Upload folder using huggingface_hub

.gitattributes

@@ -46,3 +46,4 @@ checkpoint-step-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-step-1100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-step-1200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-step-1300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-step-1400/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-step-1400/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/qwen2.5-3b-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/qwen2.5-3b-unsloth-bnb-4bit
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# 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 0.19.1

checkpoint-step-1400/adapter_config.json

@@ -0,0 +1,52 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/qwen2.5-3b-unsloth-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "up_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-step-1400/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfb8e434089168515fcd6e326ed69780376b07e5b1dd77c127cb2d5c2e55f5e0
+size 239536272

checkpoint-step-1400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7ddb236750ecbd335cff7fdb3ab1a1096134c22fc700fb0c2999b4f53606611
+size 122203333

checkpoint-step-1400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce8e9b54cfb1e0a9cce010ae4a19fdc2a39e42bc335462238d75f5068953f37f
+size 14645

checkpoint-step-1400/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fba806492ab5aceed56cb83dcb3d9014855c8c87d2f01be0521dfc18ed4d8a9d
+size 1383

checkpoint-step-1400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8583a0423946422daa10508625c35e8476b3cba6bc3fb991eeafee478349f252
+size 1465

checkpoint-step-1400/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31
+size 11422356

checkpoint-step-1400/tokenizer_config.json

@@ -0,0 +1,201 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": true,
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<|PAD_TOKEN|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  }
+}

