Upload 12 files

README.md

@@ -0,0 +1,202 @@
+---
+base_model: VietAI/vit5-base
+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 0.13.0

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "VietAI/vit5-base",
+  "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": 8,
+  "lora_dropout": 0.2,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "encoder.block.0.layer.0.SelfAttention.q",
+    "decoder.block.0.layer.0.SelfAttention.q",
+    "encoder.block.0.layer.0.SelfAttention.v",
+    "decoder.block.0.layer.0.SelfAttention.k",
+    "encoder.block.0.layer.0.SelfAttention.k",
+    "decoder.block.0.layer.0.SelfAttention.v"
+  ],
+  "task_type": "SEQ2SEQ_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65888f0de5ec92baef29077564e77fedd9844936f582be94e36eaf7a08fa51a1
+size 1181328

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d99aa47f1373e797a786636450d11ce1bedf1e455ecc4f1adb13558d091ec34
+size 2366982

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:888d142298de620b1c05abd3048212502b637c5c30e2c251c2040a31bcf632ab
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:313d9e6a2e2433f67a0da276d33bd1e89d9178f1f5f7d57255849b717b7138ef
+size 1064

special_tokens_map.json

@@ -0,0 +1,103 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>"
+  ],
+  "eos_token": "</s>",
+  "pad_token": "</s>",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59986b62f9f0b90edafb9b073ea7b93d21114a5841219a1ea2399ade73f729c6
+size 820370

tokenizer_config.json

@@ -0,0 +1,902 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "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": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36000": {
+      "content": "<extra_id_95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36001": {
+      "content": "<extra_id_94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36002": {
+      "content": "<extra_id_93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36003": {
+      "content": "<extra_id_92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36004": {
+      "content": "<extra_id_91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36005": {
+      "content": "<extra_id_90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36006": {
+      "content": "<extra_id_89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36007": {
+      "content": "<extra_id_88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36008": {
+      "content": "<extra_id_87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36009": {
+      "content": "<extra_id_86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36010": {
+      "content": "<extra_id_85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36011": {
+      "content": "<extra_id_84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36012": {
+      "content": "<extra_id_83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36013": {
+      "content": "<extra_id_82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36014": {
+      "content": "<extra_id_81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36015": {
+      "content": "<extra_id_80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36016": {
+      "content": "<extra_id_79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36017": {
+      "content": "<extra_id_78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36018": {
+      "content": "<extra_id_77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36019": {
+      "content": "<extra_id_76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36020": {
+      "content": "<extra_id_75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36021": {
+      "content": "<extra_id_74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36022": {
+      "content": "<extra_id_73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36023": {
+      "content": "<extra_id_72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36024": {
+      "content": "<extra_id_71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36025": {
+      "content": "<extra_id_70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36026": {
+      "content": "<extra_id_69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36027": {
+      "content": "<extra_id_68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36028": {
+      "content": "<extra_id_67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36029": {
