Add final balanced 0.1 epoch checkpoint with resume state

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,206 @@
+---
+base_model: google/t5gemma-2-4b-4b
+library_name: peft
+tags:
+- base_model:adapter:google/t5gemma-2-4b-4b
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.20.0

adapter_config.json

@@ -0,0 +1,53 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/t5gemma-2-4b-4b",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 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": "0.20.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "fc1",
+    "fc2",
+    "self_attn.out_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "SEQ_2_SEQ_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac53bdc65d392bbcb46a2de3678eadc04fd98246538c9de63d6eaa3aa927e17b
+size 546596416

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:474e131855868c59cf9db6a6a8366da3482729dc99a6bf172ee0d3e4f9cf7b4c
+size 954500299

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04057f6594d8eee7900f9e376353e3b13e2398d1b22f940d5d512e58979232db
+size 15429

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76de3d100535a7b9e296d3b41c84e956c087211b0282d3dc0588544246db65bb
+size 15429

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf72aa9be6982d680d7215394fe5a81b7fa316e5f76b855e63d86c9eb52bfb6d
+size 15429

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7c80d0296f2414f6806f640444ee16c87ad585edb508b315765c9fec043ce60
+size 15429

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f9d740f6ed12e07aff83ead7b812970b205c9bd60bd7af93eb3503747e6ceba
+size 1465

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f22dee48d75e17109810fa1ecbf2321c4c1c16caf9177fb269222a6a4e056379
+size 33384485

