End of training

README.md

@@ -0,0 +1,84 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+model-index:
+- name: mt5-gigatrue-tpb
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# mt5-gigatrue-tpb
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 19.8924
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0003
+- train_batch_size: 128
+- eval_batch_size: 128
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss |
+|:-------------:|:------:|:-----:|:---------------:|
+| 46.6558       | 0.1015 | 3000  | 21.7202         |
+| 32.5002       | 0.2030 | 6000  | 21.1662         |
+| 31.6686       | 0.3044 | 9000  | 20.6858         |
+| 31.3231       | 0.4059 | 12000 | 20.5872         |
+| 31.1165       | 0.5074 | 15000 | 20.3965         |
+| 31.0253       | 0.6089 | 18000 | 20.2668         |
+| 30.9446       | 0.7104 | 21000 | 20.1311         |
+| 30.9031       | 0.8119 | 24000 | 20.0952         |
+| 30.8587       | 0.9133 | 27000 | 20.0290         |
+| 30.8229       | 1.0148 | 30000 | 20.1145         |
+| 30.821        | 1.1163 | 33000 | 19.9165         |
+| 30.7911       | 1.2178 | 36000 | 19.8157         |
+| 30.784        | 1.3193 | 39000 | 19.9888         |
+| 30.7765       | 1.4207 | 42000 | 19.9128         |
+| 30.774        | 1.5222 | 45000 | 19.8938         |
+| 30.7461       | 1.6237 | 48000 | 19.7771         |
+| 30.7454       | 1.7252 | 51000 | 19.9231         |
+| 30.724        | 1.8267 | 54000 | 19.7420         |
+| 30.731        | 1.9282 | 57000 | 19.8704         |
+| 30.7417       | 2.0296 | 60000 | 19.9472         |
+| 30.7423       | 2.1311 | 63000 | 19.9312         |
+| 30.7266       | 2.2326 | 66000 | 19.9009         |
+| 30.7288       | 2.3341 | 69000 | 19.9468         |
+| 30.7245       | 2.4356 | 72000 | 19.8720         |
+| 30.7434       | 2.5370 | 75000 | 19.9333         |
+| 30.731        | 2.6385 | 78000 | 19.8618         |
+| 30.7104       | 2.7400 | 81000 | 19.8979         |
+| 30.7213       | 2.8415 | 84000 | 19.8811         |
+| 30.7303       | 2.9430 | 87000 | 19.8924         |
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.5.1
+- Datasets 3.2.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "../txprun/pruned_models/mt5-gigatrue-tpb-base",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 1024,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "mt5",
+  "num_decoder_layers": 8,
+  "num_heads": 6,
+  "num_layers": 8,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": true,
+  "vocab_size": 74584
+}

coreconfig.json

@@ -0,0 +1,26 @@
+{
+  "out_name": "mt5-gigatrue-tpb",
+  "remove_layers": false,
+  "model_archetype": "mt5",
+  "model_name": "../txprun/pruned_models/mt5-gigatrue-tpb-base",
+  "tokenizer_name": "../txprun/pruned_models/mt5-gigatrue-tpb-base",
+  "model_torch_dtype": "bfloat16",
+  "dataset_lang": "en",
+  "dataset_name": "Plasmoxy/gigatrue",
+  "dataset_tokenized_cache_name": "gigatrue_tokenized_mt5_tpb_110-35",
+  "use_half_val_dataset": true,
+  "max_input_length": 110,
+  "max_target_length": 35,
+  "batch_size": 128,
+  "learning_rate": 0.0003,
+  "num_train_epochs": 3,
+  "pkg_versions": {
+    "optimum": "1.23.3",
+    "transformers": "4.45.2",
+    "openvino": "2024.6.0",
+    "nncf": "2.14.1",
+    "torch": "2.5.1",
+    "datasets": "3.2.0",
+    "peft": "0.13.3.dev0"
+  }
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.45.2"
+}

logs/events.out.tfevents.1744673255.gna4000.937530.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:369f3d13fb4a9b36c3310a347c4656f38e91d105a967cd4648bfab71b7888b8b
+size 5283

logs/events.out.tfevents.1744673410.gna4000.937747.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7ac27124d2a3bad4dfc41c55e92f3a213f00d5b3ef3cdf498a65639f12eb2f7
+size 5490

logs/events.out.tfevents.1744673763.gna4000.938624.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e82b8e26d6a1771b4057262047d4f9a7e65fc638b443d8365a77c1b59ab71270
+size 20044

