Upload folder using huggingface_hub

sft/checkpoint-2100/README.md

@@ -0,0 +1,206 @@
+---
+base_model: Itau-Unibanco/NorBERTo-base
+library_name: peft
+tags:
+- base_model:adapter:Itau-Unibanco/NorBERTo-base
+- lora
+- transformers
+---
+
+# 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 0.20.0

sft/checkpoint-2100/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Itau-Unibanco/NorBERTo-base",
+  "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,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.20.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "Wi",
+    "Wqkv",
+    "Wo"
+  ],
+  "target_parameters": null,
+  "task_type": "FEATURE_EXTRACTION",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

sft/checkpoint-2100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa6452c598bf09450dc4e6e4e42cfd12950bcb51e453f9fc3edc3a6ce7543675
+size 13538528

sft/checkpoint-2100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:594eb334c2061b0cca8d0fe62c30972fdd5a8c48ace71e351a86e1d2b7efedfe
+size 27204427

sft/checkpoint-2100/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0a4ac69d11987afc3d20a7e53a27edd4d897de8c8d284de9cf197ec4fe10472
+size 14917

sft/checkpoint-2100/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a7d31b3394f0ab5e7389598c4f44645c7a6d186d89517101aba0ed13db69962
+size 1383

sft/checkpoint-2100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad78a57deb251ac755d617e09e0d0c13238c1b4829580ddd1e0f44f1c04e2833
+size 1465

sft/checkpoint-2100/sft/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Itau-Unibanco/NorBERTo-base",
+  "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": [
+    "classifier",
+    "classifier",
+    "score"
+  ],
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.20.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "Wi",
+    "Wqkv",
+    "Wo"
+  ],
+  "target_parameters": null,
+  "task_type": "SEQ_CLS",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

sft/checkpoint-2100/sft/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ee703e9eaeaa5465460f7dc8f0467c805bc604374df97f7161b19ce540b156a
+size 13547940

sft/checkpoint-2100/tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "[SEP]",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 8192,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "tokenizer_class": "TokenizersBackend",
+  "truncation_side": "right",
+  "unk_token": "[UNK]"
+}

sft/checkpoint-2100/trainer_state.json

@@ -0,0 +1,1154 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.381060391267366,
+  "eval_steps": 150,
+  "global_step": 2100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01701162461015027,
+      "grad_norm": 116.99359893798828,
+      "learning_rate": 4.666666666666667e-06,
+      "loss": 39.077762858072916,
+      "step": 15
+    },
+    {
+      "epoch": 0.03402324922030054,
+      "grad_norm": 114.67162322998047,
+      "learning_rate": 9.666666666666667e-06,
+      "loss": 37.629154459635416,
+      "step": 30
+    },
+    {
+      "epoch": 0.05103487383045081,
+      "grad_norm": 78.71202850341797,
+      "learning_rate": 1.4666666666666668e-05,
+      "loss": 36.40402018229167,
+      "step": 45
+    },
+    {
+      "epoch": 0.06804649844060108,
+      "grad_norm": 77.94384002685547,
+      "learning_rate": 1.9666666666666666e-05,
+      "loss": 35.03992513020833,
+      "step": 60
+    },
+    {
+      "epoch": 0.08505812305075135,
+      "grad_norm": 69.6011734008789,
+      "learning_rate": 2.466666666666667e-05,
+      "loss": 34.81482747395833,
+      "step": 75
+    },
+    {
+      "epoch": 0.10206974766090161,
+      "grad_norm": 74.6609878540039,
+      "learning_rate": 2.9666666666666672e-05,
+      "loss": 33.83201497395833,
+      "step": 90
+    },
+    {
+      "epoch": 0.11908137227105188,
+      "grad_norm": 73.47967529296875,
+      "learning_rate": 3.466666666666667e-05,
+      "loss": 34.1611328125,
+      "step": 105
+    },
+    {
+      "epoch": 0.13609299688120216,
+      "grad_norm": 57.3227424621582,
+      "learning_rate": 3.966666666666667e-05,
+      "loss": 33.17495524088542,
+      "step": 120
+    },
+    {
+      "epoch": 0.15310462149135243,
+      "grad_norm": 41.92803955078125,
+      "learning_rate": 4.466666666666667e-05,