tokenizer_config.json

@@ -0,0 +1,27 @@
+{
+  "backend": "tokenizers",
+  "boi_token": "<start_of_image>",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eoi_token": "<end_of_image>",
+  "eos_token": "<eos>",
+  "extra_special_tokens": [],
+  "image_token": "<image_soft_token>",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "boi_token": "<start_of_image>",
+    "eoi_token": "<end_of_image>",
+    "image_token": "<image_soft_token>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "processor_class": "Gemma3Processor",
+  "sp_model_kwargs": null,
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,744 @@
+{
+  "best_global_step": 1000,
+  "best_metric": 0.18616674840450287,
+  "best_model_checkpoint": "/workspace/t5gemma_continuation/runs/t5gemma-2-4b-netjets-balanced-0p1/checkpoint-1000",
+  "epoch": 0.10003237293622531,
+  "eval_steps": 1000,
+  "global_step": 2472,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0010116542570411137,
+      "grad_norm": 0.7588071823120117,
+      "learning_rate": 9.997674418116759e-06,
+      "loss": 0.09478737831115723,
+      "step": 25
+    },
+    {
+      "epoch": 0.0020233085140822274,
+      "grad_norm": 0.7066558003425598,
+      "learning_rate": 9.990308418965396e-06,
+      "loss": 0.08540201187133789,
+      "step": 50
+    },
+    {
+      "epoch": 0.003034962771123341,
+      "grad_norm": 0.9437556862831116,
+      "learning_rate": 9.977905399713323e-06,
+      "loss": 0.08831601142883301,
+      "step": 75
+    },
+    {
+      "epoch": 0.004046617028164455,
+      "grad_norm": 0.6379377245903015,
+      "learning_rate": 9.96047787947801e-06,
+      "loss": 0.08719367980957031,
+      "step": 100
+    },
+    {
+      "epoch": 0.005058271285205568,
+      "grad_norm": 0.7673565745353699,
+      "learning_rate": 9.938043448909642e-06,
+      "loss": 0.08562824249267578,
+      "step": 125
+    },
+    {
+      "epoch": 0.006069925542246682,
+      "grad_norm": 0.8915950655937195,
+      "learning_rate": 9.910624752435825e-06,
+      "loss": 0.08884576797485351,
+      "step": 150
+    },
+    {
+      "epoch": 0.007081579799287795,
+      "grad_norm": 0.9796419739723206,
+      "learning_rate": 9.87824946540519e-06,
+      "loss": 0.0844249153137207,
+      "step": 175
+    },
+    {
+      "epoch": 0.00809323405632891,
+      "grad_norm": 0.7828882932662964,
+      "learning_rate": 9.840950266152993e-06,
+      "loss": 0.08762908935546875,
+      "step": 200
+    },
+    {
+      "epoch": 0.009104888313370023,
+      "grad_norm": 0.8314036130905151,
+      "learning_rate": 9.798764803016892e-06,
+      "loss": 0.08477160453796387,
+      "step": 225
+    },
+    {
+      "epoch": 0.010116542570411136,
+      "grad_norm": 0.9383084177970886,
+      "learning_rate": 9.7517356563362e-06,
+      "loss": 0.0796052074432373,
+      "step": 250
+    },
+    {
+      "epoch": 0.01112819682745225,
+      "grad_norm": 0.6904627680778503,
+      "learning_rate": 9.699910295472986e-06,
+      "loss": 0.08183086395263672,
+      "step": 275
+    },
+    {
+      "epoch": 0.012139851084493364,
+      "grad_norm": 0.7161296010017395,
+      "learning_rate": 9.643341030898358e-06,
+      "loss": 0.08600561141967773,
+      "step": 300
+    },
+    {
+      "epoch": 0.013151505341534477,
+      "grad_norm": 0.7295992374420166,
+      "learning_rate": 9.582084961392358e-06,
+      "loss": 0.08031168937683106,
+      "step": 325
+    },
+    {
+      "epoch": 0.01416315959857559,
+      "grad_norm": 0.8786855340003967,
+      "learning_rate": 9.516203916410702e-06,
+      "loss": 0.07677621841430664,
+      "step": 350
+    },
+    {
+      "epoch": 0.015174813855616705,
+      "grad_norm": 0.664604127407074,
+      "learning_rate": 9.445764393676567e-06,
+      "loss": 0.08257333755493164,
+      "step": 375
+    },
+    {
+      "epoch": 0.01618646811265782,
+      "grad_norm": 0.6612857580184937,
+      "learning_rate": 9.370837492060428e-06,
+      "loss": 0.07814112663269043,
+      "step": 400
+    },
+    {
+      "epoch": 0.01719812236969893,
+      "grad_norm": 0.6337666511535645,
+      "learning_rate": 9.291498839815658e-06,
+      "loss": 0.07912947177886963,