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1255da2ca3766e547e120aac4a547683fcfeb2938252760d4aa58600877fc54
+size 240894640

nvidia_smi_early.log

@@ -0,0 +1,22 @@
+Tue Apr 15 01:36:33 2025       
++-----------------------------------------------------------------------------------------+
+| NVIDIA-SMI 550.144.03             Driver Version: 550.144.03     CUDA Version: 12.4     |
+|-----------------------------------------+------------------------+----------------------+
+| GPU  Name                 Persistence-M | Bus-Id          Disp.A | Volatile Uncorr. ECC |
+| Fan  Temp   Perf          Pwr:Usage/Cap |           Memory-Usage | GPU-Util  Compute M. |
+|                                         |                        |               MIG M. |
+|=========================================+========================+======================|
+|   0  NVIDIA RTX A4000               Off |   00000000:01:00.0 Off |                  Off |
+| 54%   77C    P2            138W /  140W |   10967MiB /  16376MiB |    100%      Default |
+|                                         |                        |                  N/A |
++-----------------------------------------+------------------------+----------------------+
+                                                                                         
++-----------------------------------------------------------------------------------------+
+| Processes:                                                                              |
+|  GPU   GI   CI        PID   Type   Process name                              GPU Memory |
+|        ID   ID                                                               Usage      |
+|=========================================================================================|
+|    0   N/A  N/A      1927      G   /usr/lib/xorg/Xorg                              4MiB |
+|    0   N/A  N/A    936168      C   ...ik/miniforge3/envs/alpha/bin/python       1620MiB |
+|    0   N/A  N/A    938624      C   ...ik/miniforge3/envs/alpha/bin/python       9330MiB |
++-----------------------------------------------------------------------------------------+