+      "loss": 33.14850056966146,
+      "step": 135
+    },
+    {
+      "epoch": 0.1701162461015027,
+      "grad_norm": 57.70565414428711,
+      "learning_rate": 4.966666666666667e-05,
+      "loss": 33.152496337890625,
+      "step": 150
+    },
+    {
+      "epoch": 0.1701162461015027,
+      "eval_accuracy": 0.519298245614035,
+      "eval_loss": 1.9665578603744507,
+      "eval_macro_f1": 0.43657905964809113,
+      "eval_runtime": 7.6538,
+      "eval_samples_per_second": 74.472,
+      "eval_steps_per_second": 9.407,
+      "step": 150
+    },
+    {
+      "epoch": 0.18712787071165296,
+      "grad_norm": 63.17024612426758,
+      "learning_rate": 4.940323955669225e-05,
+      "loss": 31.66871541341146,
+      "step": 165
+    },
+    {
+      "epoch": 0.20413949532180323,
+      "grad_norm": 73.78040313720703,
+      "learning_rate": 4.8763853367433935e-05,
+      "loss": 31.002229817708333,
+      "step": 180
+    },
+    {
+      "epoch": 0.2211511199319535,
+      "grad_norm": 46.99962615966797,
+      "learning_rate": 4.812446717817562e-05,
+      "loss": 31.49439900716146,
+      "step": 195
+    },
+    {
+      "epoch": 0.23816274454210376,
+      "grad_norm": 59.367454528808594,
+      "learning_rate": 4.748508098891731e-05,
+      "loss": 30.110245768229166,
+      "step": 210
+    },
+    {
+      "epoch": 0.25517436915225405,
+      "grad_norm": 65.87191009521484,
+      "learning_rate": 4.6845694799659e-05,
+      "loss": 31.120613606770835,
+      "step": 225
+    },
+    {
+      "epoch": 0.2721859937624043,
+      "grad_norm": 54.601192474365234,
+      "learning_rate": 4.620630861040069e-05,
+      "loss": 30.689495849609376,
+      "step": 240
+    },
+    {
+      "epoch": 0.2891976183725546,
+      "grad_norm": 85.62554931640625,
+      "learning_rate": 4.5566922421142375e-05,
+      "loss": 28.9639892578125,
+      "step": 255
+    },
+    {
+      "epoch": 0.30620924298270485,
+      "grad_norm": 55.505699157714844,
+      "learning_rate": 4.492753623188406e-05,
+      "loss": 29.698612467447916,
+      "step": 270
+    },
+    {
+      "epoch": 0.3232208675928551,
+      "grad_norm": 48.24406051635742,
+      "learning_rate": 4.428815004262575e-05,
+      "loss": 28.051249186197918,
+      "step": 285
+    },
+    {
+      "epoch": 0.3402324922030054,
+      "grad_norm": 83.22586822509766,
+      "learning_rate": 4.364876385336744e-05,
+      "loss": 27.165751139322918,
+      "step": 300
+    },
+    {
+      "epoch": 0.3402324922030054,
+      "eval_accuracy": 0.6140350877192983,
+      "eval_loss": 1.7097147703170776,
+      "eval_macro_f1": 0.5762605966740592,
+      "eval_runtime": 3.4179,
+      "eval_samples_per_second": 166.769,
+      "eval_steps_per_second": 21.066,
+      "step": 300
+    },
+    {
+      "epoch": 0.35724411681315565,
+      "grad_norm": 60.6512451171875,
+      "learning_rate": 4.300937766410913e-05,
+      "loss": 27.327327473958334,
+      "step": 315
+    },
+    {
+      "epoch": 0.3742557414233059,
+      "grad_norm": 75.39328002929688,
+      "learning_rate": 4.2369991474850815e-05,
+      "loss": 28.38462931315104,
+      "step": 330
+    },
+    {
+      "epoch": 0.3912673660334562,
+      "grad_norm": 60.53544235229492,
+      "learning_rate": 4.17306052855925e-05,
+      "loss": 28.571195475260417,
+      "step": 345
+    },
+    {
+      "epoch": 0.40827899064360645,
+      "grad_norm": 66.51234436035156,
+      "learning_rate": 4.109121909633419e-05,
+      "loss": 27.315740966796874,
+      "step": 360
+    },
+    {
+      "epoch": 0.4252906152537567,
+      "grad_norm": 71.48542785644531,
+      "learning_rate": 4.045183290707588e-05,
+      "loss": 26.424430338541665,
+      "step": 375
+    },
+    {
+      "epoch": 0.442302239863907,
+      "grad_norm": 65.96041107177734,
+      "learning_rate": 3.981244671781757e-05,
+      "loss": 26.818721516927084,
+      "step": 390
+    },
+    {
+      "epoch": 0.45931386447405725,
+      "grad_norm": 96.44197082519531,
+      "learning_rate": 3.9173060528559255e-05,
+      "loss": 27.456418863932292,
+      "step": 405
+    },
+    {
+      "epoch": 0.4763254890842075,
+      "grad_norm": 74.46075439453125,
+      "learning_rate": 3.8533674339300943e-05,