+      "step": 425
+    },
+    {
+      "epoch": 0.018209776626740046,
+      "grad_norm": 0.9065153002738953,
+      "learning_rate": 9.20782851824236e-06,
+      "loss": 0.08001086235046387,
+      "step": 450
+    },
+    {
+      "epoch": 0.01922143088378116,
+      "grad_norm": 0.8778851628303528,
+      "learning_rate": 9.119910980856477e-06,
+      "loss": 0.08504880905151367,
+      "step": 475
+    },
+    {
+      "epoch": 0.020233085140822272,
+      "grad_norm": 0.8410937786102295,
+      "learning_rate": 9.027834968145736e-06,
+      "loss": 0.07751385688781738,
+      "step": 500
+    },
+    {
+      "epoch": 0.021244739397863387,
+      "grad_norm": 0.8290925025939941,
+      "learning_rate": 8.931693417998515e-06,
+      "loss": 0.08087217330932617,
+      "step": 525
+    },
+    {
+      "epoch": 0.0222563936549045,
+      "grad_norm": 0.9300380349159241,
+      "learning_rate": 8.831583371896011e-06,
+      "loss": 0.07645512580871582,
+      "step": 550
+    },
+    {
+      "epoch": 0.023268047911945613,
+      "grad_norm": 1.0256469249725342,
+      "learning_rate": 8.727605876962402e-06,
+      "loss": 0.07920522689819336,
+      "step": 575
+    },
+    {
+      "epoch": 0.024279702168986728,
+      "grad_norm": 0.7493225336074829,
+      "learning_rate": 8.619865883971879e-06,
+      "loss": 0.07890358448028564,
+      "step": 600
+    },
+    {
+      "epoch": 0.025291356426027842,
+      "grad_norm": 1.3388545513153076,
+      "learning_rate": 8.508472141415468e-06,
+      "loss": 0.0720207691192627,
+      "step": 625
+    },
+    {
+      "epoch": 0.026303010683068954,
+      "grad_norm": 0.8595075011253357,
+      "learning_rate": 8.393537085734616e-06,
+      "loss": 0.07741987228393554,
+      "step": 650
+    },
+    {
+      "epoch": 0.02731466494011007,
+      "grad_norm": 0.842380940914154,
+      "learning_rate": 8.275176727832289e-06,
+      "loss": 0.078358473777771,
+      "step": 675
+    },
+    {
+      "epoch": 0.02832631919715118,
+      "grad_norm": 0.6610252261161804,
+      "learning_rate": 8.153510535976138e-06,
+      "loss": 0.07246792793273926,
+      "step": 700
+    },
+    {
+      "epoch": 0.029337973454192295,
+      "grad_norm": 0.811519205570221,
+      "learning_rate": 8.028661315211968e-06,
+      "loss": 0.07699480533599853,
+      "step": 725
+    },
+    {
+      "epoch": 0.03034962771123341,
+      "grad_norm": 0.8042305111885071,
+      "learning_rate": 7.900755083409165e-06,
+      "loss": 0.07572071552276612,
+      "step": 750
+    },
+    {
+      "epoch": 0.03136128196827452,
+      "grad_norm": 1.0434718132019043,
+      "learning_rate": 7.769920944063244e-06,
+      "loss": 0.07450762748718262,
+      "step": 775
+    },
+    {
+      "epoch": 0.03237293622531564,
+      "grad_norm": 0.7678037285804749,
+      "learning_rate": 7.636290955983891e-06,
+      "loss": 0.07479867935180665,
+      "step": 800
+    },
+    {
+      "epoch": 0.03338459048235675,
+      "grad_norm": 0.7159585356712341,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.06815961360931397,
+      "step": 825
+    },
+    {
+      "epoch": 0.03439624473939786,
+      "grad_norm": 0.8384346961975098,
+      "learning_rate": 7.361185642816315e-06,
+      "loss": 0.07340707778930664,
+      "step": 850
+    },
+    {
+      "epoch": 0.03540789899643898,
+      "grad_norm": 0.8005127310752869,
+      "learning_rate": 7.219987998159018e-06,
+      "loss": 0.07145726203918457,
+      "step": 875
+    },
+    {
+      "epoch": 0.03641955325348009,
+      "grad_norm": 0.7431536316871643,
+      "learning_rate": 7.0765495853504875e-06,
+      "loss": 0.0730298662185669,
+      "step": 900
+    },
+    {
+      "epoch": 0.0374312075105212,
+      "grad_norm": 0.8528541922569275,
+      "learning_rate": 6.931015185455915e-06,
+      "loss": 0.07038732051849365,
+      "step": 925
+    },
+    {
+      "epoch": 0.03844286176756232,
+      "grad_norm": 1.045146107673645,
+      "learning_rate": 6.7835316951470185e-06,
+      "loss": 0.07059284210205079,
+      "step": 950
+    },
+    {
+      "epoch": 0.03945451602460343,
+      "grad_norm": 0.7227703928947449,
