checkpoint-1000

qwen3.5-2b/checkpoint-1000/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen3.5-2B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3.5-2B
+- 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 0.21.0

qwen3.5-2b/checkpoint-1000/adapter_config.json

@@ -0,0 +1,56 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.5-2B",
+  "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,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "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": "0.21.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "out_proj",
+    "in_proj_a",
+    "in_proj_qkv",
+    "in_proj_z",
+    "o_proj",
+    "in_proj_b",
+    "v_proj",
+    "k_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,
+  "velora_config": null
+}

qwen3.5-2b/checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0e20a3df23bdcd723f671ce34b80795b783e0d43b77af5ea86cd54632057f9f
+size 134604152

qwen3.5-2b/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb40f5b419fb45a01f27564d943532819216044683eff73c8b9a94ed898c8b43
+size 269426431

qwen3.5-2b/checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1038a49bd92fa68e4a6e653212221a93e9b68affa3208f57f91ea09f7fe28e2
+size 14645

qwen3.5-2b/checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fd37ccb5616025d03cf39ffeb34cf2981e7ff5ce5b5ddce7468fa267198b72b
+size 1465

qwen3.5-2b/checkpoint-1000/trainer_state.json

@@ -0,0 +1,758 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5278785879247773,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005278785879247773,
+      "grad_norm": 1.305302381515503,
+      "learning_rate": 1.8947368421052634e-05,
+      "loss": 0.8562479972839355,
+      "step": 10
+    },
+    {
+      "epoch": 0.010557571758495546,
+      "grad_norm": 0.9230896830558777,
+      "learning_rate": 4e-05,
+      "loss": 0.7965596675872803,
+      "step": 20
+    },
+    {
+      "epoch": 0.01583635763774332,
+      "grad_norm": 0.7995359301567078,
+      "learning_rate": 6.105263157894737e-05,
+      "loss": 0.7992881298065185,
+      "step": 30
+    },
+    {
+      "epoch": 0.02111514351699109,
+      "grad_norm": 0.7340251207351685,
+      "learning_rate": 8.210526315789474e-05,
+      "loss": 0.6521625995635987,
+      "step": 40
+    },
+    {
+      "epoch": 0.026393929396238865,
+      "grad_norm": 1.0072991847991943,
+      "learning_rate": 0.00010315789473684211,
+      "loss": 0.6839987277984619,
+      "step": 50
+    },
+    {
+      "epoch": 0.03167271527548664,
+      "grad_norm": 0.8970349431037903,
+      "learning_rate": 0.00012421052631578949,
+      "loss": 0.6341384887695313,
+      "step": 60
+    },
+    {
+      "epoch": 0.03695150115473441,
+      "grad_norm": 0.883733332157135,
+      "learning_rate": 0.00014526315789473686,
+      "loss": 0.6603663444519043,
+      "step": 70
+    },
+    {
+      "epoch": 0.04223028703398218,
+      "grad_norm": 0.8134523630142212,
+      "learning_rate": 0.00016631578947368423,
+      "loss": 0.6564276695251465,
+      "step": 80
+    },
+    {
+      "epoch": 0.047509072913229956,
+      "grad_norm": 0.8890961408615112,
+      "learning_rate": 0.0001873684210526316,
+      "loss": 0.6585474967956543,
+      "step": 90
+    },
+    {
+      "epoch": 0.05278785879247773,
+      "grad_norm": 0.7649273872375488,
+      "learning_rate": 0.00019955555555555558,
+      "loss": 0.6272543430328369,
+      "step": 100
+    },
+    {
+      "epoch": 0.0580666446717255,
+      "grad_norm": 0.7554565072059631,
+      "learning_rate": 0.00019844444444444445,
+      "loss": 0.5757376194000244,
+      "step": 110
+    },
+    {
+      "epoch": 0.06334543055097328,
+      "grad_norm": 0.7954307794570923,