+      "content": "<extra_id_66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36030": {
+      "content": "<extra_id_65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36031": {
+      "content": "<extra_id_64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36032": {
+      "content": "<extra_id_63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36033": {
+      "content": "<extra_id_62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36034": {
+      "content": "<extra_id_61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36035": {
+      "content": "<extra_id_60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36036": {
+      "content": "<extra_id_59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36037": {
+      "content": "<extra_id_58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36038": {
+      "content": "<extra_id_57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36039": {
+      "content": "<extra_id_56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36040": {
+      "content": "<extra_id_55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36041": {
+      "content": "<extra_id_54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36042": {
+      "content": "<extra_id_53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36043": {
+      "content": "<extra_id_52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36044": {
+      "content": "<extra_id_51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36045": {
+      "content": "<extra_id_50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36046": {
+      "content": "<extra_id_49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36047": {
+      "content": "<extra_id_48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36048": {
+      "content": "<extra_id_47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36049": {
+      "content": "<extra_id_46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36050": {
+      "content": "<extra_id_45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36051": {
+      "content": "<extra_id_44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36052": {
+      "content": "<extra_id_43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36053": {
+      "content": "<extra_id_42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36054": {
+      "content": "<extra_id_41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36055": {
+      "content": "<extra_id_40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36056": {
+      "content": "<extra_id_39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36057": {
+      "content": "<extra_id_38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36058": {
+      "content": "<extra_id_37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36059": {
+      "content": "<extra_id_36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36060": {
+      "content": "<extra_id_35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36061": {
+      "content": "<extra_id_34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36062": {
+      "content": "<extra_id_33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36063": {
+      "content": "<extra_id_32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36064": {
+      "content": "<extra_id_31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36065": {
+      "content": "<extra_id_30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36066": {
+      "content": "<extra_id_29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36067": {
+      "content": "<extra_id_28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36068": {
+      "content": "<extra_id_27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36069": {
+      "content": "<extra_id_26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36070": {
+      "content": "<extra_id_25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36071": {
+      "content": "<extra_id_24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36072": {
+      "content": "<extra_id_23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36073": {
+      "content": "<extra_id_22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36074": {
+      "content": "<extra_id_21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36075": {
+      "content": "<extra_id_20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36076": {
+      "content": "<extra_id_19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36077": {