+      "learning_rate": 6.634247978430359e-06,
+      "loss": 0.06966906547546386,
+      "step": 975
+    },
+    {
+      "epoch": 0.040466170281644544,
+      "grad_norm": 0.8465985655784607,
+      "learning_rate": 6.483314716389888e-06,
+      "loss": 0.07425240516662597,
+      "step": 1000
+    },
+    {
+      "epoch": 0.040466170281644544,
+      "eval_loss": 0.18616674840450287,
+      "eval_runtime": 417.5341,
+      "eval_samples_per_second": 102.76,
+      "eval_steps_per_second": 3.212,
+      "step": 1000
+    },
+    {
+      "epoch": 0.04147782453868566,
+      "grad_norm": 0.9529474377632141,
+      "learning_rate": 6.330884255095409e-06,
+      "loss": 0.07227096557617188,
+      "step": 1025
+    },
+    {
+      "epoch": 0.04248947879572677,
+      "grad_norm": 0.8593569397926331,
+      "learning_rate": 6.1771104518304925e-06,
+      "loss": 0.06962797641754151,
+      "step": 1050
+    },
+    {
+      "epoch": 0.043501133052767885,
+      "grad_norm": 1.56771719455719,
+      "learning_rate": 6.0221485197949995e-06,
+      "loss": 0.0692414665222168,
+      "step": 1075
+    },
+    {
+      "epoch": 0.044512787309809,
+      "grad_norm": 0.9446329474449158,
+      "learning_rate": 5.866154871439018e-06,
+      "loss": 0.07052364349365234,
+      "step": 1100
+    },
+    {
+      "epoch": 0.045524441566850114,
+      "grad_norm": 0.9508762359619141,
+      "learning_rate": 5.709286960586318e-06,
+      "loss": 0.06672035217285156,
+      "step": 1125
+    },
+    {
+      "epoch": 0.046536095823891226,
+      "grad_norm": 0.9291703701019287,
+      "learning_rate": 5.551703123506678e-06,
+      "loss": 0.07133745193481446,
+      "step": 1150
+    },
+    {
+      "epoch": 0.047547750080932344,
+      "grad_norm": 1.0664215087890625,
+      "learning_rate": 5.393562419097525e-06,
+      "loss": 0.07111708641052246,
+      "step": 1175
+    },
+    {
+      "epoch": 0.048559404337973455,
+      "grad_norm": 0.9802451729774475,
+      "learning_rate": 5.235024468336154e-06,
+      "loss": 0.06713025569915772,
+      "step": 1200
+    },
+    {
+      "epoch": 0.04957105859501457,
+      "grad_norm": 0.9398006200790405,
+      "learning_rate": 5.07624929316463e-06,
+      "loss": 0.06843162536621093,
+      "step": 1225
+    },
+    {
+      "epoch": 0.050582712852055685,
+      "grad_norm": 0.8841513991355896,
+      "learning_rate": 4.917397154969965e-06,
+      "loss": 0.0674632453918457,
+      "step": 1250
+    },
+    {
+      "epoch": 0.051594367109096796,
+      "grad_norm": 0.9453590512275696,
+      "learning_rate": 4.758628392822602e-06,
+      "loss": 0.06608812808990479,
+      "step": 1275
+    },
+    {
+      "epoch": 0.05260602136613791,
+      "grad_norm": 1.0145738124847412,
+      "learning_rate": 4.600103261636496e-06,
+      "loss": 0.0655123233795166,
+      "step": 1300
+    },
+    {
+      "epoch": 0.053617675623179026,
+      "grad_norm": 0.8218289613723755,
+      "learning_rate": 4.441981770414145e-06,
+      "loss": 0.06619914054870606,
+      "step": 1325
+    },
+    {
+      "epoch": 0.05462932988022014,
+      "grad_norm": 0.9566552042961121,
+      "learning_rate": 4.284423520739811e-06,
+      "loss": 0.06477892875671387,
+      "step": 1350
+    },
+    {
+      "epoch": 0.05564098413726125,
+      "grad_norm": 0.8886809945106506,
+      "learning_rate": 4.127587545684002e-06,
+      "loss": 0.06271601676940917,
+      "step": 1375
+    },
+    {
+      "epoch": 0.05665263839430236,
+      "grad_norm": 0.9757625460624695,
+      "learning_rate": 3.971632149281768e-06,
+      "loss": 0.0660263204574585,
+      "step": 1400
+    },
+    {
+      "epoch": 0.05766429265134348,
+      "grad_norm": 0.9931125044822693,
+      "learning_rate": 3.8167147467468655e-06,
+      "loss": 0.06467216968536377,
+      "step": 1425
+    },
+    {
+      "epoch": 0.05867594690838459,
+      "grad_norm": 0.7876198887825012,
+      "learning_rate": 3.6629917055830685e-06,
+      "loss": 0.06067314147949219,
+      "step": 1450
+    },
+    {
+      "epoch": 0.0596876011654257,
+      "grad_norm": 0.8658786416053772,
+      "learning_rate": 3.51061818775298e-06,
