checkpoint-1000

gemma-3-1b-it/best_checkpoint_wer/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e644975c99ac223264512fb07c7c08963ad42d3000d0f2bab24f4b5b82b1ab8a
+oid sha256:c4c531843e623a958a0ad70a5a27d3c5802f98e86c290605e1eae70f0336ce1f
 size 104414464

gemma-3-1b-it/best_checkpoint_wer/best_metrics.json

@@ -1,7 +1,7 @@
 {
-  "step": 500,
-  "wer": 1.1390086753589366,
+  "step": 1000,
+  "wer": 1.068743341281518,
   "exact_match": 0.0,
-  "hallucination_rate": 0.28125,
+  "hallucination_rate": 0.2734375,
   "n_examples": 128
 }

gemma-3-1b-it/best_checkpoint_wer/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54ec7f55c4e5598212048715269706a320ab15a7b9e5e6d110b818b9cee06a6e
+oid sha256:7a134e034421ad6ee5b2ea95a657be8170c3910556af6e21b7abaf21b8cdfc53
 size 209043559

gemma-3-1b-it/best_checkpoint_wer/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2132fc4d19d14100b640922770daaccd5ab22ad28b26977bde2e1edfdf786ca0
+oid sha256:f50a92d6f3dd5f4837113f6f1a8e0f390b6c016f02edd62dff252f181500c03a
 size 14645

gemma-3-1b-it/best_checkpoint_wer/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d04075e5bd36a63855dde80f5114b540b10a15f0bce2934328ba1707e95005bf
+oid sha256:801efa7a34763673ae41afa0f5537f3b9eb879e89866fdaf355f422e93c18286
 size 1465