+      "loss": 27.342032877604165,
+      "step": 420
+    },
+    {
+      "epoch": 0.4933371136943578,
+      "grad_norm": 98.2132339477539,
+      "learning_rate": 3.789428815004263e-05,
+      "loss": 27.26170654296875,
+      "step": 435
+    },
+    {
+      "epoch": 0.5103487383045081,
+      "grad_norm": 66.33806610107422,
+      "learning_rate": 3.725490196078432e-05,
+      "loss": 26.62706298828125,
+      "step": 450
+    },
+    {
+      "epoch": 0.5103487383045081,
+      "eval_accuracy": 0.6473684210526316,
+      "eval_loss": 1.612095832824707,
+      "eval_macro_f1": 0.6036091764418378,
+      "eval_runtime": 3.4226,
+      "eval_samples_per_second": 166.541,
+      "eval_steps_per_second": 21.037,
+      "step": 450
+    },
+    {
+      "epoch": 0.5273603629146584,
+      "grad_norm": 59.41883087158203,
+      "learning_rate": 3.661551577152601e-05,
+      "loss": 25.6656494140625,
+      "step": 465
+    },
+    {
+      "epoch": 0.5443719875248086,
+      "grad_norm": 86.57988739013672,
+      "learning_rate": 3.5976129582267696e-05,
+      "loss": 25.688761393229168,
+      "step": 480
+    },
+    {
+      "epoch": 0.5613836121349589,
+      "grad_norm": 87.54814147949219,
+      "learning_rate": 3.5336743393009384e-05,
+      "loss": 26.806388346354165,
+      "step": 495
+    },
+    {
+      "epoch": 0.5783952367451092,
+      "grad_norm": 65.40018463134766,
+      "learning_rate": 3.469735720375107e-05,
+      "loss": 25.533500162760415,
+      "step": 510
+    },
+    {
+      "epoch": 0.5954068613552594,
+      "grad_norm": 65.12799072265625,
+      "learning_rate": 3.405797101449276e-05,
+      "loss": 26.228350830078124,
+      "step": 525
+    },
+    {
+      "epoch": 0.6124184859654097,
+      "grad_norm": 65.55587768554688,
+      "learning_rate": 3.341858482523445e-05,
+      "loss": 26.634810384114584,
+      "step": 540
+    },
+    {
+      "epoch": 0.62943011057556,
+      "grad_norm": 68.18641662597656,
+      "learning_rate": 3.2779198635976136e-05,
+      "loss": 25.533231608072917,
+      "step": 555
+    },
+    {
+      "epoch": 0.6464417351857102,
+      "grad_norm": 80.25837707519531,
+      "learning_rate": 3.2139812446717824e-05,
+      "loss": 24.925142415364583,
+      "step": 570
+    },
+    {
+      "epoch": 0.6634533597958605,
+      "grad_norm": 58.9185905456543,
+      "learning_rate": 3.150042625745951e-05,
+      "loss": 24.743680826822917,
+      "step": 585
+    },
+    {
+      "epoch": 0.6804649844060108,
+      "grad_norm": 59.13557815551758,
+      "learning_rate": 3.08610400682012e-05,
+      "loss": 25.899686686197917,
+      "step": 600
+    },
+    {
+      "epoch": 0.6804649844060108,
+      "eval_accuracy": 0.6421052631578947,
+      "eval_loss": 1.5752904415130615,
+      "eval_macro_f1": 0.6148540921288014,
+      "eval_runtime": 3.4091,
+      "eval_samples_per_second": 167.201,
+      "eval_steps_per_second": 21.12,
+      "step": 600
+    },
+    {
+      "epoch": 0.697476609016161,
+      "grad_norm": 63.18887710571289,
+      "learning_rate": 3.0221653878942884e-05,
+      "loss": 25.722517903645834,
+      "step": 615
+    },
+    {
+      "epoch": 0.7144882336263113,
+      "grad_norm": 81.7510757446289,
+      "learning_rate": 2.9582267689684573e-05,
+      "loss": 24.722237141927085,
+      "step": 630
+    },
+    {
+      "epoch": 0.7314998582364616,
+      "grad_norm": 59.331199645996094,
+      "learning_rate": 2.894288150042626e-05,
+      "loss": 25.852589925130207,
+      "step": 645
+    },
+    {
+      "epoch": 0.7485114828466118,
+      "grad_norm": 82.33928680419922,
+      "learning_rate": 2.830349531116795e-05,
+      "loss": 25.581608072916666,
+      "step": 660
+    },
+    {
+      "epoch": 0.7655231074567621,
+      "grad_norm": 73.93915557861328,
+      "learning_rate": 2.7664109121909637e-05,
+      "loss": 24.140205891927085,
+      "step": 675
+    },
+    {
+      "epoch": 0.7825347320669124,
+      "grad_norm": 88.01911926269531,
+      "learning_rate": 2.7024722932651325e-05,
+      "loss": 25.460465494791666,
+      "step": 690
+    },
+    {
+      "epoch": 0.7995463566770626,
+      "grad_norm": 74.82182312011719,
+      "learning_rate": 2.6385336743393013e-05,
