0:45:04"}
-{"current_steps": 700, "total_steps": 783, "loss": 0.012, "learning_rate": 3.390626842550265e-06, "epoch": 2.680708472953566, "percentage": 89.4, "elapsed_time": "5:39:12", "remaining_time": "0:40:13"}
-{"current_steps": 710, "total_steps": 783, "loss": 0.0067, "learning_rate": 2.629638910251153e-06, "epoch": 2.7190043082814745, "percentage": 90.68, "elapsed_time": "5:44:06", "remaining_time": "0:35:22"}
-{"current_steps": 720, "total_steps": 783, "loss": 0.0097, "learning_rate": 1.9629677764635312e-06, "epoch": 2.7573001436093825, "percentage": 91.95, "elapsed_time": "5:48:49", "remaining_time": "0:30:31"}
-{"current_steps": 730, "total_steps": 783, "loss": 0.0075, "learning_rate": 1.3919408173262317e-06, "epoch": 2.795595978937291, "percentage": 93.23, "elapsed_time": "5:53:43", "remaining_time": "0:25:40"}
-{"current_steps": 740, "total_steps": 783, "loss": 0.0089, "learning_rate": 9.176949765612453e-07, "epoch": 2.8338918142651988, "percentage": 94.51, "elapsed_time": "5:58:39", "remaining_time": "0:20:50"}
-{"current_steps": 750, "total_steps": 783, "loss": 0.0087, "learning_rate": 5.411745017609493e-07, "epoch": 2.8721876495931067, "percentage": 95.79, "elapsed_time": "6:03:30", "remaining_time": "0:15:59"}
-{"current_steps": 760, "total_steps": 783, "loss": 0.0102, "learning_rate": 2.631290643430817e-07, "epoch": 2.9104834849210146, "percentage": 97.06, "elapsed_time": "6:08:26", "remaining_time": "0:11:09"}
-{"current_steps": 770, "total_steps": 783, "loss": 0.0088, "learning_rate": 8.411226691683593e-08, "epoch": 2.948779320248923, "percentage": 98.34, "elapsed_time": "6:13:25", "remaining_time": "0:06:18"}
-{"current_steps": 780, "total_steps": 783, "loss": 0.0095, "learning_rate": 4.4805410319148645e-09, "epoch": 2.987075155576831, "percentage": 99.62, "elapsed_time": "6:18:15", "remaining_time": "0:01:27"}
-{"current_steps": 783, "total_steps": 783, "epoch": 2.998563906175203, "percentage": 100.0, "elapsed_time": "6:19:45", "remaining_time": "0:00:00"}

Distinguisher(RC)/trainer_state.json

@@ -1,588 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 2.998563906175203,
-  "eval_steps": 500,
-  "global_step": 783,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.03829583532790809,
-      "grad_norm": 12.114680290222168,
-      "learning_rate": 1.2658227848101267e-05,
-      "loss": 7.1401,
-      "step": 10
-    },
-    {
-      "epoch": 0.07659167065581618,
-      "grad_norm": 12.290201187133789,
-      "learning_rate": 2.5316455696202533e-05,
-      "loss": 6.0679,
-      "step": 20
-    },
-    {
-      "epoch": 0.11488750598372427,
-      "grad_norm": 2.9069294929504395,
-      "learning_rate": 3.79746835443038e-05,
-      "loss": 2.0361,
-      "step": 30
-    },
-    {
-      "epoch": 0.15318334131163236,
-      "grad_norm": 3.1070704460144043,
-      "learning_rate": 5.0632911392405066e-05,
-      "loss": 0.2922,
-      "step": 40
-    },
-    {
-      "epoch": 0.19147917663954045,
-      "grad_norm": 2.5955960750579834,
-      "learning_rate": 6.329113924050633e-05,
-      "loss": 0.0919,
-      "step": 50
-    },
-    {
-      "epoch": 0.22977501196744854,
-      "grad_norm": 3.1834232807159424,
-      "learning_rate": 7.59493670886076e-05,
-      "loss": 0.0652,
-      "step": 60
-    },
-    {
-      "epoch": 0.26807084729535663,
-      "grad_norm": 0.4948560893535614,
-      "learning_rate": 8.860759493670887e-05,