+      "learning_rate": 0.00019733333333333335,
+      "loss": 0.641472053527832,
+      "step": 120
+    },
+    {
+      "epoch": 0.06862421643022105,
+      "grad_norm": 0.672359824180603,
+      "learning_rate": 0.00019622222222222225,
+      "loss": 0.563064432144165,
+      "step": 130
+    },
+    {
+      "epoch": 0.07390300230946882,
+      "grad_norm": 0.6992788314819336,
+      "learning_rate": 0.0001951111111111111,
+      "loss": 0.600986099243164,
+      "step": 140
+    },
+    {
+      "epoch": 0.0791817881887166,
+      "grad_norm": 0.6328181028366089,
+      "learning_rate": 0.000194,
+      "loss": 0.5295759201049804,
+      "step": 150
+    },
+    {
+      "epoch": 0.08446057406796437,
+      "grad_norm": 0.6692398190498352,
+      "learning_rate": 0.0001928888888888889,
+      "loss": 0.6027700901031494,
+      "step": 160
+    },
+    {
+      "epoch": 0.08973935994721215,
+      "grad_norm": 0.7081276774406433,
+      "learning_rate": 0.0001917777777777778,
+      "loss": 0.5615420341491699,
+      "step": 170
+    },
+    {
+      "epoch": 0.09501814582645991,
+      "grad_norm": 0.5484495759010315,
+      "learning_rate": 0.00019066666666666668,
+      "loss": 0.5883731842041016,
+      "step": 180
+    },
+    {
+      "epoch": 0.10029693170570769,
+      "grad_norm": 0.7612242102622986,
+      "learning_rate": 0.00018955555555555558,
+      "loss": 0.5624749183654785,
+      "step": 190
+    },
+    {
+      "epoch": 0.10557571758495546,
+      "grad_norm": 0.678548276424408,
+      "learning_rate": 0.00018844444444444445,
+      "loss": 0.5546360969543457,
+      "step": 200
+    },
+    {
+      "epoch": 0.11085450346420324,
+      "grad_norm": 0.5756900906562805,
+      "learning_rate": 0.00018733333333333335,
+      "loss": 0.5600387573242187,
+      "step": 210
+    },
+    {
+      "epoch": 0.116133289343451,
+      "grad_norm": 0.5475565791130066,
+      "learning_rate": 0.00018622222222222223,
+      "loss": 0.5820147037506104,
+      "step": 220
+    },
+    {
+      "epoch": 0.12141207522269878,
+      "grad_norm": 0.6964915990829468,
+      "learning_rate": 0.00018511111111111113,
+      "loss": 0.5699102401733398,
+      "step": 230
+    },
+    {
+      "epoch": 0.12669086110194655,
+      "grad_norm": 0.6508777737617493,
+      "learning_rate": 0.00018400000000000003,
+      "loss": 0.5863839626312256,
+      "step": 240
+    },
+    {
+      "epoch": 0.13196964698119432,
+      "grad_norm": 0.6375535726547241,
+      "learning_rate": 0.00018288888888888887,
+      "loss": 0.5772487640380859,
+      "step": 250
+    },
+    {
+      "epoch": 0.1372484328604421,
+      "grad_norm": 0.5595227479934692,
+      "learning_rate": 0.00018177777777777778,
+      "loss": 0.603016710281372,
+      "step": 260
+    },
+    {
+      "epoch": 0.14252721873968988,
+      "grad_norm": 0.5612871646881104,
+      "learning_rate": 0.00018066666666666668,
+      "loss": 0.5080572605133057,
+      "step": 270
+    },
+    {
+      "epoch": 0.14780600461893764,
+      "grad_norm": 0.762787938117981,
+      "learning_rate": 0.00017955555555555558,
+      "loss": 0.6409445762634277,
+      "step": 280
+    },
+    {
+      "epoch": 0.1530847904981854,
+      "grad_norm": 0.6885519623756409,
+      "learning_rate": 0.00017844444444444445,
+      "loss": 0.6149398803710937,
+      "step": 290
+    },
+    {
+      "epoch": 0.1583635763774332,
+      "grad_norm": 0.6986534595489502,
+      "learning_rate": 0.00017733333333333335,
+      "loss": 0.5259696960449218,
+      "step": 300
+    },
+    {
+      "epoch": 0.16364236225668097,
+      "grad_norm": 0.601087212562561,
+      "learning_rate": 0.00017622222222222223,
