Upload 13 files

README.md

@@ -1,3 +1,206 @@
----
-license: mit
----
+---
+base_model: aubmindlab/bert-base-arabertv2
+library_name: peft
+tags:
+- base_model:adapter:aubmindlab/bert-base-arabertv2
+- 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 0.16.0

adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "aubmindlab/bert-base-arabertv2",
+  "bias": "none",
+  "corda_config": null,
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "value",
+    "query",
+    "key",
+    "dense"
+  ],
+  "task_type": "TOKEN_CLS",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:562b54444fbd2c7f6fe1e1a4c406bc692f29a6b5356b38598e05db2d9ef28838
+size 21281828

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:def2173bc32a7a1d8df143d80d71abc5ca7146ac0812a1cce9426bb6c5657ce8
+size 42645434

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97bea06cae02251004d8bd547ce89f1872f61885d4ea2866bfe86efc737d83f8
+size 14244

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5639f8b8124ec21146f909df725d0dc799daa79b05ba933872dc3cd3b0a7e67
+size 988

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bb76a250c7e90c6534fa88a95fa832be4927a4f0ac1d857ee18fd6b6f8c211b
+size 1064

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,339 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "+ا",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "1": {
+      "content": "+ك",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "2": {
+      "content": "ب+",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "3": {
+      "content": "+هم",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "4": {
+      "content": "+ات",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "5": {
+      "content": "+ي",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "6": {
+      "content": "ل+",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "7": {
+      "content": "+هما",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "8": {
+      "content": "+نا",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "9": {
+      "content": "+ن",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "10": {
+      "content": "+ها",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "11": {
+      "content": "+كما",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "12": {
+      "content": "+ة",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "13": {
+      "content": "ف+",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "14": {
+      "content": "+كم",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "15": {
+      "content": "+كن",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "16": {
+      "content": "+ت",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "17": {
+      "content": "[بريد]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "18": {
+      "content": "[مستخدم]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "19": {
+      "content": "لل+",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "20": {
+      "content": "ال+",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "21": {
+      "content": "[رابط]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "22": {
+      "content": "س+",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "23": {
+      "content": "+ان",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "24": {
+      "content": "+وا",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "25": {
+      "content": "+ه",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "26": {
+      "content": "+ون",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "27": {
+      "content": "+هن",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "28": {
+      "content": "+ين",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "29": {
+      "content": "��+",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "30": {
+      "content": "ك+",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "31": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "33": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "34": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "35": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": [
+    "+ك",
+    "+كما",
+    "ك+",
+    "+وا",
+    "+ين",
+    "و+",
+    "+كن",
+    "+ان",
+    "+هم",
+    "+ة",
+    "[بريد]",
+    "لل+",
+    "+ي",
+    "+ت",
+    "+ن",
+    "س+",
+    "ل+",
+    "[مستخدم]",
+    "+كم",
+    "+ا",
+    "ب+",
+    "ف+",
+    "+نا",