gemma-3-1b-it/best_checkpoint_wer/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.26229508196721313,
+  "epoch": 0.5245901639344263,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -366,6 +366,372 @@
       "eval_samples_per_second": 34.443,
       "eval_steps_per_second": 8.613,
       "step": 500
+    },
+    {
+      "epoch": 0.26229508196721313,
+      "step": 500,
+      "test_best_wer": 1.1390086753589366,
+      "test_exact_match": 0.0,
+      "test_hallucination_rate": 0.28125,
+      "test_wer": 1.1390086753589366
+    },
+    {
+      "epoch": 0.26754098360655737,
+      "grad_norm": 0.6836485266685486,
+      "learning_rate": 0.00015438983986747654,
+      "loss": 0.7229701519012451,
+      "step": 510
+    },
+    {
+      "epoch": 0.27278688524590167,
+      "grad_norm": 0.6233025193214417,
+      "learning_rate": 0.00015328547763666483,
+      "loss": 0.7291789531707764,
+      "step": 520
+    },
+    {
+      "epoch": 0.2780327868852459,
+      "grad_norm": 0.7435803413391113,
+      "learning_rate": 0.00015218111540585313,
+      "loss": 0.6764275074005127,
+      "step": 530
+    },
+    {
+      "epoch": 0.28327868852459015,
+      "grad_norm": 0.6755605936050415,
+      "learning_rate": 0.00015107675317504142,
+      "loss": 0.713279390335083,
+      "step": 540
+    },
+    {
+      "epoch": 0.28852459016393445,
+      "grad_norm": 1.268239974975586,
+      "learning_rate": 0.00014997239094422971,
+      "loss": 0.7585635662078858,
+      "step": 550
+    },
+    {
+      "epoch": 0.2937704918032787,
+      "grad_norm": 0.6028411388397217,
+      "learning_rate": 0.000148868028713418,
+      "loss": 0.6682120323181152,
+      "step": 560
+    },
+    {
+      "epoch": 0.29901639344262293,
+      "grad_norm": 0.6842379570007324,
+      "learning_rate": 0.0001477636664826063,
+      "loss": 0.6770430564880371,
+      "step": 570
+    },
+    {
+      "epoch": 0.3042622950819672,
+      "grad_norm": 1.2270914316177368,
+      "learning_rate": 0.0001466593042517946,
+      "loss": 0.704667329788208,
+      "step": 580
+    },
+    {
+      "epoch": 0.30950819672131147,
+      "grad_norm": 0.9267876148223877,
+      "learning_rate": 0.0001455549420209829,
+      "loss": 0.6503843784332275,
+      "step": 590
+    },
+    {
+      "epoch": 0.31475409836065577,
+      "grad_norm": 0.6021356582641602,
+      "learning_rate": 0.00014445057979017118,
+      "loss": 0.691249418258667,
+      "step": 600
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.7987799048423767,
+      "learning_rate": 0.00014334621755935948,
+      "loss": 0.6753934383392334,
+      "step": 610
+    },
+    {
+      "epoch": 0.32524590163934425,
+      "grad_norm": 0.7932137250900269,
+      "learning_rate": 0.00014224185532854777,
+      "loss": 0.740220594406128,
+      "step": 620
+    },
+    {
+      "epoch": 0.33049180327868855,
+      "grad_norm": 0.6394649744033813,
+      "learning_rate": 0.00014113749309773606,
+      "loss": 0.6681424617767334,
+      "step": 630
+    },
+    {
+      "epoch": 0.3357377049180328,
+      "grad_norm": 0.6621270179748535,
+      "learning_rate": 0.00014003313086692436,
+      "loss": 0.6998953342437744,
+      "step": 640
+    },
+    {
+      "epoch": 0.34098360655737703,
+      "grad_norm": 0.6594683527946472,
+      "learning_rate": 0.00013892876863611265,
+      "loss": 0.6756977081298828,
+      "step": 650
+    },
+    {
+      "epoch": 0.3462295081967213,
+      "grad_norm": 0.6369149684906006,
+      "learning_rate": 0.00013782440640530095,
+      "loss": 0.6814823627471924,
+      "step": 660
+    },
+    {
+      "epoch": 0.35147540983606557,
+      "grad_norm": 0.5597897171974182,
+      "learning_rate": 0.00013672004417448924,
+      "loss": 0.6507920265197754,
+      "step": 670
+    },
+    {
+      "epoch": 0.35672131147540986,
+      "grad_norm": 0.6039972901344299,
+      "learning_rate": 0.00013561568194367753,
+      "loss": 0.6367014408111572,
+      "step": 680
+    },
+    {
+      "epoch": 0.3619672131147541,
+      "grad_norm": 0.5688148736953735,
+      "learning_rate": 0.00013451131971286583,
+      "loss": 0.6138595104217529,
+      "step": 690
+    },
+    {
+      "epoch": 0.36721311475409835,
+      "grad_norm": 0.6039051413536072,
+      "learning_rate": 0.00013340695748205412,
+      "loss": 0.6540034294128418,
+      "step": 700
+    },
+    {
+      "epoch": 0.37245901639344264,
+      "grad_norm": 0.6174374222755432,
+      "learning_rate": 0.00013230259525124242,
+      "loss": 0.6867434024810791,
+      "step": 710
+    },
+    {
+      "epoch": 0.3777049180327869,
+      "grad_norm": 0.8699930906295776,
+      "learning_rate": 0.0001311982330204307,
+      "loss": 0.6717788696289062,
+      "step": 720
+    },
+    {
+      "epoch": 0.3829508196721311,
+      "grad_norm": 0.7272820472717285,
+      "learning_rate": 0.000130093870789619,
+      "loss": 0.6900745868682862,
+      "step": 730
+    },
+    {
+      "epoch": 0.3881967213114754,
+      "grad_norm": 4.704572677612305,
+      "learning_rate": 0.0001289895085588073,
+      "loss": 0.6664741992950439,
+      "step": 740
+    },
+    {
+      "epoch": 0.39344262295081966,
+      "grad_norm": 0.7410299181938171,
+      "learning_rate": 0.0001278851463279956,