-      "loss": 0.065,
-      "step": 70
-    },
-    {
-      "epoch": 0.3063666826232647,
-      "grad_norm": 4.939356803894043,
-      "learning_rate": 9.999950215549828e-05,
-      "loss": 0.0777,
-      "step": 80
-    },
-    {
-      "epoch": 0.3446625179511728,
-      "grad_norm": 0.27955248951911926,
-      "learning_rate": 9.993977281025862e-05,
-      "loss": 0.0447,
-      "step": 90
-    },
-    {
-      "epoch": 0.3829583532790809,
-      "grad_norm": 0.9528509378433228,
-      "learning_rate": 9.978061083707403e-05,
-      "loss": 0.0483,
-      "step": 100
-    },
-    {
-      "epoch": 0.421254188606989,
-      "grad_norm": 0.26919859647750854,
-      "learning_rate": 9.952233313552917e-05,
-      "loss": 0.0358,
-      "step": 110
-    },
-    {
-      "epoch": 0.4595500239348971,
-      "grad_norm": 0.38545727729797363,
-      "learning_rate": 9.916545394966561e-05,
-      "loss": 0.0294,
-      "step": 120
-    },
-    {
-      "epoch": 0.49784585926280517,
-      "grad_norm": 0.13197395205497742,
-      "learning_rate": 9.871068384409573e-05,
-      "loss": 0.025,
-      "step": 130
-    },
-    {
-      "epoch": 0.5361416945907133,
-      "grad_norm": 0.40990087389945984,
-      "learning_rate": 9.815892828923243e-05,
-      "loss": 0.0201,
-      "step": 140
-    },
-    {
-      "epoch": 0.5744375299186214,
-      "grad_norm": 0.11029577255249023,
-      "learning_rate": 9.751128585845156e-05,
-      "loss": 0.0192,
-      "step": 150
-    },
-    {
-      "epoch": 0.6127333652465294,
-      "grad_norm": 0.12566852569580078,
-      "learning_rate": 9.676904604077627e-05,
-      "loss": 0.0149,
-      "step": 160
-    },
-    {
-      "epoch": 0.6510292005744376,
-      "grad_norm": 0.21772828698158264,
-      "learning_rate": 9.593368667343905e-05,
-      "loss": 0.0148,
-      "step": 170
-    },
-    {
-      "epoch": 0.6893250359023456,
-      "grad_norm": 0.3083280920982361,
-      "learning_rate": 9.500687099943233e-05,
-      "loss": 0.016,
-      "step": 180
-    },
-    {
-      "epoch": 0.7276208712302538,
-      "grad_norm": 0.577683687210083,
-      "learning_rate": 9.39904443559073e-05,
-      "loss": 0.0192,
-      "step": 190
-    },
-    {
-      "epoch": 0.7659167065581618,
-      "grad_norm": 0.11208537220954895,
-      "learning_rate": 9.288643050001361e-05,
-      "loss": 0.019,
-      "step": 200
-    },
-    {
-      "epoch": 0.8042125418860699,
-      "grad_norm": 0.11990990489721298,
-      "learning_rate": 9.16970275794961e-05,
-      "loss": 0.0207,
-      "step": 210
-    },
-    {
-      "epoch": 0.842508377213978,
-      "grad_norm": 0.23755091428756714,
-      "learning_rate": 9.042460375607072e-05,
-      "loss": 0.0186,
-      "step": 220
-    },
-    {
-      "epoch": 0.8808042125418861,
-      "grad_norm": 0.18448826670646667,
-      "learning_rate": 8.90716924902941e-05,
-      "loss": 0.0154,
-      "step": 230
-    },
-    {
-      "epoch": 0.9191000478697942,
-      "grad_norm": 0.2485741823911667,
-      "learning_rate": 8.764098749731479e-05,
-      "loss": 0.0179,
-      "step": 240
-    },
-    {
-      "epoch": 0.9573958831977023,
-      "grad_norm": 0.08395718783140182,
-      "learning_rate": 8.613533738354927e-05,
-      "loss": 0.0159,
-      "step": 250
-    },
-    {
-      "epoch": 0.9956917185256103,
-      "grad_norm": 0.03579740598797798,
-      "learning_rate": 8.455773997496174e-05,