+      "loss": 25.53566691080729,
+      "step": 705
+    },
+    {
+      "epoch": 0.8165579812872129,
+      "grad_norm": 53.480384826660156,
+      "learning_rate": 2.57459505541347e-05,
+      "loss": 24.06074422200521,
+      "step": 720
+    },
+    {
+      "epoch": 0.8335696058973632,
+      "grad_norm": 62.765567779541016,
+      "learning_rate": 2.510656436487639e-05,
+      "loss": 25.66954142252604,
+      "step": 735
+    },
+    {
+      "epoch": 0.8505812305075134,
+      "grad_norm": 61.93996047973633,
+      "learning_rate": 2.4467178175618073e-05,
+      "loss": 25.64231160481771,
+      "step": 750
+    },
+    {
+      "epoch": 0.8505812305075134,
+      "eval_accuracy": 0.6666666666666666,
+      "eval_loss": 1.4923547506332397,
+      "eval_macro_f1": 0.634289650129149,
+      "eval_runtime": 3.4068,
+      "eval_samples_per_second": 167.313,
+      "eval_steps_per_second": 21.134,
+      "step": 750
+    },
+    {
+      "epoch": 0.8675928551176637,
+      "grad_norm": 88.9131851196289,
+      "learning_rate": 2.382779198635976e-05,
+      "loss": 25.273152669270832,
+      "step": 765
+    },
+    {
+      "epoch": 0.884604479727814,
+      "grad_norm": 103.49991607666016,
+      "learning_rate": 2.318840579710145e-05,
+      "loss": 25.633394368489583,
+      "step": 780
+    },
+    {
+      "epoch": 0.9016161043379642,
+      "grad_norm": 71.47494506835938,
+      "learning_rate": 2.2549019607843138e-05,
+      "loss": 24.569466145833335,
+      "step": 795
+    },
+    {
+      "epoch": 0.9186277289481145,
+      "grad_norm": 84.61474609375,
+      "learning_rate": 2.1909633418584826e-05,
+      "loss": 24.982352701822915,
+      "step": 810
+    },
+    {
+      "epoch": 0.9356393535582648,
+      "grad_norm": 106.77224731445312,
+      "learning_rate": 2.1270247229326514e-05,
+      "loss": 23.428892008463542,
+      "step": 825
+    },
+    {
+      "epoch": 0.952650978168415,
+      "grad_norm": 64.02266693115234,
+      "learning_rate": 2.06308610400682e-05,
+      "loss": 23.625968424479165,
+      "step": 840
+    },
+    {
+      "epoch": 0.9696626027785653,
+      "grad_norm": 83.47174835205078,
+      "learning_rate": 1.999147485080989e-05,
+      "loss": 24.876424153645832,
+      "step": 855
+    },
+    {
+      "epoch": 0.9866742273887156,
+      "grad_norm": 68.72810363769531,
+      "learning_rate": 1.9352088661551578e-05,
+      "loss": 23.115681966145832,
+      "step": 870
+    },
+    {
+      "epoch": 1.00340232492203,
+      "grad_norm": 52.63280487060547,
+      "learning_rate": 1.8712702472293266e-05,
+      "loss": 23.462247721354167,
+      "step": 885
+    },
+    {
+      "epoch": 1.0204139495321802,
+      "grad_norm": 54.332237243652344,
+      "learning_rate": 1.8073316283034954e-05,
+      "loss": 25.237931315104166,
+      "step": 900
+    },
+    {
+      "epoch": 1.0204139495321802,
+      "eval_accuracy": 0.6631578947368421,
+      "eval_loss": 1.4844019412994385,
+      "eval_macro_f1": 0.6347159169539845,
+      "eval_runtime": 3.3664,
+      "eval_samples_per_second": 169.319,
+      "eval_steps_per_second": 21.388,
+      "step": 900
+    },
+    {
+      "epoch": 1.0374255741423306,
+      "grad_norm": 76.4985580444336,
+      "learning_rate": 1.7433930093776642e-05,
+      "loss": 25.129193115234376,
+      "step": 915
+    },
+    {
+      "epoch": 1.0544371987524808,
+      "grad_norm": 63.44844436645508,
+      "learning_rate": 1.679454390451833e-05,
+      "loss": 25.12100626627604,
+      "step": 930
+    },
+    {
+      "epoch": 1.0714488233626311,
+      "grad_norm": 85.40037536621094,
+      "learning_rate": 1.6155157715260018e-05,
+      "loss": 24.0731689453125,
+      "step": 945
+    },
+    {
+      "epoch": 1.0884604479727813,
+      "grad_norm": 61.12846755981445,
+      "learning_rate": 1.5515771526001706e-05,
+      "loss": 23.815816243489582,
+      "step": 960
+    },
+    {
+      "epoch": 1.1054720725829317,
+      "grad_norm": 88.95614624023438,
+      "learning_rate": 1.4876385336743392e-05,
+      "loss": 23.149064127604166,
+      "step": 975
+    },
+    {
+      "epoch": 1.1224836971930818,
+      "grad_norm": 81.11243438720703,
+      "learning_rate": 1.423699914748508e-05,
+      "loss": 24.921358235677083,