+      "loss": 0.6386402606964111,
+      "step": 750
+    },
+    {
+      "epoch": 0.39868852459016396,
+      "grad_norm": 0.6447997093200684,
+      "learning_rate": 0.00012678078409718389,
+      "loss": 0.656829833984375,
+      "step": 760
+    },
+    {
+      "epoch": 0.4039344262295082,
+      "grad_norm": 0.5744156837463379,
+      "learning_rate": 0.00012567642186637218,
+      "loss": 0.6654098510742188,
+      "step": 770
+    },
+    {
+      "epoch": 0.40918032786885244,
+      "grad_norm": 0.5341398119926453,
+      "learning_rate": 0.00012457205963556047,
+      "loss": 0.6406219005584717,
+      "step": 780
+    },
+    {
+      "epoch": 0.41442622950819674,
+      "grad_norm": 0.600540280342102,
+      "learning_rate": 0.00012346769740474877,
+      "loss": 0.659253454208374,
+      "step": 790
+    },
+    {
+      "epoch": 0.419672131147541,
+      "grad_norm": 0.7170221209526062,
+      "learning_rate": 0.00012236333517393706,
+      "loss": 0.6802017211914062,
+      "step": 800
+    },
+    {
+      "epoch": 0.4249180327868852,
+      "grad_norm": 0.7966761589050293,
+      "learning_rate": 0.00012125897294312535,
+      "loss": 0.6104480743408203,
+      "step": 810
+    },
+    {
+      "epoch": 0.4301639344262295,
+      "grad_norm": 0.671951413154602,
+      "learning_rate": 0.00012015461071231365,
+      "loss": 0.7058865070343018,
+      "step": 820
+    },
+    {
+      "epoch": 0.43540983606557376,
+      "grad_norm": 0.6206080913543701,
+      "learning_rate": 0.00011905024848150194,
+      "loss": 0.6379797458648682,
+      "step": 830
+    },
+    {
+      "epoch": 0.44065573770491806,
+      "grad_norm": 0.6439060568809509,
+      "learning_rate": 0.00011794588625069024,
+      "loss": 0.6559050559997559,
+      "step": 840
+    },
+    {
+      "epoch": 0.4459016393442623,
+      "grad_norm": 0.7650911808013916,
+      "learning_rate": 0.00011684152401987853,
+      "loss": 0.664661169052124,
+      "step": 850
+    },
+    {
+      "epoch": 0.45114754098360654,
+      "grad_norm": 0.6379468441009521,
+      "learning_rate": 0.00011573716178906681,
+      "loss": 0.6635408878326416,
+      "step": 860
+    },
+    {
+      "epoch": 0.45639344262295084,
+      "grad_norm": 0.6033166646957397,
+      "learning_rate": 0.00011463279955825512,
+      "loss": 0.6439225673675537,
+      "step": 870
+    },
+    {
+      "epoch": 0.4616393442622951,
+      "grad_norm": 0.6554288268089294,
+      "learning_rate": 0.0001135284373274434,
+      "loss": 0.6234912872314453,
+      "step": 880
+    },
+    {
+      "epoch": 0.4668852459016393,
+      "grad_norm": 0.7938706278800964,
+      "learning_rate": 0.0001124240750966317,
+      "loss": 0.6458295822143555,
+      "step": 890
+    },
+    {
+      "epoch": 0.4721311475409836,
+      "grad_norm": 0.7794424891471863,
+      "learning_rate": 0.00011131971286581999,
+      "loss": 0.6645576000213623,
+      "step": 900
+    },
+    {
+      "epoch": 0.47737704918032786,
+      "grad_norm": 0.6669194102287292,
+      "learning_rate": 0.0001102153506350083,
+      "loss": 0.706819725036621,
+      "step": 910
+    },
+    {
+      "epoch": 0.48262295081967216,
+      "grad_norm": 0.5930067896842957,
+      "learning_rate": 0.00010911098840419657,
+      "loss": 0.6377612113952636,
+      "step": 920
+    },
+    {
+      "epoch": 0.4878688524590164,
+      "grad_norm": 0.5960756540298462,
+      "learning_rate": 0.00010800662617338488,
+      "loss": 0.6585844993591309,
+      "step": 930
+    },
+    {
+      "epoch": 0.49311475409836064,
+      "grad_norm": 0.8185632228851318,
+      "learning_rate": 0.00010690226394257316,
+      "loss": 0.6509750366210938,
+      "step": 940
+    },
+    {
+      "epoch": 0.49836065573770494,
+      "grad_norm": 0.5078699588775635,
+      "learning_rate": 0.00010579790171176147,
+      "loss": 0.6630078315734863,
+      "step": 950
+    },
+    {
+      "epoch": 0.5036065573770492,
+      "grad_norm": 0.5847029685974121,
+      "learning_rate": 0.00010469353948094975,
+      "loss": 0.6561220169067383,
+      "step": 960
+    },
+    {
+      "epoch": 0.5088524590163934,
+      "grad_norm": 0.5837432146072388,
+      "learning_rate": 0.00010358917725013806,
+      "loss": 0.6355574607849122,
+      "step": 970
+    },
+    {
+      "epoch": 0.5140983606557377,
+      "grad_norm": 0.5932501554489136,
+      "learning_rate": 0.00010248481501932634,
+      "loss": 0.6037593364715577,
+      "step": 980
+    },
+    {
+      "epoch": 0.519344262295082,
+      "grad_norm": 0.6490769982337952,
+      "learning_rate": 0.00010138045278851464,
+      "loss": 0.7359431266784668,
+      "step": 990
+    },
+    {
+      "epoch": 0.5245901639344263,
+      "grad_norm": 0.8101118206977844,
+      "learning_rate": 0.00010027609055770292,
+      "loss": 0.5702367305755616,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5245901639344263,
+      "eval_loss": 0.6413107514381409,
+      "eval_runtime": 327.3739,
+      "eval_samples_per_second": 34.459,
+      "eval_steps_per_second": 8.617,
+      "step": 1000
     }
   ],
   "logging_steps": 10,
@@ -385,7 +751,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.8628493340644864e+16,
+  "total_flos": 5.744543485750426e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