trainer_state.json

@@ -0,0 +1,484 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 3000,
+  "global_step": 88686,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.382721060821325e-05,
+      "grad_norm": 1216.0,
+      "learning_rate": 0.00029999661727893914,
+      "loss": 684.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.10148163182463973,
+      "grad_norm": 26.75,
+      "learning_rate": 0.000289851836817536,
+      "loss": 46.6558,
+      "step": 3000
+    },
+    {
+      "epoch": 0.10148163182463973,
+      "eval_loss": 21.720190048217773,
+      "eval_runtime": 69.6955,
+      "eval_samples_per_second": 1354.534,
+      "eval_steps_per_second": 10.589,
+      "step": 3000
+    },
+    {
+      "epoch": 0.20296326364927947,
+      "grad_norm": 22.875,
+      "learning_rate": 0.000279703673635072,
+      "loss": 32.5002,
+      "step": 6000
+    },
+    {
+      "epoch": 0.20296326364927947,
+      "eval_loss": 21.16615867614746,
+      "eval_runtime": 69.7326,
+      "eval_samples_per_second": 1353.815,
+      "eval_steps_per_second": 10.583,
+      "step": 6000
+    },
+    {
+      "epoch": 0.30444489547391923,
+      "grad_norm": 25.5,
+      "learning_rate": 0.00026955551045260807,
+      "loss": 31.6686,
+      "step": 9000
+    },
+    {
+      "epoch": 0.30444489547391923,
+      "eval_loss": 20.685806274414062,
+      "eval_runtime": 69.6891,
+      "eval_samples_per_second": 1354.659,
+      "eval_steps_per_second": 10.59,
+      "step": 9000
+    },
+    {
+      "epoch": 0.40592652729855894,
+      "grad_norm": 23.25,
+      "learning_rate": 0.0002594073472701441,
+      "loss": 31.3231,
+      "step": 12000
+    },
+    {
+      "epoch": 0.40592652729855894,
+      "eval_loss": 20.587228775024414,
+      "eval_runtime": 69.7199,
+      "eval_samples_per_second": 1354.062,
+      "eval_steps_per_second": 10.585,
+      "step": 12000
+    },
+    {
+      "epoch": 0.5074081591231987,
+      "grad_norm": 22.75,
+      "learning_rate": 0.0002492591840876801,
+      "loss": 31.1165,
+      "step": 15000
+    },
+    {
+      "epoch": 0.5074081591231987,
+      "eval_loss": 20.39651107788086,
+      "eval_runtime": 69.6974,
+      "eval_samples_per_second": 1354.497,
+      "eval_steps_per_second": 10.589,
+      "step": 15000
+    },
+    {
+      "epoch": 0.6088897909478385,
+      "grad_norm": 20.125,
+      "learning_rate": 0.0002391110209052161,
+      "loss": 31.0253,
+      "step": 18000
+    },
+    {
+      "epoch": 0.6088897909478385,
+      "eval_loss": 20.266767501831055,
+      "eval_runtime": 69.7207,
+      "eval_samples_per_second": 1354.045,
+      "eval_steps_per_second": 10.585,
+      "step": 18000
+    },
+    {
+      "epoch": 0.7103714227724782,
+      "grad_norm": 22.875,
+      "learning_rate": 0.00022896285772275215,
+      "loss": 30.9446,
+      "step": 21000
+    },
+    {
+      "epoch": 0.7103714227724782,
+      "eval_loss": 20.1310977935791,
+      "eval_runtime": 69.7013,
+      "eval_samples_per_second": 1354.422,
+      "eval_steps_per_second": 10.588,
+      "step": 21000
+    },
+    {
+      "epoch": 0.8118530545971179,
+      "grad_norm": 23.75,
+      "learning_rate": 0.0002188146945402882,
+      "loss": 30.9031,
+      "step": 24000
+    },
+    {
+      "epoch": 0.8118530545971179,
+      "eval_loss": 20.095190048217773,
+      "eval_runtime": 69.7102,
+      "eval_samples_per_second": 1354.25,
+      "eval_steps_per_second": 10.587,
+      "step": 24000
+    },
+    {
+      "epoch": 0.9133346864217576,
+      "grad_norm": 20.875,
+      "learning_rate": 0.00020866653135782423,
+      "loss": 30.8587,
+      "step": 27000
+    },
+    {
+      "epoch": 0.9133346864217576,
+      "eval_loss": 20.028963088989258,
+      "eval_runtime": 69.6951,
+      "eval_samples_per_second": 1354.544,
+      "eval_steps_per_second": 10.589,
+      "step": 27000
+    },
+    {
+      "epoch": 1.0148163182463974,
+      "grad_norm": 27.875,
+      "learning_rate": 0.00019851836817536025,
+      "loss": 30.8229,
+      "step": 30000
+    },
+    {
+      "epoch": 1.0148163182463974,
+      "eval_loss": 20.114498138427734,