checkpoint-step-1400/trainer_state.json

@@ -0,0 +1,342 @@
+{
+  "best_global_step": 400,
+  "best_metric": 0.9676186442375183,
+  "best_model_checkpoint": "./outputs/checkpoint-400",
+  "epoch": 2.6315789473684212,
+  "eval_steps": 100,
+  "global_step": 1400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09398496240601503,
+      "grad_norm": 0.9101622104644775,
+      "learning_rate": 9.8e-05,
+      "loss": 0.7848518371582032,
+      "step": 50
+    },
+    {
+      "epoch": 0.18796992481203006,
+      "grad_norm": 0.8308438062667847,
+      "learning_rate": 9.683053040103493e-05,
+      "loss": 0.7757094573974609,
+      "step": 100
+    },
+    {
+      "epoch": 0.18796992481203006,
+      "eval_loss": 0.9840108752250671,
+      "eval_runtime": 81.3507,
+      "eval_samples_per_second": 5.814,
+      "eval_steps_per_second": 1.463,
+      "step": 100
+    },
+    {
+      "epoch": 0.2819548872180451,
+      "grad_norm": 1.0474584102630615,
+      "learning_rate": 9.359637774902976e-05,
+      "loss": 0.7674188995361328,
+      "step": 150
+    },
+    {
+      "epoch": 0.37593984962406013,
+      "grad_norm": 0.8780233860015869,
+      "learning_rate": 9.036222509702458e-05,
+      "loss": 0.7395731353759766,
+      "step": 200
+    },
+    {
+      "epoch": 0.37593984962406013,
+      "eval_loss": 0.9940316081047058,
+      "eval_runtime": 80.2928,
+      "eval_samples_per_second": 5.891,
+      "eval_steps_per_second": 1.482,
+      "step": 200
+    },
+    {
+      "epoch": 0.4699248120300752,
+      "grad_norm": 0.9176077246665955,
+      "learning_rate": 8.712807244501941e-05,
+      "loss": 0.7627955627441406,
+      "step": 250
+    },
+    {
+      "epoch": 0.5639097744360902,
+      "grad_norm": 0.8625491857528687,
+      "learning_rate": 8.389391979301423e-05,
+      "loss": 0.7164928436279296,
+      "step": 300
+    },
+    {
+      "epoch": 0.5639097744360902,
+      "eval_loss": 0.9823606014251709,
+      "eval_runtime": 80.8571,
+      "eval_samples_per_second": 5.85,
+      "eval_steps_per_second": 1.472,
+      "step": 300
+    },
+    {
+      "epoch": 0.6578947368421053,
+      "grad_norm": 0.8384292125701904,
+      "learning_rate": 8.065976714100906e-05,
+      "loss": 0.73987548828125,
+      "step": 350
+    },
+    {
+      "epoch": 0.7518796992481203,
+      "grad_norm": 0.8384448885917664,
+      "learning_rate": 7.742561448900388e-05,
+      "loss": 0.7277918243408203,
+      "step": 400
+    },
+    {
+      "epoch": 0.7518796992481203,
+      "eval_loss": 0.9676186442375183,
+      "eval_runtime": 80.4443,
+      "eval_samples_per_second": 5.88,
+      "eval_steps_per_second": 1.479,
+      "step": 400
+    },
+    {
+      "epoch": 0.8458646616541353,
+      "grad_norm": 0.866162121295929,
+      "learning_rate": 7.41914618369987e-05,
+      "loss": 0.7323916625976562,
+      "step": 450
+    },
+    {
+      "epoch": 0.9398496240601504,
+      "grad_norm": 0.8226180076599121,
+      "learning_rate": 7.095730918499353e-05,
+      "loss": 0.7260687255859375,
+      "step": 500
+    },
+    {
+      "epoch": 0.9398496240601504,
+      "eval_loss": 0.9678767919540405,
+      "eval_runtime": 80.5208,
+      "eval_samples_per_second": 5.874,
+      "eval_steps_per_second": 1.478,
+      "step": 500
+    },
+    {
+      "epoch": 1.0338345864661653,
+      "grad_norm": 1.0985685586929321,
+      "learning_rate": 6.772315653298837e-05,
+      "loss": 0.6786854553222657,
+      "step": 550
+    },
+    {
+      "epoch": 1.1278195488721805,
+      "grad_norm": 1.0968552827835083,
+      "learning_rate": 6.44890038809832e-05,
+      "loss": 0.580701789855957,
+      "step": 600
+    },
+    {
+      "epoch": 1.1278195488721805,
+      "eval_loss": 1.0256125926971436,
+      "eval_runtime": 80.6908,
+      "eval_samples_per_second": 5.862,
+      "eval_steps_per_second": 1.475,
+      "step": 600
+    },
+    {
+      "epoch": 1.2218045112781954,
+      "grad_norm": 1.0653274059295654,
+      "learning_rate": 6.1254851228978e-05,
+      "loss": 0.583438491821289,
+      "step": 650
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 1.1410211324691772,
+      "learning_rate": 5.802069857697283e-05,
+      "loss": 0.5911675262451171,
+      "step": 700
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "eval_loss": 1.0415176153182983,
+      "eval_runtime": 80.2742,
+      "eval_samples_per_second": 5.892,
+      "eval_steps_per_second": 1.482,
+      "step": 700
+    },
+    {
+      "epoch": 1.4097744360902256,