gemma-3-1b-it/checkpoint-1000/README.md

@@ -0,0 +1,207 @@
+---
+base_model: google/gemma-3-1b-it
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:google/gemma-3-1b-it
+- 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

gemma-3-1b-it/checkpoint-1000/adapter_config.json

@@ -0,0 +1,51 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-3-1b-it",
+  "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": [
+    "down_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "up_proj",
+    "gate_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
+}

gemma-3-1b-it/checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4c531843e623a958a0ad70a5a27d3c5802f98e86c290605e1eae70f0336ce1f
+size 104414464

gemma-3-1b-it/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a134e034421ad6ee5b2ea95a657be8170c3910556af6e21b7abaf21b8cdfc53
+size 209043559

gemma-3-1b-it/checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f50a92d6f3dd5f4837113f6f1a8e0f390b6c016f02edd62dff252f181500c03a
+size 14645

gemma-3-1b-it/checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:801efa7a34763673ae41afa0f5537f3b9eb879e89866fdaf355f422e93c18286
+size 1465

gemma-3-1b-it/checkpoint-1000/trainer_state.json

@@ -0,0 +1,758 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5245901639344263,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005245901639344262,
+      "grad_norm": 5.850006580352783,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 1.626298713684082,
+      "step": 10
+    },
+    {
+      "epoch": 0.010491803278688525,
+      "grad_norm": 1.7961169481277466,
+      "learning_rate": 3.958333333333333e-05,
+      "loss": 1.3221087455749512,
+      "step": 20
+    },
+    {
+      "epoch": 0.015737704918032787,
+      "grad_norm": 1.4881651401519775,
+      "learning_rate": 6.041666666666667e-05,
+      "loss": 1.1436286926269532,
+      "step": 30
+    },
+    {
+      "epoch": 0.02098360655737705,
+      "grad_norm": 1.0592900514602661,
+      "learning_rate": 8.125000000000001e-05,
+      "loss": 0.9118364334106446,
+      "step": 40
+    },
+    {
+      "epoch": 0.02622950819672131,
+      "grad_norm": 1.3136152029037476,
+      "learning_rate": 0.00010208333333333333,
+      "loss": 0.9902483940124511,
+      "step": 50
+    },
+    {
+      "epoch": 0.031475409836065574,
+      "grad_norm": 1.0517693758010864,
+      "learning_rate": 0.00012291666666666668,
+      "loss": 0.9533065795898438,
+      "step": 60
+    },
+    {
+      "epoch": 0.036721311475409836,
+      "grad_norm": 1.0763620138168335,
+      "learning_rate": 0.00014375,
+      "loss": 0.9590832710266113,
+      "step": 70
+    },
+    {
+      "epoch": 0.0419672131147541,
+      "grad_norm": 1.126420497894287,
+      "learning_rate": 0.00016458333333333334,
+      "loss": 0.8696105003356933,
+      "step": 80
+    },
+    {
+      "epoch": 0.04721311475409836,
+      "grad_norm": 1.0479974746704102,
+      "learning_rate": 0.00018541666666666668,
+      "loss": 0.8585530281066894,
+      "step": 90
+    },
+    {
+      "epoch": 0.05245901639344262,
+      "grad_norm": 0.9453676342964172,
+      "learning_rate": 0.0001996686913307565,
+      "loss": 0.81344633102417,
+      "step": 100
+    },
+    {
+      "epoch": 0.057704918032786885,
+      "grad_norm": 0.9837343692779541,
+      "learning_rate": 0.0001985643290999448,
+      "loss": 0.9181200981140136,
+      "step": 110
+    },
+    {
+      "epoch": 0.06295081967213115,
+      "grad_norm": 0.8958956003189087,
+      "learning_rate": 0.00019745996686913308,
+      "loss": 0.826357650756836,
+      "step": 120
+    },
+    {
+      "epoch": 0.06819672131147542,
+      "grad_norm": 0.9927870631217957,
+      "learning_rate": 0.0001963556046383214,
+      "loss": 0.8804688453674316,
+      "step": 130
+    },
+    {
+      "epoch": 0.07344262295081967,
+      "grad_norm": 0.8682142496109009,
+      "learning_rate": 0.00019525124240750967,
+      "loss": 0.8082976341247559,
+      "step": 140
+    },
+    {
+      "epoch": 0.07868852459016394,
+      "grad_norm": 0.837242841720581,
+      "learning_rate": 0.00019414688017669799,
+      "loss": 0.8015812873840332,
+      "step": 150
+    },
+    {
+      "epoch": 0.0839344262295082,
+      "grad_norm": 1.099856972694397,
+      "learning_rate": 0.00019304251794588625,
+      "loss": 0.7791732311248779,
+      "step": 160
+    },
+    {
+      "epoch": 0.08918032786885247,