+    "+ها",
+    "+ون",
+    "+هما",
+    "ال+",
+    "+ه",
+    "+هن",
+    "+ات",
+    "[رابط]"
+  ],
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,646 @@
+{
+  "best_global_step": 13430,
+  "best_metric": 0.8506006776876477,
+  "best_model_checkpoint": "./aner_lora_model/checkpoint-13430",
+  "epoch": 34.0,
+  "eval_steps": 500,
+  "global_step": 13430,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.1466563940048218,
+      "learning_rate": 9.450337512054003e-06,
+      "loss": 1.6728,
+      "step": 395
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.07284681130834977,
+      "eval_loss": 0.8734206557273865,
+      "eval_precision": 0.09899928520371694,
+      "eval_recall": 0.05762429789889744,
+      "eval_runtime": 6.1863,
+      "eval_samples_per_second": 415.757,
+      "eval_steps_per_second": 6.628,
+      "step": 395
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.8038758039474487,
+      "learning_rate": 1.8948891031822567e-05,
+      "loss": 0.5426,
+      "step": 790
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.6452263332997278,
+      "eval_loss": 0.3722752630710602,
+      "eval_precision": 0.6259780907668232,
+      "eval_recall": 0.6656958602038694,
+      "eval_runtime": 6.2125,
+      "eval_samples_per_second": 414.003,
+      "eval_steps_per_second": 6.6,
+      "step": 790
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.234807014465332,
+      "learning_rate": 2.844744455159113e-05,
+      "loss": 0.3384,
+      "step": 1185
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.7009996970614966,
+      "eval_loss": 0.2873896658420563,
+      "eval_precision": 0.6811224489795918,
+      "eval_recall": 0.7220719783648846,
+      "eval_runtime": 6.2219,
+      "eval_samples_per_second": 413.378,
+      "eval_steps_per_second": 6.59,
+      "step": 1185
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.2888472080230713,
+      "learning_rate": 3.7970106075216974e-05,
+      "loss": 0.2783,
+      "step": 1580
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.7592421915002561,
+      "eval_loss": 0.27101996541023254,
+      "eval_precision": 0.7476805163372328,
+      "eval_recall": 0.7711670480549199,
+      "eval_runtime": 6.2368,
+      "eval_samples_per_second": 412.391,
+      "eval_steps_per_second": 6.574,
+      "step": 1580
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.091982841491699,
+      "learning_rate": 4.749276759884282e-05,
+      "loss": 0.2408,
+      "step": 1975
+    },
+    {
+      "epoch": 5.0,
+      "eval_f1": 0.7708728179551123,
+      "eval_loss": 0.2352629005908966,
+      "eval_precision": 0.7405136067458796,
+      "eval_recall": 0.8038277511961722,
+      "eval_runtime": 6.2249,
+      "eval_samples_per_second": 413.181,
+      "eval_steps_per_second": 6.586,
+      "step": 1975
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 3.6555726528167725,
+      "learning_rate": 5.699132111861139e-05,
+      "loss": 0.2138,
+      "step": 2370
+    },
+    {
+      "epoch": 6.0,
+      "eval_f1": 0.7946803069053708,
+      "eval_loss": 0.23413550853729248,
+      "eval_precision": 0.7818035426731079,
+      "eval_recall": 0.8079883503224464,
+      "eval_runtime": 6.2199,
+      "eval_samples_per_second": 413.509,
+      "eval_steps_per_second": 6.592,
+      "step": 2370
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 1.3194808959960938,
+      "learning_rate": 6.648987463837994e-05,
+      "loss": 0.1997,
+      "step": 2765
+    },
+    {
+      "epoch": 7.0,
+      "eval_f1": 0.7968973259848949,
+      "eval_loss": 0.217984139919281,
+      "eval_precision": 0.7822079743538369,
+      "eval_recall": 0.8121489494487206,
+      "eval_runtime": 6.2321,
+      "eval_samples_per_second": 412.701,
+      "eval_steps_per_second": 6.579,
+      "step": 2765
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 3.00563907623291,
+      "learning_rate": 7.601253616200579e-05,
+      "loss": 0.1796,
+      "step": 3160
+    },
+    {
+      "epoch": 8.0,
+      "eval_f1": 0.8006453564586065,
+      "eval_loss": 0.21363000571727753,
+      "eval_precision": 0.776908023483366,
+      "eval_recall": 0.8258789265654254,
+      "eval_runtime": 6.2148,
+      "eval_samples_per_second": 413.849,
+      "eval_steps_per_second": 6.597,
+      "step": 3160
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 1.7021512985229492,