+      "loss": 0.6464223384857177,
+      "step": 310
+    },
+    {
+      "epoch": 0.16892114813592873,
+      "grad_norm": 0.4432871639728546,
+      "learning_rate": 0.00017511111111111113,
+      "loss": 0.509718942642212,
+      "step": 320
+    },
+    {
+      "epoch": 0.1741999340151765,
+      "grad_norm": 0.5295445322990417,
+      "learning_rate": 0.000174,
+      "loss": 0.5282030582427979,
+      "step": 330
+    },
+    {
+      "epoch": 0.1794787198944243,
+      "grad_norm": 0.695189893245697,
+      "learning_rate": 0.0001728888888888889,
+      "loss": 0.5390444278717041,
+      "step": 340
+    },
+    {
+      "epoch": 0.18475750577367206,
+      "grad_norm": 0.6871212124824524,
+      "learning_rate": 0.0001717777777777778,
+      "loss": 0.6001670360565186,
+      "step": 350
+    },
+    {
+      "epoch": 0.19003629165291983,
+      "grad_norm": 0.5886061787605286,
+      "learning_rate": 0.00017066666666666668,
+      "loss": 0.5532281875610352,
+      "step": 360
+    },
+    {
+      "epoch": 0.1953150775321676,
+      "grad_norm": 0.4359692931175232,
+      "learning_rate": 0.00016955555555555555,
+      "loss": 0.5710611343383789,
+      "step": 370
+    },
+    {
+      "epoch": 0.20059386341141539,
+      "grad_norm": 0.5859516859054565,
+      "learning_rate": 0.00016844444444444445,
+      "loss": 0.527172040939331,
+      "step": 380
+    },
+    {
+      "epoch": 0.20587264929066315,
+      "grad_norm": 0.595167875289917,
+      "learning_rate": 0.00016733333333333335,
+      "loss": 0.5060821056365967,
+      "step": 390
+    },
+    {
+      "epoch": 0.21115143516991092,
+      "grad_norm": 0.5597789883613586,
+      "learning_rate": 0.00016622222222222223,
+      "loss": 0.5472925186157227,
+      "step": 400
+    },
+    {
+      "epoch": 0.21643022104915868,
+      "grad_norm": 0.5002998113632202,
+      "learning_rate": 0.00016511111111111113,
+      "loss": 0.5917861461639404,
+      "step": 410
+    },
+    {
+      "epoch": 0.22170900692840648,
+      "grad_norm": 0.6672388911247253,
+      "learning_rate": 0.000164,
+      "loss": 0.5691781044006348,
+      "step": 420
+    },
+    {
+      "epoch": 0.22698779280765424,
+      "grad_norm": 0.580162763595581,
+      "learning_rate": 0.0001628888888888889,
+      "loss": 0.5123159408569335,
+      "step": 430
+    },
+    {
+      "epoch": 0.232266578686902,
+      "grad_norm": 0.5568054914474487,
+      "learning_rate": 0.00016177777777777778,
+      "loss": 0.5455626010894775,
+      "step": 440
+    },
+    {
+      "epoch": 0.23754536456614977,
+      "grad_norm": 0.6651593446731567,
+      "learning_rate": 0.00016066666666666668,
+      "loss": 0.5399269104003906,
+      "step": 450
+    },
+    {
+      "epoch": 0.24282415044539757,
+      "grad_norm": 0.5001797080039978,
+      "learning_rate": 0.00015955555555555558,
+      "loss": 0.5277121543884278,
+      "step": 460
+    },
+    {
+      "epoch": 0.24810293632464533,
+      "grad_norm": 0.5514921545982361,
+      "learning_rate": 0.00015844444444444445,
+      "loss": 0.5342081546783447,
+      "step": 470
+    },
+    {
+      "epoch": 0.2533817222038931,
+      "grad_norm": 0.5599192380905151,
+      "learning_rate": 0.00015733333333333333,
+      "loss": 0.5150089263916016,
+      "step": 480
+    },
+    {
+      "epoch": 0.2586605080831409,
+      "grad_norm": 0.563194215297699,
+      "learning_rate": 0.00015622222222222223,
+      "loss": 0.5231950759887696,
+      "step": 490
+    },
+    {
+      "epoch": 0.26393929396238863,
+      "grad_norm": 0.7210673689842224,
+      "learning_rate": 0.00015511111111111113,
+      "loss": 0.5708573818206787,