-      "loss": 0.0136,
-      "step": 260
-    },
-    {
-      "epoch": 1.0339875538535184,
-      "grad_norm": 0.11624525487422943,
-      "learning_rate": 8.291133634824015e-05,
-      "loss": 0.0193,
-      "step": 270
-    },
-    {
-      "epoch": 1.0722833891814265,
-      "grad_norm": 0.2623934745788574,
-      "learning_rate": 8.119940457675268e-05,
-      "loss": 0.0173,
-      "step": 280
-    },
-    {
-      "epoch": 1.1105792245093347,
-      "grad_norm": 0.16395702958106995,
-      "learning_rate": 7.942535320373698e-05,
-      "loss": 0.0171,
-      "step": 290
-    },
-    {
-      "epoch": 1.1488750598372426,
-      "grad_norm": 0.29613885283470154,
-      "learning_rate": 7.759271445571715e-05,
-      "loss": 0.0089,
-      "step": 300
-    },
-    {
-      "epoch": 1.1871708951651507,
-      "grad_norm": 0.06282398104667664,
-      "learning_rate": 7.570513720966108e-05,
-      "loss": 0.0126,
-      "step": 310
-    },
-    {
-      "epoch": 1.2254667304930589,
-      "grad_norm": 0.10816850513219833,
-      "learning_rate": 7.376637972788082e-05,
-      "loss": 0.0128,
-      "step": 320
-    },
-    {
-      "epoch": 1.263762565820967,
-      "grad_norm": 0.16520057618618011,
-      "learning_rate": 7.178030217514113e-05,
-      "loss": 0.0116,
-      "step": 330
-    },
-    {
-      "epoch": 1.3020584011488752,
-      "grad_norm": 0.1243121325969696,
-      "learning_rate": 6.975085893287501e-05,
-      "loss": 0.0094,
-      "step": 340
-    },
-    {
-      "epoch": 1.340354236476783,
-      "grad_norm": 0.06126997992396355,
-      "learning_rate": 6.768209072580925e-05,
-      "loss": 0.0105,
-      "step": 350
-    },
-    {
-      "epoch": 1.3786500718046912,
-      "grad_norm": 0.04886842891573906,
-      "learning_rate": 6.557811657667586e-05,
-      "loss": 0.0094,
-      "step": 360
-    },
-    {
-      "epoch": 1.4169459071325994,
-      "grad_norm": 0.11320311576128006,
-      "learning_rate": 6.344312560502834e-05,
-      "loss": 0.0102,
-      "step": 370
-    },
-    {
-      "epoch": 1.4552417424605073,
-      "grad_norm": 0.11746253073215485,
-      "learning_rate": 6.128136868649156e-05,
-      "loss": 0.0173,
-      "step": 380
-    },
-    {
-      "epoch": 1.4935375777884154,
-      "grad_norm": 0.2587246894836426,
-      "learning_rate": 5.909714998905209e-05,
-      "loss": 0.0184,
-      "step": 390
-    },
-    {
-      "epoch": 1.5318334131163236,
-      "grad_norm": 0.07182590663433075,
-      "learning_rate": 5.6894818403240936e-05,
-      "loss": 0.0141,
-      "step": 400
-    },
-    {
-      "epoch": 1.5701292484442317,
-      "grad_norm": 0.061123911291360855,
-      "learning_rate": 5.467875888327112e-05,
-      "loss": 0.0104,
-      "step": 410
-    },
-    {
-      "epoch": 1.6084250837721399,
-      "grad_norm": 0.21772031486034393,
-      "learning_rate": 5.245338371637091e-05,
-      "loss": 0.0095,
-      "step": 420
-    },
-    {
-      "epoch": 1.6467209191000478,
-      "grad_norm": 0.04732087627053261,
-      "learning_rate": 5.022312373769547e-05,
-      "loss": 0.0129,
-      "step": 430
-    },
-    {
-      "epoch": 1.685016754427956,
-      "grad_norm": 0.07505133748054504,
-      "learning_rate": 4.7992419508308656e-05,
-      "loss": 0.016,
-      "step": 440
-    },
-    {
-      "epoch": 1.723312589755864,
-      "grad_norm": 0.2977347671985626,