+      "learning_rate": 8.553519768563163e-05,
+      "loss": 0.1628,
+      "step": 3555
+    },
+    {
+      "epoch": 9.0,
+      "eval_f1": 0.8144906889182865,
+      "eval_loss": 0.21552523970603943,
+      "eval_precision": 0.7972111553784861,
+      "eval_recall": 0.8325358851674641,
+      "eval_runtime": 6.2332,
+      "eval_samples_per_second": 412.63,
+      "eval_steps_per_second": 6.578,
+      "step": 3555
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 1.311308741569519,
+      "learning_rate": 9.505785920925749e-05,
+      "loss": 0.1487,
+      "step": 3950
+    },
+    {
+      "epoch": 10.0,
+      "eval_f1": 0.8213381921247089,
+      "eval_loss": 0.2061518430709839,
+      "eval_precision": 0.7998817034700315,
+      "eval_recall": 0.8439775327647181,
+      "eval_runtime": 6.2201,
+      "eval_samples_per_second": 413.497,
+      "eval_steps_per_second": 6.592,
+      "step": 3950
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 0.8549454808235168,
+      "learning_rate": 9.998387447114843e-05,
+      "loss": 0.1373,
+      "step": 4345
+    },
+    {
+      "epoch": 11.0,
+      "eval_f1": 0.8243118796684744,
+      "eval_loss": 0.22040106356143951,
+      "eval_precision": 0.8111155859846959,
+      "eval_recall": 0.8379446640316206,
+      "eval_runtime": 6.2308,
+      "eval_samples_per_second": 412.791,
+      "eval_steps_per_second": 6.58,
+      "step": 4345
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 1.147991418838501,
+      "learning_rate": 9.984720099749273e-05,
+      "loss": 0.1214,
+      "step": 4740
+    },
+    {
+      "epoch": 12.0,
+      "eval_f1": 0.833384789544098,
+      "eval_loss": 0.21504363417625427,
+      "eval_precision": 0.824643584521385,
+      "eval_recall": 0.8423132931142084,
+      "eval_runtime": 6.2273,
+      "eval_samples_per_second": 413.023,
+      "eval_steps_per_second": 6.584,
+      "step": 4740
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 0.7487550973892212,
+      "learning_rate": 9.957158852398329e-05,
+      "loss": 0.1091,
+      "step": 5135
+    },
+    {
+      "epoch": 13.0,
+      "eval_f1": 0.83111337061515,
+      "eval_loss": 0.21468985080718994,
+      "eval_precision": 0.8128480509148767,
+      "eval_recall": 0.8502184314541293,
+      "eval_runtime": 6.2234,
+      "eval_samples_per_second": 413.28,
+      "eval_steps_per_second": 6.588,
+      "step": 5135
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 1.407198429107666,
+      "learning_rate": 9.915780526469535e-05,
+      "loss": 0.0979,
+      "step": 5530
+    },
+    {
+      "epoch": 14.0,
+      "eval_f1": 0.838515129458251,
+      "eval_loss": 0.21988336741924286,
+      "eval_precision": 0.8382536382536383,
+      "eval_recall": 0.8387767838568754,
+      "eval_runtime": 6.2301,
+      "eval_samples_per_second": 412.832,
+      "eval_steps_per_second": 6.581,
+      "step": 5530
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 0.48871779441833496,
+      "learning_rate": 9.86070045568485e-05,
+      "loss": 0.0873,
+      "step": 5925
+    },
+    {
+      "epoch": 15.0,
+      "eval_f1": 0.8290302907094939,
+      "eval_loss": 0.22614166140556335,
+      "eval_precision": 0.8105744384814152,
+      "eval_recall": 0.848346161847306,
+      "eval_runtime": 6.2224,
+      "eval_samples_per_second": 413.346,
+      "eval_steps_per_second": 6.589,
+      "step": 5925
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 2.422437906265259,
+      "learning_rate": 9.792072164611214e-05,
+      "loss": 0.0784,
+      "step": 6320
+    },
+    {
+      "epoch": 16.0,
+      "eval_f1": 0.8394858611825193,
+      "eval_loss": 0.2310497760772705,
+      "eval_precision": 0.8300122000813339,
+      "eval_recall": 0.8491782816725608,
+      "eval_runtime": 6.2296,
+      "eval_samples_per_second": 412.868,
+      "eval_steps_per_second": 6.581,
+      "step": 6320
+    },
+    {
+      "epoch": 17.0,
+      "grad_norm": 1.0132837295532227,
+      "learning_rate": 9.710086940741867e-05,
+      "loss": 0.0699,
+      "step": 6715
+    },
+    {
+      "epoch": 17.0,
+      "eval_f1": 0.8350071736011477,
+      "eval_loss": 0.24940118193626404,
+      "eval_precision": 0.8228640678650777,
+      "eval_recall": 0.8475140420220512,
+      "eval_runtime": 6.2441,
+      "eval_samples_per_second": 411.911,
+      "eval_steps_per_second": 6.566,
+      "step": 6715