+      "step": 500
+    },
+    {
+      "epoch": 0.26393929396238863,
+      "eval_loss": 0.534747838973999,
+      "eval_runtime": 459.3797,
+      "eval_samples_per_second": 24.383,
+      "eval_steps_per_second": 6.097,
+      "step": 500
+    },
+    {
+      "epoch": 0.26393929396238863,
+      "step": 500,
+      "test_best_wer": 0.21571711227233525,
+      "test_exact_match": 0.0,
+      "test_hallucination_rate": 0.09375,
+      "test_wer": 0.4919080716351276
+    },
+    {
+      "epoch": 0.2692180798416364,
+      "grad_norm": 0.5391792058944702,
+      "learning_rate": 0.000154,
+      "loss": 0.5354532241821289,
+      "step": 510
+    },
+    {
+      "epoch": 0.2744968657208842,
+      "grad_norm": 0.5327297449111938,
+      "learning_rate": 0.0001528888888888889,
+      "loss": 0.5177035331726074,
+      "step": 520
+    },
+    {
+      "epoch": 0.27977565160013196,
+      "grad_norm": 0.5588216781616211,
+      "learning_rate": 0.00015177777777777778,
+      "loss": 0.5256490707397461,
+      "step": 530
+    },
+    {
+      "epoch": 0.28505443747937975,
+      "grad_norm": 0.6024046540260315,
+      "learning_rate": 0.00015066666666666668,
+      "loss": 0.5359174728393554,
+      "step": 540
+    },
+    {
+      "epoch": 0.2903332233586275,
+      "grad_norm": 0.5452874898910522,
+      "learning_rate": 0.00014955555555555555,
+      "loss": 0.5050687313079834,
+      "step": 550
+    },
+    {
+      "epoch": 0.2956120092378753,
+      "grad_norm": 0.5716919898986816,
+      "learning_rate": 0.00014844444444444445,
+      "loss": 0.5043536186218261,
+      "step": 560
+    },
+    {
+      "epoch": 0.3008907951171231,
+      "grad_norm": 0.5621301531791687,
+      "learning_rate": 0.00014733333333333335,
+      "loss": 0.5681197643280029,
+      "step": 570
+    },
+    {
+      "epoch": 0.3061695809963708,
+      "grad_norm": 0.49813947081565857,
+      "learning_rate": 0.00014622222222222223,
+      "loss": 0.5073559761047364,
+      "step": 580
+    },
+    {
+      "epoch": 0.3114483668756186,
+      "grad_norm": 0.5197216272354126,
+      "learning_rate": 0.0001451111111111111,
+      "loss": 0.510869026184082,
+      "step": 590
+    },
+    {
+      "epoch": 0.3167271527548664,
+      "grad_norm": 0.5098935961723328,
+      "learning_rate": 0.000144,
+      "loss": 0.5177080154418945,
+      "step": 600
+    },
+    {
+      "epoch": 0.32200593863411414,
+      "grad_norm": 0.5004557967185974,
+      "learning_rate": 0.0001428888888888889,
+      "loss": 0.5292775154113769,
+      "step": 610
+    },
+    {
+      "epoch": 0.32728472451336194,
+      "grad_norm": 0.6179164052009583,
+      "learning_rate": 0.00014177777777777778,
+      "loss": 0.532755994796753,
+      "step": 620
+    },
+    {
+      "epoch": 0.3325635103926097,
+      "grad_norm": 0.4971306025981903,
+      "learning_rate": 0.00014066666666666668,
+      "loss": 0.5370781421661377,
+      "step": 630
+    },
+    {
+      "epoch": 0.33784229627185747,
+      "grad_norm": 0.5876296758651733,
+      "learning_rate": 0.00013955555555555558,
+      "loss": 0.5408426284790039,
+      "step": 640
+    },
+    {
+      "epoch": 0.34312108215110526,
+      "grad_norm": 0.4632679522037506,
+      "learning_rate": 0.00013844444444444445,
+      "loss": 0.475573205947876,
+      "step": 650
+    },
+    {
+      "epoch": 0.348399868030353,
+      "grad_norm": 0.6051201224327087,
+      "learning_rate": 0.00013733333333333333,
+      "loss": 0.5176257133483887,
+      "step": 660
+    },
+    {
+      "epoch": 0.3536786539096008,
+      "grad_norm": 0.5086127519607544,
+      "learning_rate": 0.00013622222222222223,
+      "loss": 0.543503713607788,