+      "content": "<extra_id_18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36078": {
+      "content": "<extra_id_17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36079": {
+      "content": "<extra_id_16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36080": {
+      "content": "<extra_id_15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36081": {
+      "content": "<extra_id_14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36082": {
+      "content": "<extra_id_13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36083": {
+      "content": "<extra_id_12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36084": {
+      "content": "<extra_id_11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36085": {
+      "content": "<extra_id_10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36086": {
+      "content": "<extra_id_9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36087": {
+      "content": "<extra_id_8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36088": {
+      "content": "<extra_id_7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36089": {
+      "content": "<extra_id_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36090": {
+      "content": "<extra_id_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36091": {
+      "content": "<extra_id_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36092": {
+      "content": "<extra_id_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36093": {
+      "content": "<extra_id_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36094": {
+      "content": "<extra_id_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36095": {
+      "content": "<extra_id_0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 96,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,635 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 8668,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.046146746654360866,
+      "grad_norm": 0.21824534237384796,
+      "learning_rate": 2.23760092272203e-06,
+      "loss": 3.136,
+      "step": 100
+    },
+    {
+      "epoch": 0.09229349330872173,
+      "grad_norm": 0.2850794494152069,
+      "learning_rate": 4.544405997693195e-06,
+      "loss": 3.1073,
+      "step": 200
+    },
+    {
+      "epoch": 0.1384402399630826,
+      "grad_norm": 0.36149144172668457,
+      "learning_rate": 6.828143021914648e-06,
+      "loss": 3.1035,
+      "step": 300
+    },
+    {
+      "epoch": 0.18458698661744347,
+      "grad_norm": 0.5060057640075684,
+      "learning_rate": 9.134948096885815e-06,
+      "loss": 3.106,
+      "step": 400
+    },
+    {
+      "epoch": 0.23073373327180433,
+      "grad_norm": 0.3851727247238159,
+      "learning_rate": 1.144175317185698e-05,
+      "loss": 3.0204,
+      "step": 500
+    },
+    {
+      "epoch": 0.2768804799261652,
+      "grad_norm": 0.30784064531326294,
+      "learning_rate": 1.3748558246828143e-05,
+      "loss": 2.9708,
+      "step": 600
+    },
+    {
+      "epoch": 0.3230272265805261,
+      "grad_norm": 0.6206746697425842,
+      "learning_rate": 1.605536332179931e-05,
+      "loss": 2.8294,
+      "step": 700
+    },
+    {
+      "epoch": 0.36917397323488693,
+      "grad_norm": 0.47670331597328186,
+      "learning_rate": 1.8362168396770474e-05,
+      "loss": 2.6824,
+      "step": 800
+    },
+    {
+      "epoch": 0.4153207198892478,
+      "grad_norm": 0.4056473672389984,
+      "learning_rate": 1.9925650557620818e-05,
+      "loss": 2.4481,
+      "step": 900
+    },
+    {
+      "epoch": 0.46146746654360865,
+      "grad_norm": 0.8275523781776428,
+      "learning_rate": 1.96692731701064e-05,
+      "loss": 2.0463,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5076142131979695,
+      "grad_norm": 0.5123036503791809,
+      "learning_rate": 1.9412895782591976e-05,
+      "loss": 1.9237,
+      "step": 1100
+    },
+    {
+      "epoch": 0.5537609598523304,
+      "grad_norm": 0.7184427976608276,
+      "learning_rate": 1.9156518395077554e-05,
+      "loss": 1.881,
+      "step": 1200
+    },
+    {
+      "epoch": 0.5999077065066912,
+      "grad_norm": 1.0534940958023071,
+      "learning_rate": 1.8900141007563134e-05,
+      "loss": 1.8219,
+      "step": 1300
+    },
+    {
+      "epoch": 0.6460544531610521,
+      "grad_norm": 0.9063017964363098,
+      "learning_rate": 1.8646327393923858e-05,
+      "loss": 1.7868,