+      "step": 990
+    },
+    {
+      "epoch": 1.1394953218032322,
+      "grad_norm": 89.6662826538086,
+      "learning_rate": 1.3597612958226768e-05,
+      "loss": 24.148970540364584,
+      "step": 1005
+    },
+    {
+      "epoch": 1.1565069464133826,
+      "grad_norm": 76.58106231689453,
+      "learning_rate": 1.2958226768968456e-05,
+      "loss": 23.3828125,
+      "step": 1020
+    },
+    {
+      "epoch": 1.1735185710235327,
+      "grad_norm": 57.90241622924805,
+      "learning_rate": 1.2318840579710146e-05,
+      "loss": 23.80557861328125,
+      "step": 1035
+    },
+    {
+      "epoch": 1.190530195633683,
+      "grad_norm": 78.67855072021484,
+      "learning_rate": 1.1679454390451834e-05,
+      "loss": 25.015262858072916,
+      "step": 1050
+    },
+    {
+      "epoch": 1.190530195633683,
+      "eval_accuracy": 0.6771929824561403,
+      "eval_loss": 1.4616774320602417,
+      "eval_macro_f1": 0.6469672228058898,
+      "eval_runtime": 3.3981,
+      "eval_samples_per_second": 167.739,
+      "eval_steps_per_second": 21.188,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2075418202438333,
+      "grad_norm": NaN,
+      "learning_rate": 1.104006820119352e-05,
+      "loss": 24.526371256510416,
+      "step": 1065
+    },
+    {
+      "epoch": 1.2245534448539837,
+      "grad_norm": 94.34043884277344,
+      "learning_rate": 1.0400682011935209e-05,
+      "loss": 24.23281453450521,
+      "step": 1080
+    },
+    {
+      "epoch": 1.2415650694641338,
+      "grad_norm": 84.55120086669922,
+      "learning_rate": 9.761295822676897e-06,
+      "loss": 23.37388916015625,
+      "step": 1095
+    },
+    {
+      "epoch": 1.258576694074284,
+      "grad_norm": 98.98963928222656,
+      "learning_rate": 9.121909633418585e-06,
+      "loss": 24.879107666015624,
+      "step": 1110
+    },
+    {
+      "epoch": 1.2755883186844343,
+      "grad_norm": 93.77626037597656,
+      "learning_rate": 8.482523444160273e-06,
+      "loss": 23.596321614583335,
+      "step": 1125
+    },
+    {
+      "epoch": 1.2925999432945847,
+      "grad_norm": 76.52169036865234,
+      "learning_rate": 7.84313725490196e-06,
+      "loss": 23.6485595703125,
+      "step": 1140
+    },
+    {
+      "epoch": 1.3096115679047349,
+      "grad_norm": 64.10005950927734,
+      "learning_rate": 7.203751065643649e-06,
+      "loss": 23.198685709635416,
+      "step": 1155
+    },
+    {
+      "epoch": 1.3266231925148853,
+      "grad_norm": 61.74102783203125,
+      "learning_rate": 6.564364876385337e-06,
+      "loss": 22.906901041666668,
+      "step": 1170
+    },
+    {
+      "epoch": 1.3436348171250354,
+      "grad_norm": 68.70774841308594,
+      "learning_rate": 5.924978687127026e-06,
+      "loss": 23.642818196614584,
+      "step": 1185
+    },
+    {
+      "epoch": 1.3606464417351858,
+      "grad_norm": 105.86067199707031,
+      "learning_rate": 5.285592497868714e-06,
+      "loss": 23.631290690104166,
+      "step": 1200
+    },
+    {
+      "epoch": 1.3606464417351858,
+      "eval_accuracy": 0.6684210526315789,
+      "eval_loss": 1.4395803213119507,
+      "eval_macro_f1": 0.6398363484455968,
+      "eval_runtime": 3.3938,
+      "eval_samples_per_second": 167.951,
+      "eval_steps_per_second": 21.215,
+      "step": 1200
+    },
+    {
+      "epoch": 1.377658066345336,
+      "grad_norm": 74.67951965332031,
+      "learning_rate": 1.7038413878562578e-05,
+      "loss": 23.69179484049479,
+      "step": 1215
+    },
+    {
+      "epoch": 1.3946696909554863,
+      "grad_norm": 66.90929412841797,
+      "learning_rate": 1.657372986369269e-05,
+      "loss": 24.378173828125,
+      "step": 1230
+    },
+    {
+      "epoch": 1.4116813155656365,
+      "grad_norm": 72.71094512939453,
+      "learning_rate": 1.61090458488228e-05,
+      "loss": 25.47337443033854,
+      "step": 1245
+    },
+    {
+      "epoch": 1.4286929401757869,
+      "grad_norm": 82.03230285644531,
+      "learning_rate": 1.5644361833952914e-05,
+      "loss": 24.95899658203125,
+      "step": 1260
+    },
+    {
+      "epoch": 1.445704564785937,
+      "grad_norm": 86.57196044921875,
+      "learning_rate": 1.5179677819083023e-05,
+      "loss": 24.54622802734375,
+      "step": 1275