+      "loss": 0.06845765113830567,
+      "step": 1475
+    },
+    {
+      "epoch": 0.06069925542246682,
+      "grad_norm": 0.8782923817634583,
+      "learning_rate": 3.359747993063682e-06,
+      "loss": 0.06363529682159424,
+      "step": 1500
+    },
+    {
+      "epoch": 0.06171090967950793,
+      "grad_norm": 0.8501570820808411,
+      "learning_rate": 3.2105334039272924e-06,
+      "loss": 0.06508552074432374,
+      "step": 1525
+    },
+    {
+      "epoch": 0.06272256393654904,
+      "grad_norm": 0.9424809217453003,
+      "learning_rate": 3.06312503165311e-06,
+      "loss": 0.06868315219879151,
+      "step": 1550
+    },
+    {
+      "epoch": 0.06373421819359015,
+      "grad_norm": 0.8879184722900391,
+      "learning_rate": 2.9176716644265228e-06,
+      "loss": 0.06361775398254395,
+      "step": 1575
+    },
+    {
+      "epoch": 0.06474587245063128,
+      "grad_norm": 0.8703402280807495,
+      "learning_rate": 2.7743201171280776e-06,
+      "loss": 0.06295756340026855,
+      "step": 1600
+    },
+    {
+      "epoch": 0.06575752670767239,
+      "grad_norm": 0.8063569068908691,
+      "learning_rate": 2.6332150831443524e-06,
+      "loss": 0.06665169715881347,
+      "step": 1625
+    },
+    {
+      "epoch": 0.0667691809647135,
+      "grad_norm": 0.899817943572998,
+      "learning_rate": 2.494498988320166e-06,
+      "loss": 0.06509072303771973,
+      "step": 1650
+    },
+    {
+      "epoch": 0.06778083522175461,
+      "grad_norm": 0.7589254975318909,
+      "learning_rate": 2.358311847199567e-06,
+      "loss": 0.06155346870422363,
+      "step": 1675
+    },
+    {
+      "epoch": 0.06879248947879572,
+      "grad_norm": 0.9403272867202759,
+      "learning_rate": 2.224791121700673e-06,
+      "loss": 0.06310113906860351,
+      "step": 1700
+    },
+    {
+      "epoch": 0.06980414373583683,
+      "grad_norm": 0.9749501347541809,
+      "learning_rate": 2.094071582367053e-06,
+      "loss": 0.05723265171051026,
+      "step": 1725
+    },
+    {
+      "epoch": 0.07081579799287796,
+      "grad_norm": 1.0470415353775024,
+      "learning_rate": 1.9662851723356628e-06,
+      "loss": 0.0638632583618164,
+      "step": 1750
+    },
+    {
+      "epoch": 0.07182745224991907,
+      "grad_norm": 0.9093928337097168,
+      "learning_rate": 1.8415608741586595e-06,
+      "loss": 0.059368858337402346,
+      "step": 1775
+    },
+    {
+      "epoch": 0.07283910650696018,
+      "grad_norm": 1.184372901916504,
+      "learning_rate": 1.7200245796135085e-06,
+      "loss": 0.0635831117630005,
+      "step": 1800
+    },
+    {
+      "epoch": 0.0738507607640013,
+      "grad_norm": 0.9792858362197876,
+      "learning_rate": 1.601798962632799e-06,
+      "loss": 0.06337547302246094,
+      "step": 1825
+    },
+    {
+      "epoch": 0.0748624150210424,
+      "grad_norm": 0.8788456320762634,
+      "learning_rate": 1.4870033554820256e-06,
+      "loss": 0.05948060989379883,
+      "step": 1850
+    },
+    {
+      "epoch": 0.07587406927808352,
+      "grad_norm": 1.129376769065857,
+      "learning_rate": 1.3757536283103145e-06,
+      "loss": 0.06096158981323242,
+      "step": 1875
+    },
+    {
+      "epoch": 0.07688572353512464,
+      "grad_norm": 1.0180684328079224,
+      "learning_rate": 1.2681620721956727e-06,
+      "loss": 0.06047186851501465,
+      "step": 1900
+    },
+    {
+      "epoch": 0.07789737779216575,
+      "grad_norm": 0.7889450788497925,
+      "learning_rate": 1.1643372858028185e-06,
+      "loss": 0.06576673984527588,
+      "step": 1925
+    },
+    {
+      "epoch": 0.07890903204920686,
+      "grad_norm": 0.9547349810600281,
+      "learning_rate": 1.0643840657679716e-06,
+      "loss": 0.06420350551605225,
+      "step": 1950
+    },
+    {
+      "epoch": 0.07992068630624798,
+      "grad_norm": 1.0346224308013916,
+      "learning_rate": 9.684033009212752e-07,
+      "loss": 0.06534246444702148,
+      "step": 1975
+    },
+    {
+      "epoch": 0.08093234056328909,
+      "grad_norm": 0.962091326713562,
+      "learning_rate": 8.764918704535979e-07,
+      "loss": 0.06413849830627441,
+      "step": 2000
+    },
+    {
+      "epoch": 0.08093234056328909,