+      "step": 1400
+    },
+    {
+      "epoch": 0.6922011998154131,
+      "grad_norm": 0.7229586839675903,
+      "learning_rate": 1.8389950006409436e-05,
+      "loss": 1.7581,
+      "step": 1500
+    },
+    {
+      "epoch": 0.7383479464697739,
+      "grad_norm": 0.6040017604827881,
+      "learning_rate": 1.8133572618895013e-05,
+      "loss": 1.7096,
+      "step": 1600
+    },
+    {
+      "epoch": 0.7844946931241348,
+      "grad_norm": 0.7014355659484863,
+      "learning_rate": 1.7877195231380594e-05,
+      "loss": 1.6372,
+      "step": 1700
+    },
+    {
+      "epoch": 0.8306414397784956,
+      "grad_norm": 0.45642441511154175,
+      "learning_rate": 1.762081784386617e-05,
+      "loss": 1.5638,
+      "step": 1800
+    },
+    {
+      "epoch": 0.8767881864328565,
+      "grad_norm": 0.7556698322296143,
+      "learning_rate": 1.7364440456351752e-05,
+      "loss": 1.5481,
+      "step": 1900
+    },
+    {
+      "epoch": 0.9229349330872173,
+      "grad_norm": 0.48637843132019043,
+      "learning_rate": 1.710806306883733e-05,
+      "loss": 1.4976,
+      "step": 2000
+    },
+    {
+      "epoch": 0.9690816797415782,
+      "grad_norm": 0.6813339591026306,
+      "learning_rate": 1.685168568132291e-05,
+      "loss": 1.4417,
+      "step": 2100
+    },
+    {
+      "epoch": 1.015228426395939,
+      "grad_norm": 1.094603180885315,
+      "learning_rate": 1.6595308293808488e-05,
+      "loss": 1.3938,
+      "step": 2200
+    },
+    {
+      "epoch": 1.0613751730503,
+      "grad_norm": 0.37147483229637146,
+      "learning_rate": 1.6338930906294065e-05,
+      "loss": 1.3497,
+      "step": 2300
+    },
+    {
+      "epoch": 1.1075219197046609,
+      "grad_norm": 0.2780097424983978,
+      "learning_rate": 1.6082553518779646e-05,
+      "loss": 1.3099,
+      "step": 2400
+    },
+    {
+      "epoch": 1.1536686663590217,
+      "grad_norm": 0.271342933177948,
+      "learning_rate": 1.5826176131265223e-05,
+      "loss": 1.285,
+      "step": 2500
+    },
+    {
+      "epoch": 1.1998154130133827,
+      "grad_norm": 0.27299413084983826,
+      "learning_rate": 1.55697987437508e-05,
+      "loss": 1.2614,
+      "step": 2600
+    },
+    {
+      "epoch": 1.2459621596677435,
+      "grad_norm": 0.29231297969818115,
+      "learning_rate": 1.531342135623638e-05,
+      "loss": 1.2308,
+      "step": 2700
+    },
+    {
+      "epoch": 1.2921089063221043,
+      "grad_norm": 0.22232797741889954,
+      "learning_rate": 1.505704396872196e-05,
+      "loss": 1.1944,
+      "step": 2800
+    },
+    {
+      "epoch": 1.338255652976465,
+      "grad_norm": 0.9203324913978577,
+      "learning_rate": 1.480066658120754e-05,
+      "loss": 1.1544,
+      "step": 2900
+    },
+    {
+      "epoch": 1.384402399630826,
+      "grad_norm": 0.19580288231372833,
+      "learning_rate": 1.4544289193693117e-05,
+      "loss": 1.0996,
+      "step": 3000
+    },
+    {
+      "epoch": 1.430549146285187,
+      "grad_norm": 0.42558759450912476,
+      "learning_rate": 1.4287911806178696e-05,
+      "loss": 1.0759,
+      "step": 3100
+    },
+    {
+      "epoch": 1.4766958929395477,
+      "grad_norm": 0.24304209649562836,
+      "learning_rate": 1.4031534418664275e-05,
+      "loss": 1.0637,
+      "step": 3200
+    },
+    {
+      "epoch": 1.5228426395939088,
+      "grad_norm": 0.25986990332603455,
+      "learning_rate": 1.3775157031149852e-05,
+      "loss": 1.0446,
+      "step": 3300
+    },
+    {
+      "epoch": 1.5689893862482696,
+      "grad_norm": 0.20725102722644806,
+      "learning_rate": 1.3518779643635433e-05,
+      "loss": 1.0384,
+      "step": 3400
+    },
+    {
+      "epoch": 1.6151361329026304,
+      "grad_norm": 0.18936870992183685,
+      "learning_rate": 1.3262402256121012e-05,
+      "loss": 1.0139,
+      "step": 3500
+    },
+    {
+      "epoch": 1.6612828795569912,
+      "grad_norm": 0.19966499507427216,
+      "learning_rate": 1.300602486860659e-05,
+      "loss": 1.0058,
+      "step": 3600
+    },
+    {
+      "epoch": 1.707429626211352,
+      "grad_norm": 0.30528759956359863,
+      "learning_rate": 1.2749647481092169e-05,
+      "loss": 0.9838,
+      "step": 3700
+    },
+    {
+      "epoch": 1.753576372865713,
+      "grad_norm": 0.2316664308309555,
+      "learning_rate": 1.2493270093577748e-05,
+      "loss": 0.9904,
+      "step": 3800
+    },
+    {
+      "epoch": 1.7997231195200738,