-      "learning_rate": 4.576571247380014e-05,
-      "loss": 0.0115,
-      "step": 450
-    },
-    {
-      "epoch": 1.761608425083772,
-      "grad_norm": 0.06472886353731155,
-      "learning_rate": 4.354743612114123e-05,
-      "loss": 0.0111,
-      "step": 460
-    },
-    {
-      "epoch": 1.7999042604116804,
-      "grad_norm": 0.08027333766222,
-      "learning_rate": 4.134200715138681e-05,
-      "loss": 0.0117,
-      "step": 470
-    },
-    {
-      "epoch": 1.8382000957395883,
-      "grad_norm": 0.7646312713623047,
-      "learning_rate": 3.9153816685798947e-05,
-      "loss": 0.0143,
-      "step": 480
-    },
-    {
-      "epoch": 1.8764959310674965,
-      "grad_norm": 0.07349566370248795,
-      "learning_rate": 3.6987221522901e-05,
-      "loss": 0.0114,
-      "step": 490
-    },
-    {
-      "epoch": 1.9147917663954046,
-      "grad_norm": 0.18471819162368774,
-      "learning_rate": 3.4846535463870236e-05,
-      "loss": 0.0109,
-      "step": 500
-    },
-    {
-      "epoch": 1.9530876017233125,
-      "grad_norm": 0.06120637059211731,
-      "learning_rate": 3.2736020723540125e-05,
-      "loss": 0.0101,
-      "step": 510
-    },
-    {
-      "epoch": 1.9913834370512207,
-      "grad_norm": 0.06429634988307953,
-      "learning_rate": 3.065987944411397e-05,
-      "loss": 0.0123,
-      "step": 520
-    },
-    {
-      "epoch": 2.029679272379129,
-      "grad_norm": 0.2524162232875824,
-      "learning_rate": 2.8622245328485907e-05,
-      "loss": 0.0112,
-      "step": 530
-    },
-    {
-      "epoch": 2.0679751077070367,
-      "grad_norm": 0.05845191329717636,
-      "learning_rate": 2.6627175409828187e-05,
-      "loss": 0.0099,
-      "step": 540
-    },
-    {
-      "epoch": 2.106270943034945,
-      "grad_norm": 0.10983314365148544,
-      "learning_rate": 2.4678641973831838e-05,
-      "loss": 0.0111,
-      "step": 550
-    },
-    {
-      "epoch": 2.144566778362853,
-      "grad_norm": 0.02283252775669098,
-      "learning_rate": 2.27805246496837e-05,
-      "loss": 0.0112,
-      "step": 560
-    },
-    {
-      "epoch": 2.182862613690761,
-      "grad_norm": 0.3609371781349182,
-      "learning_rate": 2.0936602685527445e-05,
-      "loss": 0.0072,
-      "step": 570
-    },
-    {
-      "epoch": 2.2211584490186693,
-      "grad_norm": 0.042387451976537704,
-      "learning_rate": 1.9150547423788223e-05,
-      "loss": 0.0108,
-      "step": 580
-    },
-    {
-      "epoch": 2.2594542843465772,
-      "grad_norm": 0.19681565463542938,
-      "learning_rate": 1.742591499134321e-05,
-      "loss": 0.0146,
-      "step": 590
-    },
-    {
-      "epoch": 2.297750119674485,
-      "grad_norm": 0.06592544913291931,
-      "learning_rate": 1.5766139219092026e-05,
-      "loss": 0.0104,
-      "step": 600
-    },
-    {
-      "epoch": 2.3360459550023935,
-      "grad_norm": 0.051050640642642975,
-      "learning_rate": 1.4174524805024841e-05,
-      "loss": 0.0095,
-      "step": 610
-    },
-    {
-      "epoch": 2.3743417903303015,
-      "grad_norm": 0.04150964319705963,
-      "learning_rate": 1.2654240734400485e-05,
-      "loss": 0.009,
-      "step": 620
-    },
-    {
-      "epoch": 2.41263762565821,
-      "grad_norm": 0.07302859425544739,
-      "learning_rate": 1.1208313970135648e-05,
-      "loss": 0.0114,
-      "step": 630
-    },
-    {
-      "epoch": 2.4509334609861178,
-      "grad_norm": 0.021421028301119804,