+    },
+    {
+      "epoch": 1.4627161893960874,
+      "grad_norm": 74.7414321899414,
+      "learning_rate": 1.4714993804213136e-05,
+      "loss": 23.085076904296876,
+      "step": 1290
+    },
+    {
+      "epoch": 1.4797278140062375,
+      "grad_norm": 94.59770202636719,
+      "learning_rate": 1.4250309789343247e-05,
+      "loss": 23.9911865234375,
+      "step": 1305
+    },
+    {
+      "epoch": 1.496739438616388,
+      "grad_norm": 101.66040802001953,
+      "learning_rate": 1.378562577447336e-05,
+      "loss": 23.332171630859374,
+      "step": 1320
+    },
+    {
+      "epoch": 1.5137510632265383,
+      "grad_norm": 62.254207611083984,
+      "learning_rate": 1.332094175960347e-05,
+      "loss": 23.564457194010416,
+      "step": 1335
+    },
+    {
+      "epoch": 1.5307626878366885,
+      "grad_norm": 70.31668090820312,
+      "learning_rate": 1.2856257744733583e-05,
+      "loss": 23.473478190104167,
+      "step": 1350
+    },
+    {
+      "epoch": 1.5307626878366885,
+      "eval_accuracy": 0.6789473684210526,
+      "eval_loss": 1.4255586862564087,
+      "eval_macro_f1": 0.6559084859040256,
+      "eval_runtime": 7.8053,
+      "eval_samples_per_second": 73.028,
+      "eval_steps_per_second": 9.225,
+      "step": 1350
+    },
+    {
+      "epoch": 1.5477743124468386,
+      "grad_norm": 64.91326904296875,
+      "learning_rate": 1.2391573729863694e-05,
+      "loss": 22.909114583333334,
+      "step": 1365
+    },
+    {
+      "epoch": 1.564785937056989,
+      "grad_norm": 126.73609924316406,
+      "learning_rate": 1.1926889714993805e-05,
+      "loss": 22.4288818359375,
+      "step": 1380
+    },
+    {
+      "epoch": 1.5817975616671394,
+      "grad_norm": 89.65287780761719,
+      "learning_rate": 1.1462205700123916e-05,
+      "loss": 23.543758138020834,
+      "step": 1395
+    },
+    {
+      "epoch": 1.5988091862772895,
+      "grad_norm": 78.0611343383789,
+      "learning_rate": 1.0997521685254029e-05,
+      "loss": 23.460017903645834,
+      "step": 1410
+    },
+    {
+      "epoch": 1.6158208108874397,
+      "grad_norm": 60.02608108520508,
+      "learning_rate": 1.053283767038414e-05,
+      "loss": 23.610856119791666,
+      "step": 1425
+    },
+    {
+      "epoch": 1.63283243549759,
+      "grad_norm": 66.4963607788086,
+      "learning_rate": 1.006815365551425e-05,
+      "loss": 23.6200439453125,
+      "step": 1440
+    },
+    {
+      "epoch": 1.6498440601077404,
+      "grad_norm": 96.63013458251953,
+      "learning_rate": 9.603469640644363e-06,
+      "loss": 23.953694661458332,
+      "step": 1455
+    },
+    {
+      "epoch": 1.6668556847178906,
+      "grad_norm": 67.95073699951172,
+      "learning_rate": 9.138785625774474e-06,
+      "loss": 23.530977376302083,
+      "step": 1470
+    },
+    {
+      "epoch": 1.6838673093280407,
+      "grad_norm": 98.09580993652344,
+      "learning_rate": 8.674101610904585e-06,
+      "loss": 22.67149454752604,
+      "step": 1485
+    },
+    {
+      "epoch": 1.7008789339381911,
+      "grad_norm": 85.86138916015625,
+      "learning_rate": 8.209417596034696e-06,
+      "loss": 24.940730794270834,
+      "step": 1500
+    },
+    {
+      "epoch": 1.7008789339381911,
+      "eval_accuracy": 0.6754385964912281,
+      "eval_loss": 1.419843316078186,
+      "eval_macro_f1": 0.6513890829522841,
+      "eval_runtime": 3.4776,
+      "eval_samples_per_second": 163.906,
+      "eval_steps_per_second": 20.704,
+      "step": 1500
+    },
+    {
+      "epoch": 1.7178905585483415,
+      "grad_norm": 87.5401611328125,
+      "learning_rate": 7.744733581164808e-06,
+      "loss": 24.91673583984375,
+      "step": 1515
+    },
+    {
+      "epoch": 1.7349021831584917,
+      "grad_norm": 88.96635437011719,
+      "learning_rate": 7.280049566294919e-06,
+      "loss": 23.793229166666666,
+      "step": 1530
+    },
+    {
+      "epoch": 1.7519138077686418,
+      "grad_norm": 58.651832580566406,
+      "learning_rate": 6.815365551425032e-06,
+      "loss": 22.266153971354168,
+      "step": 1545
+    },
+    {
+      "epoch": 1.7689254323787922,
+      "grad_norm": 59.3929443359375,
+      "learning_rate": 6.350681536555144e-06,
+      "loss": 23.80609130859375,
+      "step": 1560