+      "grad_norm": 1.0943447351455688,
+      "learning_rate": 5.478654592496766e-05,
+      "loss": 0.6138821029663086,
+      "step": 750
+    },
+    {
+      "epoch": 1.5037593984962405,
+      "grad_norm": 1.004882574081421,
+      "learning_rate": 5.1552393272962485e-05,
+      "loss": 0.6031227111816406,
+      "step": 800
+    },
+    {
+      "epoch": 1.5037593984962405,
+      "eval_loss": 1.0161856412887573,
+      "eval_runtime": 80.0684,
+      "eval_samples_per_second": 5.907,
+      "eval_steps_per_second": 1.486,
+      "step": 800
+    },
+    {
+      "epoch": 1.5977443609022557,
+      "grad_norm": 1.0877087116241455,
+      "learning_rate": 4.831824062095731e-05,
+      "loss": 0.5991556930541992,
+      "step": 850
+    },
+    {
+      "epoch": 1.6917293233082706,
+      "grad_norm": 1.2106397151947021,
+      "learning_rate": 4.508408796895214e-05,
+      "loss": 0.6013988876342773,
+      "step": 900
+    },
+    {
+      "epoch": 1.6917293233082706,
+      "eval_loss": 1.0028849840164185,
+      "eval_runtime": 80.8781,
+      "eval_samples_per_second": 5.848,
+      "eval_steps_per_second": 1.471,
+      "step": 900
+    },
+    {
+      "epoch": 1.7857142857142856,
+      "grad_norm": 1.123062252998352,
+      "learning_rate": 4.1849935316946965e-05,
+      "loss": 0.592793083190918,
+      "step": 950
+    },
+    {
+      "epoch": 1.8796992481203008,
+      "grad_norm": 1.0219600200653076,
+      "learning_rate": 3.861578266494178e-05,
+      "loss": 0.6088079071044922,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8796992481203008,
+      "eval_loss": 1.0209505558013916,
+      "eval_runtime": 80.909,
+      "eval_samples_per_second": 5.846,
+      "eval_steps_per_second": 1.471,
+      "step": 1000
+    },
+    {
+      "epoch": 1.973684210526316,
+      "grad_norm": 1.03061044216156,
+      "learning_rate": 3.5381630012936615e-05,
+      "loss": 0.5962826919555664,
+      "step": 1050
+    },
+    {
+      "epoch": 2.0676691729323307,
+      "grad_norm": 1.2498968839645386,
+      "learning_rate": 3.214747736093144e-05,
+      "loss": 0.47724185943603514,
+      "step": 1100
+    },
+    {
+      "epoch": 2.0676691729323307,
+      "eval_loss": 1.1276904344558716,
+      "eval_runtime": 81.046,
+      "eval_samples_per_second": 5.836,
+      "eval_steps_per_second": 1.468,
+      "step": 1100
+    },
+    {
+      "epoch": 2.161654135338346,
+      "grad_norm": 1.1484302282333374,
+      "learning_rate": 2.8913324708926264e-05,
+      "loss": 0.4027834701538086,
+      "step": 1150
+    },
+    {
+      "epoch": 2.255639097744361,
+      "grad_norm": 1.2905447483062744,
+      "learning_rate": 2.5679172056921085e-05,
+      "loss": 0.4188160705566406,
+      "step": 1200
+    },
+    {
+      "epoch": 2.255639097744361,
+      "eval_loss": 1.1084345579147339,
+      "eval_runtime": 80.5472,
+      "eval_samples_per_second": 5.872,
+      "eval_steps_per_second": 1.477,
+      "step": 1200
+    },
+    {
+      "epoch": 2.3496240601503757,
+      "grad_norm": 1.2201945781707764,
+      "learning_rate": 2.2445019404915913e-05,
+      "loss": 0.48463031768798825,
+      "step": 1250
+    },
+    {
+      "epoch": 2.443609022556391,
+      "grad_norm": 1.1054600477218628,
+      "learning_rate": 1.927554980595084e-05,
+      "loss": 0.47764671325683594,
+      "step": 1300
+    },
+    {
+      "epoch": 2.443609022556391,
+      "eval_loss": 1.0965852737426758,
+      "eval_runtime": 80.71,
+      "eval_samples_per_second": 5.86,
+      "eval_steps_per_second": 1.474,
+      "step": 1300
+    },
+    {
+      "epoch": 2.537593984962406,
+      "grad_norm": 1.2809504270553589,
+      "learning_rate": 1.6041397153945667e-05,
+      "loss": 0.48986129760742186,
+      "step": 1350
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 1.064257264137268,
+      "learning_rate": 1.2807244501940493e-05,
+      "loss": 0.49002288818359374,
+      "step": 1400
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "eval_loss": 1.0940274000167847,
+      "eval_runtime": 80.7826,
+      "eval_samples_per_second": 5.855,
+      "eval_steps_per_second": 1.473,
+      "step": 1400
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1596,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.261036730292634e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-step-1400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c88f5ec73ab38f2f0a5bb321f3c58aaa6f716ae0e803b69ff493f9e0c43f221
+size 5713