-      "learning_rate": 9.83962342596776e-06,
-      "loss": 0.0099,
-      "step": 640
-    },
-    {
-      "epoch": 2.4892292963140257,
-      "grad_norm": 0.0014052694896236062,
-      "learning_rate": 8.550894234391255e-06,
-      "loss": 0.0124,
-      "step": 650
-    },
-    {
-      "epoch": 2.527525131641934,
-      "grad_norm": 0.03385864570736885,
-      "learning_rate": 7.344692320780156e-06,
-      "loss": 0.0103,
-      "step": 660
-    },
-    {
-      "epoch": 2.565820966969842,
-      "grad_norm": 0.042098745703697205,
-      "learning_rate": 6.223419294500199e-06,
-      "loss": 0.0095,
-      "step": 670
-    },
-    {
-      "epoch": 2.6041168022977503,
-      "grad_norm": 0.0516144335269928,
-      "learning_rate": 5.189307667182347e-06,
-      "loss": 0.0094,
-      "step": 680
-    },
-    {
-      "epoch": 2.6424126376256583,
-      "grad_norm": 0.04381686449050903,
-      "learning_rate": 4.244416407678586e-06,
-      "loss": 0.0053,
-      "step": 690
-    },
-    {
-      "epoch": 2.680708472953566,
-      "grad_norm": 0.03721212223172188,
-      "learning_rate": 3.390626842550265e-06,
-      "loss": 0.012,
-      "step": 700
-    },
-    {
-      "epoch": 2.7190043082814745,
-      "grad_norm": 0.038081198930740356,
-      "learning_rate": 2.629638910251153e-06,
-      "loss": 0.0067,
-      "step": 710
-    },
-    {
-      "epoch": 2.7573001436093825,
-      "grad_norm": 0.07790064066648483,
-      "learning_rate": 1.9629677764635312e-06,
-      "loss": 0.0097,
-      "step": 720
-    },
-    {
-      "epoch": 2.795595978937291,
-      "grad_norm": 0.03576493263244629,
-      "learning_rate": 1.3919408173262317e-06,
-      "loss": 0.0075,
-      "step": 730
-    },
-    {
-      "epoch": 2.8338918142651988,
-      "grad_norm": 0.07623250037431717,
-      "learning_rate": 9.176949765612453e-07,
-      "loss": 0.0089,
-      "step": 740
-    },
-    {
-      "epoch": 2.8721876495931067,
-      "grad_norm": 0.12562915682792664,
-      "learning_rate": 5.411745017609493e-07,
-      "loss": 0.0087,
-      "step": 750
-    },
-    {
-      "epoch": 2.9104834849210146,
-      "grad_norm": 0.034880924969911575,
-      "learning_rate": 2.631290643430817e-07,
-      "loss": 0.0102,
-      "step": 760
-    },
-    {
-      "epoch": 2.948779320248923,
-      "grad_norm": 0.041406504809856415,
-      "learning_rate": 8.411226691683593e-08,
-      "loss": 0.0088,
-      "step": 770
-    },
-    {
-      "epoch": 2.987075155576831,
-      "grad_norm": 0.052220020443201065,
-      "learning_rate": 4.4805410319148645e-09,
-      "loss": 0.0095,
-      "step": 780
-    },
-    {
-      "epoch": 2.998563906175203,
-      "step": 783,
-      "total_flos": 1.277525053111953e+19,
-      "train_loss": 0.21499103556790342,
-      "train_runtime": 22786.7859,
-      "train_samples_per_second": 4.95,
-      "train_steps_per_second": 0.034
-    }
-  ],
-  "logging_steps": 10,
-  "max_steps": 783,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
-  "save_steps": 3000,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": true
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 1.277525053111953e+19,
-  "train_batch_size": 3,
-  "trial_name": null,
-  "trial_params": null
-}

Distinguisher(RC)/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b360b992d8d24e161927e9679d955ca5f1abe1505a8a6c0e7fb266de3ef76c15
-size 5432