+    },
+    {
+      "epoch": 1.7859370569889426,
+      "grad_norm": 106.14991760253906,
+      "learning_rate": 5.885997521685254e-06,
+      "loss": 24.066265869140626,
+      "step": 1575
+    },
+    {
+      "epoch": 1.8029486815990927,
+      "grad_norm": 101.99485778808594,
+      "learning_rate": 5.421313506815366e-06,
+      "loss": 24.023195393880208,
+      "step": 1590
+    },
+    {
+      "epoch": 1.8199603062092429,
+      "grad_norm": 88.27577209472656,
+      "learning_rate": 4.956629491945477e-06,
+      "loss": 23.317976888020834,
+      "step": 1605
+    },
+    {
+      "epoch": 1.8369719308193933,
+      "grad_norm": 71.86576080322266,
+      "learning_rate": 4.491945477075589e-06,
+      "loss": 24.0907958984375,
+      "step": 1620
+    },
+    {
+      "epoch": 1.8539835554295436,
+      "grad_norm": 82.11173248291016,
+      "learning_rate": 4.0272614622057e-06,
+      "loss": 22.802571614583332,
+      "step": 1635
+    },
+    {
+      "epoch": 1.8709951800396938,
+      "grad_norm": 108.7845230102539,
+      "learning_rate": 3.5625774473358117e-06,
+      "loss": 22.567728678385418,
+      "step": 1650
+    },
+    {
+      "epoch": 1.8709951800396938,
+      "eval_accuracy": 0.6877192982456141,
+      "eval_loss": 1.4086991548538208,
+      "eval_macro_f1": 0.6610420796325723,
+      "eval_runtime": 3.5341,
+      "eval_samples_per_second": 161.286,
+      "eval_steps_per_second": 20.373,
+      "step": 1650
+    },
+    {
+      "epoch": 1.888006804649844,
+      "grad_norm": 81.1729736328125,
+      "learning_rate": 2.75902901124926e-05,
+      "loss": 24.200571695963543,
+      "step": 1665
+    },
+    {
+      "epoch": 1.9050184292599943,
+      "grad_norm": 94.8641128540039,
+      "learning_rate": 2.736826524570752e-05,
+      "loss": 23.403006998697915,
+      "step": 1680
+    },
+    {
+      "epoch": 1.9220300538701447,
+      "grad_norm": 111.89988708496094,
+      "learning_rate": 2.714624037892244e-05,
+      "loss": 24.09326171875,
+      "step": 1695
+    },
+    {
+      "epoch": 1.9390416784802949,
+      "grad_norm": 88.09811401367188,
+      "learning_rate": 2.6924215512137363e-05,
+      "loss": 23.57196044921875,
+      "step": 1710
+    },
+    {
+      "epoch": 1.956053303090445,
+      "grad_norm": 98.73778533935547,
+      "learning_rate": 2.670219064535228e-05,
+      "loss": 22.270784505208333,
+      "step": 1725
+    },
+    {
+      "epoch": 1.9730649277005954,
+      "grad_norm": 107.9133071899414,
+      "learning_rate": 2.64801657785672e-05,
+      "loss": 22.151611328125,
+      "step": 1740
+    },
+    {
+      "epoch": 1.9900765523107458,
+      "grad_norm": 68.66992950439453,
+      "learning_rate": 2.625814091178212e-05,
+      "loss": 22.602714029947915,
+      "step": 1755
+    },
+    {
+      "epoch": 2.00680464984406,
+      "grad_norm": 66.64095306396484,
+      "learning_rate": 2.603611604499704e-05,
+      "loss": 23.10830281575521,
+      "step": 1770
+    },
+    {
+      "epoch": 2.0238162744542105,
+      "grad_norm": 81.31156921386719,
+      "learning_rate": 2.5814091178211964e-05,
+      "loss": 23.820869954427085,
+      "step": 1785
+    },
+    {
+      "epoch": 2.0408278990643605,
+      "grad_norm": 70.21724700927734,
+      "learning_rate": 2.559206631142688e-05,
+      "loss": 23.429854329427084,
+      "step": 1800
+    },
+    {
+      "epoch": 2.0408278990643605,
+      "eval_accuracy": 0.6736842105263158,
+      "eval_loss": 1.4127047061920166,
+      "eval_macro_f1": 0.6496893371502271,
+      "eval_runtime": 9.1009,
+      "eval_samples_per_second": 62.632,
+      "eval_steps_per_second": 7.911,
+      "step": 1800
+    },
+    {
+      "epoch": 2.057839523674511,
+      "grad_norm": 66.97808837890625,
+      "learning_rate": 2.5370041444641802e-05,
+      "loss": 22.040226236979166,
+      "step": 1815
+    },
+    {
+      "epoch": 2.074851148284661,
+      "grad_norm": 86.77315521240234,
+      "learning_rate": 2.514801657785672e-05,
+      "loss": 22.765303548177084,
+      "step": 1830
+    },
+    {
+      "epoch": 2.0918627728948116,
+      "grad_norm": 152.40870666503906,
+      "learning_rate": 2.492599171107164e-05,
+      "loss": 22.843212890625,
+      "step": 1845
+    },