+      "grad_norm": 0.9170840978622437,
+      "learning_rate": 0.00019193815571507457,
+      "loss": 0.8227507591247558,
+      "step": 170
+    },
+    {
+      "epoch": 0.09442622950819672,
+      "grad_norm": 0.8296833038330078,
+      "learning_rate": 0.00019083379348426284,
+      "loss": 0.7757059097290039,
+      "step": 180
+    },
+    {
+      "epoch": 0.09967213114754099,
+      "grad_norm": 0.7342070937156677,
+      "learning_rate": 0.00018972943125345116,
+      "loss": 0.7799826622009277,
+      "step": 190
+    },
+    {
+      "epoch": 0.10491803278688525,
+      "grad_norm": 0.7804243564605713,
+      "learning_rate": 0.00018862506902263943,
+      "loss": 0.7913103580474854,
+      "step": 200
+    },
+    {
+      "epoch": 0.11016393442622952,
+      "grad_norm": 0.7638176083564758,
+      "learning_rate": 0.00018752070679182775,
+      "loss": 0.7876776695251465,
+      "step": 210
+    },
+    {
+      "epoch": 0.11540983606557377,
+      "grad_norm": 0.6659265160560608,
+      "learning_rate": 0.00018641634456101602,
+      "loss": 0.7114231586456299,
+      "step": 220
+    },
+    {
+      "epoch": 0.12065573770491804,
+      "grad_norm": 0.6473881602287292,
+      "learning_rate": 0.00018531198233020434,
+      "loss": 0.7239602088928223,
+      "step": 230
+    },
+    {
+      "epoch": 0.1259016393442623,
+      "grad_norm": 0.8192205429077148,
+      "learning_rate": 0.0001842076200993926,
+      "loss": 0.7307174205780029,
+      "step": 240
+    },
+    {
+      "epoch": 0.13114754098360656,
+      "grad_norm": 0.6621026396751404,
+      "learning_rate": 0.00018310325786858092,
+      "loss": 0.7196334362030029,
+      "step": 250
+    },
+    {
+      "epoch": 0.13639344262295083,
+      "grad_norm": 0.6377759575843811,
+      "learning_rate": 0.0001819988956377692,
+      "loss": 0.761665153503418,
+      "step": 260
+    },
+    {
+      "epoch": 0.14163934426229507,
+      "grad_norm": 0.7564328908920288,
+      "learning_rate": 0.0001808945334069575,
+      "loss": 0.7283723831176758,
+      "step": 270
+    },
+    {
+      "epoch": 0.14688524590163934,
+      "grad_norm": 0.7781689167022705,
+      "learning_rate": 0.00017979017117614578,
+      "loss": 0.7663159370422363,
+      "step": 280
+    },
+    {
+      "epoch": 0.1521311475409836,
+      "grad_norm": 0.7704823017120361,
+      "learning_rate": 0.0001786858089453341,
+      "loss": 0.7273806095123291,
+      "step": 290
+    },
+    {
+      "epoch": 0.15737704918032788,
+      "grad_norm": 0.6168962717056274,
+      "learning_rate": 0.00017758144671452237,
+      "loss": 0.7601676940917969,
+      "step": 300
+    },
+    {
+      "epoch": 0.16262295081967212,
+      "grad_norm": 0.747313380241394,
+      "learning_rate": 0.0001764770844837107,
+      "loss": 0.7394940853118896,
+      "step": 310
+    },
+    {
+      "epoch": 0.1678688524590164,
+      "grad_norm": 0.6736217737197876,
+      "learning_rate": 0.00017537272225289895,
+      "loss": 0.674213457107544,
+      "step": 320
+    },
+    {
+      "epoch": 0.17311475409836066,
+      "grad_norm": 0.7672621011734009,
+      "learning_rate": 0.00017426836002208728,
+      "loss": 0.6635504722595215,
+      "step": 330
+    },
+    {
+      "epoch": 0.17836065573770493,
+      "grad_norm": 0.6182668209075928,
+      "learning_rate": 0.00017316399779127554,
+      "loss": 0.6947505950927735,
+      "step": 340
+    },
+    {
+      "epoch": 0.18360655737704917,
+      "grad_norm": 0.6231220960617065,
+      "learning_rate": 0.00017205963556046384,
+      "loss": 0.7503675937652587,
+      "step": 350
+    },
+    {
+      "epoch": 0.18885245901639344,
+      "grad_norm": 0.7776580452919006,
+      "learning_rate": 0.00017095527332965213,
+      "loss": 0.7351272106170654,
+      "step": 360
+    },
+    {
+      "epoch": 0.1940983606557377,
+      "grad_norm": 0.7008368968963623,
+      "learning_rate": 0.00016985091109884042,
+      "loss": 0.6939175605773926,
+      "step": 370
+    },
+    {
+      "epoch": 0.19934426229508198,
+      "grad_norm": 0.7504845261573792,
+      "learning_rate": 0.00016874654886802872,
+      "loss": 0.7262158393859863,
+      "step": 380
+    },
+    {
+      "epoch": 0.20459016393442622,
+      "grad_norm": 0.6740432977676392,
+      "learning_rate": 0.000167642186637217,
+      "loss": 0.7514342308044434,
+      "step": 390
+    },