+      "step": 670
+    },
+    {
+      "epoch": 0.3589574397888486,
+      "grad_norm": 0.45412692427635193,
+      "learning_rate": 0.00013511111111111113,
+      "loss": 0.4648271560668945,
+      "step": 680
+    },
+    {
+      "epoch": 0.3642362256680963,
+      "grad_norm": 0.5843290686607361,
+      "learning_rate": 0.000134,
+      "loss": 0.4611194133758545,
+      "step": 690
+    },
+    {
+      "epoch": 0.3695150115473441,
+      "grad_norm": 0.5016586184501648,
+      "learning_rate": 0.00013288888888888888,
+      "loss": 0.5229296684265137,
+      "step": 700
+    },
+    {
+      "epoch": 0.37479379742659186,
+      "grad_norm": 0.594906747341156,
+      "learning_rate": 0.00013177777777777778,
+      "loss": 0.4897459506988525,
+      "step": 710
+    },
+    {
+      "epoch": 0.38007258330583965,
+      "grad_norm": 0.6894946098327637,
+      "learning_rate": 0.00013066666666666668,
+      "loss": 0.5067539691925049,
+      "step": 720
+    },
+    {
+      "epoch": 0.38535136918508744,
+      "grad_norm": 0.5899446606636047,
+      "learning_rate": 0.00012955555555555555,
+      "loss": 0.572650671005249,
+      "step": 730
+    },
+    {
+      "epoch": 0.3906301550643352,
+      "grad_norm": 0.5914052724838257,
+      "learning_rate": 0.00012844444444444446,
+      "loss": 0.49350743293762206,
+      "step": 740
+    },
+    {
+      "epoch": 0.395908940943583,
+      "grad_norm": 0.5701265931129456,
+      "learning_rate": 0.00012733333333333336,
+      "loss": 0.4886340141296387,
+      "step": 750
+    },
+    {
+      "epoch": 0.40118772682283077,
+      "grad_norm": 0.5554320216178894,
+      "learning_rate": 0.00012622222222222223,
+      "loss": 0.5152291774749755,
+      "step": 760
+    },
+    {
+      "epoch": 0.4064665127020785,
+      "grad_norm": 0.542721688747406,
+      "learning_rate": 0.0001251111111111111,
+      "loss": 0.5169697284698487,
+      "step": 770
+    },
+    {
+      "epoch": 0.4117452985813263,
+      "grad_norm": 0.5239601731300354,
+      "learning_rate": 0.000124,
+      "loss": 0.5226495265960693,
+      "step": 780
+    },
+    {
+      "epoch": 0.41702408446057404,
+      "grad_norm": 0.5628821849822998,
+      "learning_rate": 0.0001228888888888889,
+      "loss": 0.4952070236206055,
+      "step": 790
+    },
+    {
+      "epoch": 0.42230287033982183,
+      "grad_norm": 0.53690505027771,
+      "learning_rate": 0.0001217777777777778,
+      "loss": 0.5176570892333985,
+      "step": 800
+    },
+    {
+      "epoch": 0.42758165621906963,
+      "grad_norm": 0.47472912073135376,
+      "learning_rate": 0.00012066666666666668,
+      "loss": 0.48554182052612305,
+      "step": 810
+    },
+    {
+      "epoch": 0.43286044209831737,
+      "grad_norm": 0.5943832397460938,
+      "learning_rate": 0.00011955555555555556,
+      "loss": 0.5519014835357666,
+      "step": 820
+    },
+    {
+      "epoch": 0.43813922797756516,
+      "grad_norm": 0.5702099800109863,
+      "learning_rate": 0.00011844444444444444,
+      "loss": 0.5203097343444825,
+      "step": 830
+    },
+    {
+      "epoch": 0.44341801385681295,
+      "grad_norm": 0.5570870637893677,
+      "learning_rate": 0.00011733333333333334,
+      "loss": 0.5008646488189697,
+      "step": 840
+    },
+    {
+      "epoch": 0.4486967997360607,
+      "grad_norm": 0.6742717623710632,
+      "learning_rate": 0.00011622222222222223,
+      "loss": 0.4884360313415527,
+      "step": 850
+    },
+    {
+      "epoch": 0.4539755856153085,
+      "grad_norm": 0.5782440900802612,
+      "learning_rate": 0.00011511111111111112,
+      "loss": 0.497051477432251,
+      "step": 860
+    },
+    {
+      "epoch": 0.4592543714945563,