+      "eval_runtime": 69.6966,
+      "eval_samples_per_second": 1354.514,
+      "eval_steps_per_second": 10.589,
+      "step": 30000
+    },
+    {
+      "epoch": 1.116297950071037,
+      "grad_norm": 20.125,
+      "learning_rate": 0.0001883702049928963,
+      "loss": 30.821,
+      "step": 33000
+    },
+    {
+      "epoch": 1.116297950071037,
+      "eval_loss": 19.9164981842041,
+      "eval_runtime": 69.8254,
+      "eval_samples_per_second": 1352.015,
+      "eval_steps_per_second": 10.569,
+      "step": 33000
+    },
+    {
+      "epoch": 1.217779581895677,
+      "grad_norm": 30.25,
+      "learning_rate": 0.0001782220418104323,
+      "loss": 30.7911,
+      "step": 36000
+    },
+    {
+      "epoch": 1.217779581895677,
+      "eval_loss": 19.815717697143555,
+      "eval_runtime": 69.8336,
+      "eval_samples_per_second": 1351.856,
+      "eval_steps_per_second": 10.568,
+      "step": 36000
+    },
+    {
+      "epoch": 1.3192612137203166,
+      "grad_norm": 23.125,
+      "learning_rate": 0.00016807387862796832,
+      "loss": 30.784,
+      "step": 39000
+    },
+    {
+      "epoch": 1.3192612137203166,
+      "eval_loss": 19.988821029663086,
+      "eval_runtime": 69.8098,
+      "eval_samples_per_second": 1352.318,
+      "eval_steps_per_second": 10.572,
+      "step": 39000
+    },
+    {
+      "epoch": 1.4207428455449564,
+      "grad_norm": 22.875,
+      "learning_rate": 0.00015792571544550436,
+      "loss": 30.7765,
+      "step": 42000
+    },
+    {
+      "epoch": 1.4207428455449564,
+      "eval_loss": 19.912771224975586,
+      "eval_runtime": 69.8089,
+      "eval_samples_per_second": 1352.334,
+      "eval_steps_per_second": 10.572,
+      "step": 42000
+    },
+    {
+      "epoch": 1.522224477369596,
+      "grad_norm": 22.375,
+      "learning_rate": 0.00014777755226304037,
+      "loss": 30.774,
+      "step": 45000
+    },
+    {
+      "epoch": 1.522224477369596,
+      "eval_loss": 19.893800735473633,
+      "eval_runtime": 69.8327,
+      "eval_samples_per_second": 1351.873,
+      "eval_steps_per_second": 10.568,
+      "step": 45000
+    },
+    {
+      "epoch": 1.6237061091942357,
+      "grad_norm": 21.375,
+      "learning_rate": 0.0001376293890805764,
+      "loss": 30.7461,
+      "step": 48000
+    },
+    {
+      "epoch": 1.6237061091942357,
+      "eval_loss": 19.777099609375,
+      "eval_runtime": 69.8255,
+      "eval_samples_per_second": 1352.013,
+      "eval_steps_per_second": 10.569,
+      "step": 48000
+    },
+    {
+      "epoch": 1.7251877410188756,
+      "grad_norm": 19.5,
+      "learning_rate": 0.00012748122589811243,
+      "loss": 30.7454,
+      "step": 51000
+    },
+    {
+      "epoch": 1.7251877410188756,
+      "eval_loss": 19.92310333251953,
+      "eval_runtime": 69.8429,
+      "eval_samples_per_second": 1351.677,
+      "eval_steps_per_second": 10.567,
+      "step": 51000
+    },
+    {
+      "epoch": 1.8266693728435153,
+      "grad_norm": 27.375,
+      "learning_rate": 0.00011733306271564845,
+      "loss": 30.724,
+      "step": 54000
+    },
+    {
+      "epoch": 1.8266693728435153,
+      "eval_loss": 19.74203872680664,
+      "eval_runtime": 69.8312,
+      "eval_samples_per_second": 1351.903,
+      "eval_steps_per_second": 10.568,
+      "step": 54000
+    },
+    {
+      "epoch": 1.928151004668155,
+      "grad_norm": 21.0,
+      "learning_rate": 0.00010718489953318448,
+      "loss": 30.731,
+      "step": 57000
+    },
+    {
+      "epoch": 1.928151004668155,
+      "eval_loss": 19.870426177978516,
+      "eval_runtime": 69.839,
+      "eval_samples_per_second": 1351.753,
+      "eval_steps_per_second": 10.567,
+      "step": 57000
+    },
+    {
+      "epoch": 2.029632636492795,
+      "grad_norm": 23.375,
+      "learning_rate": 9.703673635072052e-05,
+      "loss": 30.7417,
+      "step": 60000
+    },
+    {
+      "epoch": 2.029632636492795,
+      "eval_loss": 19.947154998779297,
+      "eval_runtime": 69.8406,
+      "eval_samples_per_second": 1351.721,
+      "eval_steps_per_second": 10.567,
+      "step": 60000
+    },
+    {