+    {
+      "epoch": 0.2098360655737705,
+      "grad_norm": 0.6686267256736755,
+      "learning_rate": 0.0001665378244064053,
+      "loss": 0.6774350166320801,
+      "step": 400
+    },
+    {
+      "epoch": 0.21508196721311476,
+      "grad_norm": 0.5805259943008423,
+      "learning_rate": 0.0001654334621755936,
+      "loss": 0.6829588413238525,
+      "step": 410
+    },
+    {
+      "epoch": 0.22032786885245903,
+      "grad_norm": 0.6207637786865234,
+      "learning_rate": 0.0001643290999447819,
+      "loss": 0.6976052761077881,
+      "step": 420
+    },
+    {
+      "epoch": 0.22557377049180327,
+      "grad_norm": 1.0807863473892212,
+      "learning_rate": 0.0001632247377139702,
+      "loss": 0.7167800426483154,
+      "step": 430
+    },
+    {
+      "epoch": 0.23081967213114754,
+      "grad_norm": 0.6717860698699951,
+      "learning_rate": 0.00016212037548315848,
+      "loss": 0.701947021484375,
+      "step": 440
+    },
+    {
+      "epoch": 0.2360655737704918,
+      "grad_norm": 0.6229609847068787,
+      "learning_rate": 0.00016101601325234678,
+      "loss": 0.6681315898895264,
+      "step": 450
+    },
+    {
+      "epoch": 0.24131147540983608,
+      "grad_norm": 0.8894275426864624,
+      "learning_rate": 0.00015991165102153507,
+      "loss": 0.7274843692779541,
+      "step": 460
+    },
+    {
+      "epoch": 0.24655737704918032,
+      "grad_norm": 0.8598907589912415,
+      "learning_rate": 0.00015880728879072336,
+      "loss": 0.6865033149719239,
+      "step": 470
+    },
+    {
+      "epoch": 0.2518032786885246,
+      "grad_norm": 1.4645612239837646,
+      "learning_rate": 0.00015770292655991166,
+      "loss": 0.6898164749145508,
+      "step": 480
+    },
+    {
+      "epoch": 0.25704918032786883,
+      "grad_norm": 0.7187657952308655,
+      "learning_rate": 0.00015659856432909995,
+      "loss": 0.7331682682037354,
+      "step": 490
+    },
+    {
+      "epoch": 0.26229508196721313,
+      "grad_norm": 0.6352348327636719,
+      "learning_rate": 0.00015549420209828824,
+      "loss": 0.6853579998016357,
+      "step": 500
+    },
+    {
+      "epoch": 0.26229508196721313,
+      "eval_loss": 0.6940423250198364,
+      "eval_runtime": 327.5265,
+      "eval_samples_per_second": 34.443,
+      "eval_steps_per_second": 8.613,
+      "step": 500
+    },
+    {
+      "epoch": 0.26229508196721313,
+      "step": 500,
+      "test_best_wer": 1.1390086753589366,
+      "test_exact_match": 0.0,
+      "test_hallucination_rate": 0.28125,
+      "test_wer": 1.1390086753589366
+    },
+    {
+      "epoch": 0.26754098360655737,
+      "grad_norm": 0.6836485266685486,
+      "learning_rate": 0.00015438983986747654,
+      "loss": 0.7229701519012451,
+      "step": 510
+    },
+    {
+      "epoch": 0.27278688524590167,
+      "grad_norm": 0.6233025193214417,
+      "learning_rate": 0.00015328547763666483,
+      "loss": 0.7291789531707764,
+      "step": 520
+    },
+    {
+      "epoch": 0.2780327868852459,
+      "grad_norm": 0.7435803413391113,
+      "learning_rate": 0.00015218111540585313,
+      "loss": 0.6764275074005127,
+      "step": 530
+    },
+    {
+      "epoch": 0.28327868852459015,
+      "grad_norm": 0.6755605936050415,
+      "learning_rate": 0.00015107675317504142,
+      "loss": 0.713279390335083,
+      "step": 540
+    },
+    {
+      "epoch": 0.28852459016393445,
+      "grad_norm": 1.268239974975586,
+      "learning_rate": 0.00014997239094422971,
+      "loss": 0.7585635662078858,
+      "step": 550
+    },
+    {
+      "epoch": 0.2937704918032787,
+      "grad_norm": 0.6028411388397217,
+      "learning_rate": 0.000148868028713418,
+      "loss": 0.6682120323181152,
+      "step": 560
+    },
+    {
+      "epoch": 0.29901639344262293,
+      "grad_norm": 0.6842379570007324,
+      "learning_rate": 0.0001477636664826063,
+      "loss": 0.6770430564880371,
+      "step": 570
+    },
+    {
+      "epoch": 0.3042622950819672,
+      "grad_norm": 1.2270914316177368,
+      "learning_rate": 0.0001466593042517946,
+      "loss": 0.704667329788208,
+      "step": 580
+    },
+    {
+      "epoch": 0.30950819672131147,
+      "grad_norm": 0.9267876148223877,
+      "learning_rate": 0.0001455549420209829,
+      "loss": 0.6503843784332275,
+      "step": 590
+    },
+    {
+      "epoch": 0.31475409836065577,
+      "grad_norm": 0.6021356582641602,