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 1.5865906476974487,
+      "learning_rate": 9.61523045626935e-05,
+      "loss": 0.0615,
+      "step": 7110
+    },
+    {
+      "epoch": 18.0,
+      "eval_f1": 0.8329538397847237,
+      "eval_loss": 0.2699420750141144,
+      "eval_precision": 0.8288362512873326,
+      "eval_recall": 0.8371125442063657,
+      "eval_runtime": 6.2246,
+      "eval_samples_per_second": 413.199,
+      "eval_steps_per_second": 6.587,
+      "step": 7110
+    },
+    {
+      "epoch": 19.0,
+      "grad_norm": 0.9923080205917358,
+      "learning_rate": 9.507285711634415e-05,
+      "loss": 0.0576,
+      "step": 7505
+    },
+    {
+      "epoch": 19.0,
+      "eval_f1": 0.82642089093702,
+      "eval_loss": 0.2682414948940277,
+      "eval_precision": 0.8138362242839855,
+      "eval_recall": 0.8394008737258165,
+      "eval_runtime": 6.2361,
+      "eval_samples_per_second": 412.439,
+      "eval_steps_per_second": 6.575,
+      "step": 7505
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 1.0131040811538696,
+      "learning_rate": 9.38677781889291e-05,
+      "loss": 0.0497,
+      "step": 7900
+    },
+    {
+      "epoch": 20.0,
+      "eval_f1": 0.8408021280949458,
+      "eval_loss": 0.2817462980747223,
+      "eval_precision": 0.8272599154419167,
+      "eval_recall": 0.854795090493031,
+      "eval_runtime": 6.2397,
+      "eval_samples_per_second": 412.202,
+      "eval_steps_per_second": 6.571,
+      "step": 7900
+    },
+    {
+      "epoch": 21.0,
+      "grad_norm": 1.129745364189148,
+      "learning_rate": 9.254042669444088e-05,
+      "loss": 0.0463,
+      "step": 8295
+    },
+    {
+      "epoch": 21.0,
+      "eval_f1": 0.8426954625687884,
+      "eval_loss": 0.2874164581298828,
+      "eval_precision": 0.8412106135986733,
+      "eval_recall": 0.8441855627210318,
+      "eval_runtime": 6.2285,
+      "eval_samples_per_second": 412.943,
+      "eval_steps_per_second": 6.583,
+      "step": 8295
+    },
+    {
+      "epoch": 22.0,
+      "grad_norm": 1.3233388662338257,
+      "learning_rate": 9.10945023569444e-05,
+      "loss": 0.0412,
+      "step": 8690
+    },
+    {
+      "epoch": 22.0,
+      "eval_f1": 0.8439258178787248,
+      "eval_loss": 0.29583561420440674,
+      "eval_precision": 0.8453350031308704,
+      "eval_recall": 0.8425213230705222,
+      "eval_runtime": 6.2232,
+      "eval_samples_per_second": 413.292,
+      "eval_steps_per_second": 6.588,
+      "step": 8690
+    },
+    {
+      "epoch": 23.0,
+      "grad_norm": 0.6825762987136841,
+      "learning_rate": 8.953403539834375e-05,
+      "loss": 0.0388,
+      "step": 9085
+    },
+    {
+      "epoch": 23.0,
+      "eval_f1": 0.8467850836189883,
+      "eval_loss": 0.29167571663856506,
+      "eval_precision": 0.845643153526971,
+      "eval_recall": 0.8479301019346785,
+      "eval_runtime": 6.2302,
+      "eval_samples_per_second": 412.826,
+      "eval_steps_per_second": 6.581,
+      "step": 9085
+    },
+    {
+      "epoch": 24.0,
+      "grad_norm": 0.829084038734436,
+      "learning_rate": 8.786337530495295e-05,
+      "loss": 0.0343,
+      "step": 9480
+    },
+    {
+      "epoch": 24.0,
+      "eval_f1": 0.8326785534401128,
+      "eval_loss": 0.29245325922966003,
+      "eval_precision": 0.8072265625,
+      "eval_recall": 0.85978780944456,
+      "eval_runtime": 6.2492,
+      "eval_samples_per_second": 411.57,
+      "eval_steps_per_second": 6.561,
+      "step": 9480
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 1.2089000940322876,
+      "learning_rate": 8.609180455499081e-05,
+      "loss": 0.0319,
+      "step": 9875
+    },
+    {
+      "epoch": 25.0,
+      "eval_f1": 0.8404788703571062,
+      "eval_loss": 0.3039838969707489,
+      "eval_precision": 0.8270237615787354,
+      "eval_recall": 0.8543790305804035,
+      "eval_runtime": 6.2496,
+      "eval_samples_per_second": 411.548,
+      "eval_steps_per_second": 6.56,
+      "step": 9875
+    },
+    {
+      "epoch": 26.0,
+      "grad_norm": 0.7031717300415039,
+      "learning_rate": 8.421527039366616e-05,
+      "loss": 0.0297,
+      "step": 10270
+    },
+    {
+      "epoch": 26.0,
+      "eval_f1": 0.8409658617818484,
+      "eval_loss": 0.3323589265346527,
+      "eval_precision": 0.8414913559675068,
+      "eval_recall": 0.840441023507385,
+      "eval_runtime": 6.2285,
+      "eval_samples_per_second": 412.939,