+      "epoch": 2.1311142683174347,
+      "grad_norm": 20.375,
+      "learning_rate": 8.688857316825655e-05,
+      "loss": 30.7423,
+      "step": 63000
+    },
+    {
+      "epoch": 2.1311142683174347,
+      "eval_loss": 19.931232452392578,
+      "eval_runtime": 69.6923,
+      "eval_samples_per_second": 1354.597,
+      "eval_steps_per_second": 10.589,
+      "step": 63000
+    },
+    {
+      "epoch": 2.232595900142074,
+      "grad_norm": 23.25,
+      "learning_rate": 7.674040998579256e-05,
+      "loss": 30.7266,
+      "step": 66000
+    },
+    {
+      "epoch": 2.232595900142074,
+      "eval_loss": 19.900915145874023,
+      "eval_runtime": 69.6769,
+      "eval_samples_per_second": 1354.896,
+      "eval_steps_per_second": 10.592,
+      "step": 66000
+    },
+    {
+      "epoch": 2.334077531966714,
+      "grad_norm": 19.625,
+      "learning_rate": 6.659224680332859e-05,
+      "loss": 30.7288,
+      "step": 69000
+    },
+    {
+      "epoch": 2.334077531966714,
+      "eval_loss": 19.946815490722656,
+      "eval_runtime": 69.7005,
+      "eval_samples_per_second": 1354.439,
+      "eval_steps_per_second": 10.588,
+      "step": 69000
+    },
+    {
+      "epoch": 2.435559163791354,
+      "grad_norm": 19.5,
+      "learning_rate": 5.644408362086462e-05,
+      "loss": 30.7245,
+      "step": 72000
+    },
+    {
+      "epoch": 2.435559163791354,
+      "eval_loss": 19.871952056884766,
+      "eval_runtime": 69.6924,
+      "eval_samples_per_second": 1354.595,
+      "eval_steps_per_second": 10.589,
+      "step": 72000
+    },
+    {
+      "epoch": 2.5370407956159937,
+      "grad_norm": 24.875,
+      "learning_rate": 4.629592043840065e-05,
+      "loss": 30.7434,
+      "step": 75000
+    },
+    {
+      "epoch": 2.5370407956159937,
+      "eval_loss": 19.933265686035156,
+      "eval_runtime": 69.6748,
+      "eval_samples_per_second": 1354.937,
+      "eval_steps_per_second": 10.592,
+      "step": 75000
+    },
+    {
+      "epoch": 2.638522427440633,
+      "grad_norm": 20.625,
+      "learning_rate": 3.614775725593667e-05,
+      "loss": 30.731,
+      "step": 78000
+    },
+    {
+      "epoch": 2.638522427440633,
+      "eval_loss": 19.861787796020508,
+      "eval_runtime": 69.6852,
+      "eval_samples_per_second": 1354.735,
+      "eval_steps_per_second": 10.59,
+      "step": 78000
+    },
+    {
+      "epoch": 2.740004059265273,
+      "grad_norm": 22.375,
+      "learning_rate": 2.59995940734727e-05,
+      "loss": 30.7104,
+      "step": 81000
+    },
+    {
+      "epoch": 2.740004059265273,
+      "eval_loss": 19.897865295410156,
+      "eval_runtime": 69.685,
+      "eval_samples_per_second": 1354.74,
+      "eval_steps_per_second": 10.591,
+      "step": 81000
+    },
+    {
+      "epoch": 2.841485691089913,
+      "grad_norm": 19.875,
+      "learning_rate": 1.5851430891008727e-05,
+      "loss": 30.7213,
+      "step": 84000
+    },
+    {
+      "epoch": 2.841485691089913,
+      "eval_loss": 19.8810977935791,
+      "eval_runtime": 69.6701,
+      "eval_samples_per_second": 1355.029,
+      "eval_steps_per_second": 10.593,
+      "step": 84000
+    },
+    {
+      "epoch": 2.9429673229145523,
+      "grad_norm": 19.875,
+      "learning_rate": 5.703267708544753e-06,
+      "loss": 30.7303,
+      "step": 87000
+    },
+    {
+      "epoch": 2.9429673229145523,
+      "eval_loss": 19.892446517944336,
+      "eval_runtime": 69.6841,
+      "eval_samples_per_second": 1354.757,
+      "eval_steps_per_second": 10.591,
+      "step": 87000
+    },
+    {
+      "epoch": 3.0,
+      "step": 88686,
+      "total_flos": 6.274081768106557e+17,
+      "train_loss": 31.441612825023114,
+      "train_runtime": 27391.1958,
+      "train_samples_per_second": 414.42,
+      "train_steps_per_second": 3.238
+    }
+  ],
+  "logging_steps": 3000,
+  "max_steps": 88686,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 3000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.274081768106557e+17,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4c72bd84e69ebe375cd5a2dbba4749c5e954f38c5d60cb25ace03b795a6d6a6
+size 5304