+      "learning_rate": 0.00014445057979017118,
+      "loss": 0.691249418258667,
+      "step": 600
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.7987799048423767,
+      "learning_rate": 0.00014334621755935948,
+      "loss": 0.6753934383392334,
+      "step": 610
+    },
+    {
+      "epoch": 0.32524590163934425,
+      "grad_norm": 0.7932137250900269,
+      "learning_rate": 0.00014224185532854777,
+      "loss": 0.740220594406128,
+      "step": 620
+    },
+    {
+      "epoch": 0.33049180327868855,
+      "grad_norm": 0.6394649744033813,
+      "learning_rate": 0.00014113749309773606,
+      "loss": 0.6681424617767334,
+      "step": 630
+    },
+    {
+      "epoch": 0.3357377049180328,
+      "grad_norm": 0.6621270179748535,
+      "learning_rate": 0.00014003313086692436,
+      "loss": 0.6998953342437744,
+      "step": 640
+    },
+    {
+      "epoch": 0.34098360655737703,
+      "grad_norm": 0.6594683527946472,
+      "learning_rate": 0.00013892876863611265,
+      "loss": 0.6756977081298828,
+      "step": 650
+    },
+    {
+      "epoch": 0.3462295081967213,
+      "grad_norm": 0.6369149684906006,
+      "learning_rate": 0.00013782440640530095,
+      "loss": 0.6814823627471924,
+      "step": 660
+    },
+    {
+      "epoch": 0.35147540983606557,
+      "grad_norm": 0.5597897171974182,
+      "learning_rate": 0.00013672004417448924,
+      "loss": 0.6507920265197754,
+      "step": 670
+    },
+    {
+      "epoch": 0.35672131147540986,
+      "grad_norm": 0.6039972901344299,
+      "learning_rate": 0.00013561568194367753,
+      "loss": 0.6367014408111572,
+      "step": 680
+    },
+    {
+      "epoch": 0.3619672131147541,
+      "grad_norm": 0.5688148736953735,
+      "learning_rate": 0.00013451131971286583,
+      "loss": 0.6138595104217529,
+      "step": 690
+    },
+    {
+      "epoch": 0.36721311475409835,
+      "grad_norm": 0.6039051413536072,
+      "learning_rate": 0.00013340695748205412,
+      "loss": 0.6540034294128418,
+      "step": 700
+    },
+    {
+      "epoch": 0.37245901639344264,
+      "grad_norm": 0.6174374222755432,
+      "learning_rate": 0.00013230259525124242,
+      "loss": 0.6867434024810791,
+      "step": 710
+    },
+    {
+      "epoch": 0.3777049180327869,
+      "grad_norm": 0.8699930906295776,
+      "learning_rate": 0.0001311982330204307,
+      "loss": 0.6717788696289062,
+      "step": 720
+    },
+    {
+      "epoch": 0.3829508196721311,
+      "grad_norm": 0.7272820472717285,
+      "learning_rate": 0.000130093870789619,
+      "loss": 0.6900745868682862,
+      "step": 730
+    },
+    {
+      "epoch": 0.3881967213114754,
+      "grad_norm": 4.704572677612305,
+      "learning_rate": 0.0001289895085588073,
+      "loss": 0.6664741992950439,
+      "step": 740
+    },
+    {
+      "epoch": 0.39344262295081966,
+      "grad_norm": 0.7410299181938171,
+      "learning_rate": 0.0001278851463279956,
+      "loss": 0.6386402606964111,
+      "step": 750
+    },
+    {
+      "epoch": 0.39868852459016396,
+      "grad_norm": 0.6447997093200684,
+      "learning_rate": 0.00012678078409718389,
+      "loss": 0.656829833984375,
+      "step": 760
+    },
+    {
+      "epoch": 0.4039344262295082,
+      "grad_norm": 0.5744156837463379,
+      "learning_rate": 0.00012567642186637218,
+      "loss": 0.6654098510742188,
+      "step": 770
+    },
+    {
+      "epoch": 0.40918032786885244,
+      "grad_norm": 0.5341398119926453,
+      "learning_rate": 0.00012457205963556047,
+      "loss": 0.6406219005584717,
+      "step": 780
+    },
+    {
+      "epoch": 0.41442622950819674,
+      "grad_norm": 0.600540280342102,
+      "learning_rate": 0.00012346769740474877,
+      "loss": 0.659253454208374,
+      "step": 790
+    },
+    {
+      "epoch": 0.419672131147541,
+      "grad_norm": 0.7170221209526062,
+      "learning_rate": 0.00012236333517393706,
+      "loss": 0.6802017211914062,
+      "step": 800
+    },
+    {
+      "epoch": 0.4249180327868852,
+      "grad_norm": 0.7966761589050293,
+      "learning_rate": 0.00012125897294312535,
+      "loss": 0.6104480743408203,
+      "step": 810
+    },
+    {
+      "epoch": 0.4301639344262295,
+      "grad_norm": 0.671951413154602,
+      "learning_rate": 0.00012015461071231365,
+      "loss": 0.7058865070343018,
+      "step": 820
+    },
+    {
+      "epoch": 0.43540983606557376,
+      "grad_norm": 0.6206080913543701,
+      "learning_rate": 0.00011905024848150194,