+      "grad_norm": 0.2217002511024475,
+      "learning_rate": 1.2236892706063325e-05,
+      "loss": 0.9735,
+      "step": 3900
+    },
+    {
+      "epoch": 1.8458698661744348,
+      "grad_norm": 0.2654038369655609,
+      "learning_rate": 1.1980515318548904e-05,
+      "loss": 0.9804,
+      "step": 4000
+    },
+    {
+      "epoch": 1.8920166128287956,
+      "grad_norm": 0.20543397963047028,
+      "learning_rate": 1.1724137931034483e-05,
+      "loss": 0.9424,
+      "step": 4100
+    },
+    {
+      "epoch": 1.9381633594831564,
+      "grad_norm": 0.24414564669132233,
+      "learning_rate": 1.1467760543520064e-05,
+      "loss": 0.9353,
+      "step": 4200
+    },
+    {
+      "epoch": 1.9843101061375172,
+      "grad_norm": 0.19333013892173767,
+      "learning_rate": 1.1211383156005641e-05,
+      "loss": 0.9374,
+      "step": 4300
+    },
+    {
+      "epoch": 2.030456852791878,
+      "grad_norm": 0.20063996315002441,
+      "learning_rate": 1.095500576849122e-05,
+      "loss": 0.9409,
+      "step": 4400
+    },
+    {
+      "epoch": 2.076603599446239,
+      "grad_norm": 0.4319429397583008,
+      "learning_rate": 1.0698628380976798e-05,
+      "loss": 0.93,
+      "step": 4500
+    },
+    {
+      "epoch": 2.1227503461006,
+      "grad_norm": 0.21358811855316162,
+      "learning_rate": 1.0442250993462377e-05,
+      "loss": 0.9231,
+      "step": 4600
+    },
+    {
+      "epoch": 2.168897092754961,
+      "grad_norm": 0.2252470701932907,
+      "learning_rate": 1.0185873605947956e-05,
+      "loss": 0.9267,
+      "step": 4700
+    },
+    {
+      "epoch": 2.2150438394093217,
+      "grad_norm": 0.6058911681175232,
+      "learning_rate": 9.929496218433535e-06,
+      "loss": 0.902,
+      "step": 4800
+    },
+    {
+      "epoch": 2.2611905860636825,
+      "grad_norm": 0.27027812600135803,
+      "learning_rate": 9.673118830919114e-06,
+      "loss": 0.8908,
+      "step": 4900
+    },
+    {
+      "epoch": 2.3073373327180433,
+      "grad_norm": 0.3116415739059448,
+      "learning_rate": 9.416741443404692e-06,
+      "loss": 0.8971,
+      "step": 5000
+    },
+    {
+      "epoch": 2.353484079372404,
+      "grad_norm": 0.2324889898300171,
+      "learning_rate": 9.160364055890272e-06,
+      "loss": 0.8927,
+      "step": 5100
+    },
+    {
+      "epoch": 2.3996308260267654,
+      "grad_norm": 0.18322697281837463,
+      "learning_rate": 8.90398666837585e-06,
+      "loss": 0.8844,
+      "step": 5200
+    },
+    {
+      "epoch": 2.445777572681126,
+      "grad_norm": 1.4241108894348145,
+      "learning_rate": 8.650173054736572e-06,
+      "loss": 0.883,
+      "step": 5300
+    },
+    {
+      "epoch": 2.491924319335487,
+      "grad_norm": 0.22246557474136353,
+      "learning_rate": 8.393795667222153e-06,
+      "loss": 0.8841,
+      "step": 5400
+    },
+    {
+      "epoch": 2.5380710659898478,
+      "grad_norm": 0.19322210550308228,
+      "learning_rate": 8.13741827970773e-06,
+      "loss": 0.89,
+      "step": 5500
+    },
+    {
+      "epoch": 2.5842178126442086,
+      "grad_norm": 0.20664915442466736,
+      "learning_rate": 7.881040892193309e-06,
+      "loss": 0.8762,
+      "step": 5600
+    },
+    {
+      "epoch": 2.6303645592985694,
+      "grad_norm": 0.19776581227779388,
+      "learning_rate": 7.624663504678887e-06,
+      "loss": 0.8649,
+      "step": 5700
+    },
+    {
+      "epoch": 2.67651130595293,
+      "grad_norm": 0.7888526916503906,
+      "learning_rate": 7.368286117164467e-06,
+      "loss": 0.8678,
+      "step": 5800
+    },
+    {
+      "epoch": 2.722658052607291,
+      "grad_norm": 0.7994652390480042,
+      "learning_rate": 7.1119087296500455e-06,
+      "loss": 0.7896,
+      "step": 5900
+    },
+    {
+      "epoch": 2.768804799261652,
+      "grad_norm": 0.2278624325990677,
+      "learning_rate": 6.855531342135624e-06,
+      "loss": 0.7324,
+      "step": 6000
+    },
+    {
+      "epoch": 2.814951545916013,
+      "grad_norm": 0.24736915528774261,
+      "learning_rate": 6.599153954621203e-06,
+      "loss": 0.7139,
+      "step": 6100
+    },
+    {
+      "epoch": 2.861098292570374,
+      "grad_norm": 0.22141049802303314,
+      "learning_rate": 6.342776567106782e-06,
+      "loss": 0.7116,
+      "step": 6200
+    },
+    {
+      "epoch": 2.9072450392247347,
+      "grad_norm": 0.21581608057022095,
+      "learning_rate": 6.08639917959236e-06,
+      "loss": 0.7185,