+      "grad_norm": 0.6157666444778442,
+      "learning_rate": 0.00011399999999999999,
+      "loss": 0.5011940956115722,
+      "step": 870
+    },
+    {
+      "epoch": 0.464533157373804,
+      "grad_norm": 0.4744451344013214,
+      "learning_rate": 0.0001128888888888889,
+      "loss": 0.4997218132019043,
+      "step": 880
+    },
+    {
+      "epoch": 0.4698119432530518,
+      "grad_norm": 0.5648385286331177,
+      "learning_rate": 0.00011177777777777778,
+      "loss": 0.5077646255493165,
+      "step": 890
+    },
+    {
+      "epoch": 0.47509072913229955,
+      "grad_norm": 0.5268929600715637,
+      "learning_rate": 0.00011066666666666667,
+      "loss": 0.4928537368774414,
+      "step": 900
+    },
+    {
+      "epoch": 0.48036951501154734,
+      "grad_norm": 0.5827873945236206,
+      "learning_rate": 0.00010955555555555557,
+      "loss": 0.5176413536071778,
+      "step": 910
+    },
+    {
+      "epoch": 0.48564830089079514,
+      "grad_norm": 0.5056174993515015,
+      "learning_rate": 0.00010844444444444446,
+      "loss": 0.5180400848388672,
+      "step": 920
+    },
+    {
+      "epoch": 0.4909270867700429,
+      "grad_norm": 0.47383710741996765,
+      "learning_rate": 0.00010733333333333333,
+      "loss": 0.4904231071472168,
+      "step": 930
+    },
+    {
+      "epoch": 0.49620587264929067,
+      "grad_norm": 0.5303201079368591,
+      "learning_rate": 0.00010622222222222222,
+      "loss": 0.4838510036468506,
+      "step": 940
+    },
+    {
+      "epoch": 0.5014846585285384,
+      "grad_norm": 0.6136945486068726,
+      "learning_rate": 0.00010511111111111112,
+      "loss": 0.4908186912536621,
+      "step": 950
+    },
+    {
+      "epoch": 0.5067634444077862,
+      "grad_norm": 0.6062966585159302,
+      "learning_rate": 0.00010400000000000001,
+      "loss": 0.5015266895294189,
+      "step": 960
+    },
+    {
+      "epoch": 0.512042230287034,
+      "grad_norm": 0.5623139142990112,
+      "learning_rate": 0.0001028888888888889,
+      "loss": 0.5161266803741456,
+      "step": 970
+    },
+    {
+      "epoch": 0.5173210161662818,
+      "grad_norm": 0.5548786520957947,
+      "learning_rate": 0.00010177777777777777,
+      "loss": 0.4842812538146973,
+      "step": 980
+    },
+    {
+      "epoch": 0.5225998020455296,
+      "grad_norm": 0.4839674234390259,
+      "learning_rate": 0.00010066666666666667,
+      "loss": 0.47931456565856934,
+      "step": 990
+    },
+    {
+      "epoch": 0.5278785879247773,
+      "grad_norm": 0.6106690764427185,
+      "learning_rate": 9.955555555555556e-05,
+      "loss": 0.5249813079833985,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5278785879247773,
+      "eval_loss": 0.4978668689727783,
+      "eval_runtime": 459.5591,
+      "eval_samples_per_second": 24.373,
+      "eval_steps_per_second": 6.095,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1895,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 1.1957050265403264e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

qwen3.5-2b/checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63f5227842d4c60d51e48d582480b968b2a26456e3111e78999104a00e72c35c
+size 5265

qwen3.5-2b/tb/events.out.tfevents.1789942145.fed349279e2c.8211.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a28bdce6a24aa7629b8f847f17deb349f7296ec63e987d7db3f5fa8e21c9eab0
-size 16665
+oid sha256:d8cb59132d4a5f5f32d6bf0c666a029e77792379d7374978e1a5e35c334efd38
+size 27752

qwen3.5-2b/test_eval/metrics.json

@@ -1,6 +1,6 @@
 {
-  "wer": 0.4919080716351276,
+  "wer": 0.3787225407133073,
   "exact_match": 0.0,
-  "hallucination_rate": 0.09375,
+  "hallucination_rate": 0.0546875,
   "n_examples": 128
 }