+    {
+      "epoch": 2.1088743975049615,
+      "grad_norm": 77.38778686523438,
+      "learning_rate": 2.470396684428656e-05,
+      "loss": 23.602665201822916,
+      "step": 1860
+    },
+    {
+      "epoch": 2.125886022115112,
+      "grad_norm": 86.81732940673828,
+      "learning_rate": 2.4481941977501482e-05,
+      "loss": 22.204569498697918,
+      "step": 1875
+    },
+    {
+      "epoch": 2.1428976467252623,
+      "grad_norm": 106.68115997314453,
+      "learning_rate": 2.4259917110716403e-05,
+      "loss": 23.353279622395835,
+      "step": 1890
+    },
+    {
+      "epoch": 2.1599092713354127,
+      "grad_norm": 67.82752227783203,
+      "learning_rate": 2.403789224393132e-05,
+      "loss": 22.071602376302085,
+      "step": 1905
+    },
+    {
+      "epoch": 2.1769208959455626,
+      "grad_norm": 108.98357391357422,
+      "learning_rate": 2.381586737714624e-05,
+      "loss": 23.617496744791666,
+      "step": 1920
+    },
+    {
+      "epoch": 2.193932520555713,
+      "grad_norm": 88.80236053466797,
+      "learning_rate": 2.3593842510361162e-05,
+      "loss": 23.64888916015625,
+      "step": 1935
+    },
+    {
+      "epoch": 2.2109441451658634,
+      "grad_norm": 76.97945404052734,
+      "learning_rate": 2.3371817643576083e-05,
+      "loss": 22.77431640625,
+      "step": 1950
+    },
+    {
+      "epoch": 2.2109441451658634,
+      "eval_accuracy": 0.6807017543859649,
+      "eval_loss": 1.4114816188812256,
+      "eval_macro_f1": 0.6538011695906434,
+      "eval_runtime": 4.0708,
+      "eval_samples_per_second": 140.023,
+      "eval_steps_per_second": 17.687,
+      "step": 1950
+    },
+    {
+      "epoch": 2.2279557697760137,
+      "grad_norm": 79.89060974121094,
+      "learning_rate": 1.3661858974358974e-05,
+      "loss": 22.299812825520835,
+      "step": 1965
+    },
+    {
+      "epoch": 2.2449673943861637,
+      "grad_norm": 68.27561950683594,
+      "learning_rate": 1.3361378205128205e-05,
+      "loss": 22.934122721354168,
+      "step": 1980
+    },
+    {
+      "epoch": 2.261979018996314,
+      "grad_norm": 88.11699676513672,
+      "learning_rate": 1.3060897435897438e-05,
+      "loss": 23.039603678385415,
+      "step": 1995
+    },
+    {
+      "epoch": 2.2789906436064644,
+      "grad_norm": 92.85344696044922,
+      "learning_rate": 1.2760416666666666e-05,
+      "loss": 22.987742106119793,
+      "step": 2010
+    },
+    {
+      "epoch": 2.296002268216615,
+      "grad_norm": 58.237430572509766,
+      "learning_rate": 1.2459935897435898e-05,
+      "loss": 22.56093953450521,
+      "step": 2025
+    },
+    {
+      "epoch": 2.313013892826765,
+      "grad_norm": 78.24669647216797,
+      "learning_rate": 1.215945512820513e-05,
+      "loss": 23.163655598958332,
+      "step": 2040
+    },
+    {
+      "epoch": 2.330025517436915,
+      "grad_norm": 76.5031967163086,
+      "learning_rate": 1.1858974358974359e-05,
+      "loss": 22.215464274088543,
+      "step": 2055
+    },
+    {
+      "epoch": 2.3470371420470655,
+      "grad_norm": 83.24020385742188,
+      "learning_rate": 1.1558493589743591e-05,
+      "loss": 21.822041829427082,
+      "step": 2070
+    },
+    {
+      "epoch": 2.364048766657216,
+      "grad_norm": 105.09784698486328,
+      "learning_rate": 1.125801282051282e-05,
+      "loss": 22.152524820963542,
+      "step": 2085
+    },
+    {
+      "epoch": 2.381060391267366,
+      "grad_norm": 68.16545104980469,
+      "learning_rate": 1.0957532051282052e-05,
+      "loss": 22.53731892903646,
+      "step": 2100
+    },
+    {
+      "epoch": 2.381060391267366,
+      "eval_accuracy": 0.6789473684210526,
+      "eval_loss": 1.3919118642807007,
+      "eval_macro_f1": 0.6545453110702925,
+      "eval_runtime": 7.6768,
+      "eval_samples_per_second": 74.25,
+      "eval_steps_per_second": 9.379,
+      "step": 2100
+    }
+  ],
+  "logging_steps": 15,
+  "max_steps": 2646,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 150,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5041298752929792.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

sft/checkpoint-2100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dec0cf06374d81a4ce515155a54fafdc9a0c6ab83b1c2fc5d91f02484b58f8c1
+size 5201