+      "step": 6300
+    },
+    {
+      "epoch": 2.9533917858790955,
+      "grad_norm": 0.27274981141090393,
+      "learning_rate": 5.830021792077939e-06,
+      "loss": 0.7114,
+      "step": 6400
+    },
+    {
+      "epoch": 2.9995385325334563,
+      "grad_norm": 0.4279099106788635,
+      "learning_rate": 5.5736444045635175e-06,
+      "loss": 0.6974,
+      "step": 6500
+    },
+    {
+      "epoch": 3.045685279187817,
+      "grad_norm": 0.4010777473449707,
+      "learning_rate": 5.3172670170490966e-06,
+      "loss": 0.7089,
+      "step": 6600
+    },
+    {
+      "epoch": 3.0918320258421783,
+      "grad_norm": 0.4470697343349457,
+      "learning_rate": 5.060889629534676e-06,
+      "loss": 0.6895,
+      "step": 6700
+    },
+    {
+      "epoch": 3.137978772496539,
+      "grad_norm": 0.534737229347229,
+      "learning_rate": 4.804512242020255e-06,
+      "loss": 0.709,
+      "step": 6800
+    },
+    {
+      "epoch": 3.1841255191509,
+      "grad_norm": 0.3858148157596588,
+      "learning_rate": 4.548134854505833e-06,
+      "loss": 0.7008,
+      "step": 6900
+    },
+    {
+      "epoch": 3.2302722658052607,
+      "grad_norm": 4.884620189666748,
+      "learning_rate": 4.291757466991412e-06,
+      "loss": 0.6926,
+      "step": 7000
+    },
+    {
+      "epoch": 3.2764190124596215,
+      "grad_norm": 0.44127726554870605,
+      "learning_rate": 4.03538007947699e-06,
+      "loss": 0.6986,
+      "step": 7100
+    },
+    {
+      "epoch": 3.3225657591139823,
+      "grad_norm": 1.2448310852050781,
+      "learning_rate": 3.7790026919625694e-06,
+      "loss": 0.6884,
+      "step": 7200
+    },
+    {
+      "epoch": 3.368712505768343,
+      "grad_norm": 0.8101204633712769,
+      "learning_rate": 3.522625304448148e-06,
+      "loss": 0.6851,
+      "step": 7300
+    },
+    {
+      "epoch": 3.4148592524227044,
+      "grad_norm": 0.5153388381004333,
+      "learning_rate": 3.2662479169337267e-06,
+      "loss": 0.6938,
+      "step": 7400
+    },
+    {
+      "epoch": 3.461005999077065,
+      "grad_norm": 0.33079493045806885,
+      "learning_rate": 3.0098705294193053e-06,
+      "loss": 0.6948,
+      "step": 7500
+    },
+    {
+      "epoch": 3.507152745731426,
+      "grad_norm": 1.0203328132629395,
+      "learning_rate": 2.7534931419048844e-06,
+      "loss": 0.6855,
+      "step": 7600
+    },
+    {
+      "epoch": 3.553299492385787,
+      "grad_norm": 0.3520820140838623,
+      "learning_rate": 2.4971157543904627e-06,
+      "loss": 0.6849,
+      "step": 7700
+    },
+    {
+      "epoch": 3.5994462390401476,
+      "grad_norm": 0.28180956840515137,
+      "learning_rate": 2.2407383668760417e-06,
+      "loss": 0.699,
+      "step": 7800
+    },
+    {
+      "epoch": 3.6455929856945084,
+      "grad_norm": 0.33973556756973267,
+      "learning_rate": 1.9843609793616204e-06,
+      "loss": 0.6756,
+      "step": 7900
+    },
+    {
+      "epoch": 3.6917397323488697,
+      "grad_norm": 0.3416615128517151,
+      "learning_rate": 1.7279835918471993e-06,
+      "loss": 0.685,
+      "step": 8000
+    },
+    {
+      "epoch": 3.7378864790032305,
+      "grad_norm": 0.7213825583457947,
+      "learning_rate": 1.4716062043327781e-06,
+      "loss": 0.6764,
+      "step": 8100
+    },
+    {
+      "epoch": 3.7840332256575913,
+      "grad_norm": 0.5637441873550415,
+      "learning_rate": 1.2152288168183566e-06,
+      "loss": 0.6896,
+      "step": 8200
+    },
+    {
+      "epoch": 3.830179972311952,
+      "grad_norm": 0.4190536141395569,
+      "learning_rate": 9.588514293039355e-07,
+      "loss": 0.675,
+      "step": 8300
+    },
+    {
+      "epoch": 3.876326718966313,
+      "grad_norm": 0.37957823276519775,
+      "learning_rate": 7.024740417895142e-07,
+      "loss": 0.6767,
+      "step": 8400
+    },
+    {
+      "epoch": 3.9224734656206737,
+      "grad_norm": 0.5404504537582397,
+      "learning_rate": 4.4609665427509294e-07,
+      "loss": 0.695,
+      "step": 8500
+    },
+    {
+      "epoch": 3.9686202122750345,
+      "grad_norm": 14.911314964294434,
+      "learning_rate": 1.8971926676067174e-07,
+      "loss": 0.6794,
+      "step": 8600
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 8668,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.884583671986995e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f25f4c63676c8f67c641355c20226b66c56f1324579ddcaea18b93da2d7de52
+size 5432