+      "loss": 0.6379797458648682,
+      "step": 830
+    },
+    {
+      "epoch": 0.44065573770491806,
+      "grad_norm": 0.6439060568809509,
+      "learning_rate": 0.00011794588625069024,
+      "loss": 0.6559050559997559,
+      "step": 840
+    },
+    {
+      "epoch": 0.4459016393442623,
+      "grad_norm": 0.7650911808013916,
+      "learning_rate": 0.00011684152401987853,
+      "loss": 0.664661169052124,
+      "step": 850
+    },
+    {
+      "epoch": 0.45114754098360654,
+      "grad_norm": 0.6379468441009521,
+      "learning_rate": 0.00011573716178906681,
+      "loss": 0.6635408878326416,
+      "step": 860
+    },
+    {
+      "epoch": 0.45639344262295084,
+      "grad_norm": 0.6033166646957397,
+      "learning_rate": 0.00011463279955825512,
+      "loss": 0.6439225673675537,
+      "step": 870
+    },
+    {
+      "epoch": 0.4616393442622951,
+      "grad_norm": 0.6554288268089294,
+      "learning_rate": 0.0001135284373274434,
+      "loss": 0.6234912872314453,
+      "step": 880
+    },
+    {
+      "epoch": 0.4668852459016393,
+      "grad_norm": 0.7938706278800964,
+      "learning_rate": 0.0001124240750966317,
+      "loss": 0.6458295822143555,
+      "step": 890
+    },
+    {
+      "epoch": 0.4721311475409836,
+      "grad_norm": 0.7794424891471863,
+      "learning_rate": 0.00011131971286581999,
+      "loss": 0.6645576000213623,
+      "step": 900
+    },
+    {
+      "epoch": 0.47737704918032786,
+      "grad_norm": 0.6669194102287292,
+      "learning_rate": 0.0001102153506350083,
+      "loss": 0.706819725036621,
+      "step": 910
+    },
+    {
+      "epoch": 0.48262295081967216,
+      "grad_norm": 0.5930067896842957,
+      "learning_rate": 0.00010911098840419657,
+      "loss": 0.6377612113952636,
+      "step": 920
+    },
+    {
+      "epoch": 0.4878688524590164,
+      "grad_norm": 0.5960756540298462,
+      "learning_rate": 0.00010800662617338488,
+      "loss": 0.6585844993591309,
+      "step": 930
+    },
+    {
+      "epoch": 0.49311475409836064,
+      "grad_norm": 0.8185632228851318,
+      "learning_rate": 0.00010690226394257316,
+      "loss": 0.6509750366210938,
+      "step": 940
+    },
+    {
+      "epoch": 0.49836065573770494,
+      "grad_norm": 0.5078699588775635,
+      "learning_rate": 0.00010579790171176147,
+      "loss": 0.6630078315734863,
+      "step": 950
+    },
+    {
+      "epoch": 0.5036065573770492,
+      "grad_norm": 0.5847029685974121,
+      "learning_rate": 0.00010469353948094975,
+      "loss": 0.6561220169067383,
+      "step": 960
+    },
+    {
+      "epoch": 0.5088524590163934,
+      "grad_norm": 0.5837432146072388,
+      "learning_rate": 0.00010358917725013806,
+      "loss": 0.6355574607849122,
+      "step": 970
+    },
+    {
+      "epoch": 0.5140983606557377,
+      "grad_norm": 0.5932501554489136,
+      "learning_rate": 0.00010248481501932634,
+      "loss": 0.6037593364715577,
+      "step": 980
+    },
+    {
+      "epoch": 0.519344262295082,
+      "grad_norm": 0.6490769982337952,
+      "learning_rate": 0.00010138045278851464,
+      "loss": 0.7359431266784668,
+      "step": 990
+    },
+    {
+      "epoch": 0.5245901639344263,
+      "grad_norm": 0.8101118206977844,
+      "learning_rate": 0.00010027609055770292,
+      "loss": 0.5702367305755616,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5245901639344263,
+      "eval_loss": 0.6413107514381409,
+      "eval_runtime": 327.3739,
+      "eval_samples_per_second": 34.459,
+      "eval_steps_per_second": 8.617,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1907,
+  "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": 5.744543485750426e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

gemma-3-1b-it/checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b3a08e619bad0c9a42d9829faf0d62ab7a15fd439c24fe4c5bd9c4bdb262129
+size 5265

gemma-3-1b-it/tb/events.out.tfevents.1789955877.fed349279e2c.8616.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6184338b72b61e2dd1c17a71df27b2bd3d53f7d5ebbf46e4dc322163b9428129
-size 16703
+oid sha256:fe448eb36a810396fcf12b7a7ea061bc32177d477dd1b574539b5d90f0c6d27a
+size 27790

gemma-3-1b-it/test_eval/metrics.json

@@ -1,6 +1,6 @@
 {
-  "wer": 1.1390086753589366,
+  "wer": 1.068743341281518,
   "exact_match": 0.0,
-  "hallucination_rate": 0.28125,
+  "hallucination_rate": 0.2734375,
   "n_examples": 128
 }