+      "eval_loss": 0.2071998119354248,
+      "eval_runtime": 416.5888,
+      "eval_samples_per_second": 102.994,
+      "eval_steps_per_second": 3.219,
+      "step": 2000
+    },
+    {
+      "epoch": 0.0819439948203302,
+      "grad_norm": 0.8268165588378906,
+      "learning_rate": 7.887425461305059e-07,
+      "loss": 0.05936159610748291,
+      "step": 2025
+    },
+    {
+      "epoch": 0.08295564907737132,
+      "grad_norm": 0.8211469650268555,
+      "learning_rate": 7.052438986521121e-07,
+      "loss": 0.06574771881103515,
+      "step": 2050
+    },
+    {
+      "epoch": 0.08396730333441244,
+      "grad_norm": 0.9656228423118591,
+      "learning_rate": 6.260802082533074e-07,
+      "loss": 0.05933941841125488,
+      "step": 2075
+    },
+    {
+      "epoch": 0.08497895759145355,
+      "grad_norm": 1.1002612113952637,
+      "learning_rate": 5.513313796346242e-07,
+      "loss": 0.05868081092834473,
+      "step": 2100
+    },
+    {
+      "epoch": 0.08599061184849466,
+      "grad_norm": 0.9568577408790588,
+      "learning_rate": 4.81072861309591e-07,
+      "loss": 0.061365365982055664,
+      "step": 2125
+    },
+    {
+      "epoch": 0.08700226610553577,
+      "grad_norm": 1.263872504234314,
+      "learning_rate": 4.1537556944998225e-07,
+      "loss": 0.05863400459289551,
+      "step": 2150
+    },
+    {
+      "epoch": 0.08801392036257688,
+      "grad_norm": 0.949004590511322,
+      "learning_rate": 3.5430581630583884e-07,
+      "loss": 0.05913155555725098,
+      "step": 2175
+    },
+    {
+      "epoch": 0.089025574619618,
+      "grad_norm": 1.2876442670822144,
+      "learning_rate": 2.979252432725027e-07,
+      "loss": 0.057411818504333495,
+      "step": 2200
+    },
+    {
+      "epoch": 0.09003722887665912,
+      "grad_norm": 1.0092101097106934,
+      "learning_rate": 2.462907586722285e-07,
+      "loss": 0.0581765079498291,
+      "step": 2225
+    },
+    {
+      "epoch": 0.09104888313370023,
+      "grad_norm": 0.8489072322845459,
+      "learning_rate": 1.994544803131737e-07,
+      "loss": 0.05828178882598877,
+      "step": 2250
+    },
+    {
+      "epoch": 0.09206053739074134,
+      "grad_norm": 0.8021871447563171,
+      "learning_rate": 1.574636828837395e-07,
+      "loss": 0.06090761184692383,
+      "step": 2275
+    },
+    {
+      "epoch": 0.09307219164778245,
+      "grad_norm": 1.2686115503311157,
+      "learning_rate": 1.2036075023537208e-07,
+      "loss": 0.061113595962524414,
+      "step": 2300
+    },
+    {
+      "epoch": 0.09408384590482356,
+      "grad_norm": 0.9067429304122925,
+      "learning_rate": 8.818313260197553e-08,
+      "loss": 0.060579957962036135,
+      "step": 2325
+    },
+    {
+      "epoch": 0.09509550016186469,
+      "grad_norm": 0.9274111390113831,
+      "learning_rate": 6.096330879912682e-08,
+      "loss": 0.0602969217300415,
+      "step": 2350
+    },
+    {
+      "epoch": 0.0961071544189058,
+      "grad_norm": 0.958638608455658,
+      "learning_rate": 3.872875344124283e-08,
+      "loss": 0.06123236656188965,
+      "step": 2375
+    },
+    {
+      "epoch": 0.09711880867594691,
+      "grad_norm": 0.9400763511657715,
+      "learning_rate": 2.1501909209790672e-08,
+      "loss": 0.05601327896118164,
+      "step": 2400
+    },
+    {
+      "epoch": 0.09813046293298802,
+      "grad_norm": 0.8256824016571045,
+      "learning_rate": 9.300164200530815e-09,
+      "loss": 0.058267130851745605,
+      "step": 2425
+    },
+    {
+      "epoch": 0.09914211719002913,
+      "grad_norm": 0.8892621397972107,
+      "learning_rate": 2.1358343726618493e-09,
+      "loss": 0.05662036895751953,
+      "step": 2450
+    },
+    {
+      "epoch": 0.10003237293622531,
+      "eval_loss": 0.21075651049613953,
+      "eval_runtime": 417.5077,
+      "eval_samples_per_second": 102.767,
+      "eval_steps_per_second": 3.212,
+      "step": 2472
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 2472,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.891199665862083e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ec6d52b83b8e0d6240836e5a7c12b9ba34ff19a144db80d31bf512ff145358c
+size 5265