+      "eval_steps_per_second": 6.583,
+      "step": 10270
+    },
+    {
+      "epoch": 27.0,
+      "grad_norm": 1.0431761741638184,
+      "learning_rate": 8.224336808020677e-05,
+      "loss": 0.0254,
+      "step": 10665
+    },
+    {
+      "epoch": 27.0,
+      "eval_f1": 0.842159067675322,
+      "eval_loss": 0.31897974014282227,
+      "eval_precision": 0.8279396984924623,
+      "eval_recall": 0.8568753900561681,
+      "eval_runtime": 6.2339,
+      "eval_samples_per_second": 412.583,
+      "eval_steps_per_second": 6.577,
+      "step": 10665
+    },
+    {
+      "epoch": 28.0,
+      "grad_norm": 0.3485606014728546,
+      "learning_rate": 8.018159389383709e-05,
+      "loss": 0.0237,
+      "step": 11060
+    },
+    {
+      "epoch": 28.0,
+      "eval_f1": 0.8385502471169687,
+      "eval_loss": 0.3295208811759949,
+      "eval_precision": 0.8301732925586136,
+      "eval_recall": 0.8470979821094238,
+      "eval_runtime": 6.2249,
+      "eval_samples_per_second": 413.179,
+      "eval_steps_per_second": 6.586,
+      "step": 11060
+    },
+    {
+      "epoch": 29.0,
+      "grad_norm": 2.1144888401031494,
+      "learning_rate": 7.80356946134664e-05,
+      "loss": 0.0217,
+      "step": 11455
+    },
+    {
+      "epoch": 29.0,
+      "eval_f1": 0.8437499999999999,
+      "eval_loss": 0.32363420724868774,
+      "eval_precision": 0.833976833976834,
+      "eval_recall": 0.8537549407114624,
+      "eval_runtime": 6.2372,
+      "eval_samples_per_second": 412.362,
+      "eval_steps_per_second": 6.573,
+      "step": 11455
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 0.29809829592704773,
+      "learning_rate": 7.581165149970385e-05,
+      "loss": 0.0204,
+      "step": 11850
+    },
+    {
+      "epoch": 30.0,
+      "eval_f1": 0.8443138900545532,
+      "eval_loss": 0.35288870334625244,
+      "eval_precision": 0.8516402116402116,
+      "eval_recall": 0.8371125442063657,
+      "eval_runtime": 6.2428,
+      "eval_samples_per_second": 411.996,
+      "eval_steps_per_second": 6.568,
+      "step": 11850
+    },
+    {
+      "epoch": 31.0,
+      "grad_norm": 0.03988971561193466,
+      "learning_rate": 7.351566362330311e-05,
+      "loss": 0.0187,
+      "step": 12245
+    },
+    {
+      "epoch": 31.0,
+      "eval_f1": 0.8424198701432547,
+      "eval_loss": 0.3403635323047638,
+      "eval_precision": 0.8347630718954249,
+      "eval_recall": 0.8502184314541293,
+      "eval_runtime": 6.1938,
+      "eval_samples_per_second": 415.254,
+      "eval_steps_per_second": 6.62,
+      "step": 12245
+    },
+    {
+      "epoch": 32.0,
+      "grad_norm": 0.40415504574775696,
+      "learning_rate": 7.115413058650544e-05,
+      "loss": 0.0168,
+      "step": 12640
+    },
+    {
+      "epoch": 32.0,
+      "eval_f1": 0.8455690929917734,
+      "eval_loss": 0.34554678201675415,
+      "eval_precision": 0.8465387823185988,
+      "eval_recall": 0.8446016226336592,
+      "eval_runtime": 6.1803,
+      "eval_samples_per_second": 416.159,
+      "eval_steps_per_second": 6.634,
+      "step": 12640
+    },
+    {
+      "epoch": 33.0,
+      "grad_norm": 1.3843847513198853,
+      "learning_rate": 6.873363468544161e-05,
+      "loss": 0.0154,
+      "step": 13035
+    },
+    {
+      "epoch": 33.0,
+      "eval_f1": 0.8446492575524833,
+      "eval_loss": 0.34318989515304565,
+      "eval_precision": 0.8317870108914885,
+      "eval_recall": 0.8579155398377366,
+      "eval_runtime": 6.1485,
+      "eval_samples_per_second": 418.312,
+      "eval_steps_per_second": 6.668,
+      "step": 13035
+    },
+    {
+      "epoch": 34.0,
+      "grad_norm": 0.4158535897731781,
+      "learning_rate": 6.626092256331148e-05,
+      "loss": 0.0141,
+      "step": 13430
+    },
+    {
+      "epoch": 34.0,
+      "eval_f1": 0.8506006776876477,
+      "eval_loss": 0.353132963180542,
+      "eval_precision": 0.8398215733982157,
+      "eval_recall": 0.8616600790513834,
+      "eval_runtime": 6.1312,
+      "eval_samples_per_second": 419.497,
+      "eval_steps_per_second": 6.687,
+      "step": 13430
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 27650,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 70,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5841542093969132e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a05a1a6deb1e510f5056f8cfb43a5e87a8f7c2bbc2a28ee049aeabe66316a67
+size 5304