training_args.json

@@ -0,0 +1,147 @@
+{
+  "output_dir": "out_models/mt5-gigatrue-tpb",
+  "overwrite_output_dir": false,
+  "do_train": false,
+  "do_eval": true,
+  "do_predict": false,
+  "eval_strategy": "steps",
+  "prediction_loss_only": false,
+  "per_device_train_batch_size": 128,
+  "per_device_eval_batch_size": 128,
+  "per_gpu_train_batch_size": null,
+  "per_gpu_eval_batch_size": null,
+  "gradient_accumulation_steps": 1,
+  "eval_accumulation_steps": null,
+  "eval_delay": 0,
+  "torch_empty_cache_steps": null,
+  "learning_rate": 0.0003,
+  "weight_decay": 0.0,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "adam_epsilon": 1e-08,
+  "max_grad_norm": 1.0,
+  "num_train_epochs": 3,
+  "max_steps": -1,
+  "lr_scheduler_type": "linear",
+  "lr_scheduler_kwargs": {},
+  "warmup_ratio": 0.0,
+  "warmup_steps": 0,
+  "log_level": "passive",
+  "log_level_replica": "warning",
+  "log_on_each_node": true,
+  "logging_dir": "out_models/mt5-gigatrue-tpb/logs",
+  "logging_strategy": "steps",
+  "logging_first_step": true,
+  "logging_steps": 3000,
+  "logging_nan_inf_filter": true,
+  "save_strategy": "steps",
+  "save_steps": 3000,
+  "save_total_limit": null,
+  "save_safetensors": true,
+  "save_on_each_node": false,
+  "save_only_model": false,
+  "restore_callback_states_from_checkpoint": false,
+  "no_cuda": false,
+  "use_cpu": false,
+  "use_mps_device": false,
+  "seed": 42,
+  "data_seed": null,
+  "jit_mode_eval": false,
+  "use_ipex": false,
+  "bf16": false,
+  "fp16": false,
+  "fp16_opt_level": "O1",
+  "half_precision_backend": "auto",
+  "bf16_full_eval": false,
+  "fp16_full_eval": false,
+  "tf32": null,
+  "local_rank": 0,
+  "ddp_backend": null,
+  "tpu_num_cores": null,
+  "tpu_metrics_debug": false,
+  "debug": [],
+  "dataloader_drop_last": false,
+  "eval_steps": 3000,
+  "dataloader_num_workers": 0,
+  "dataloader_prefetch_factor": null,
+  "past_index": -1,
+  "run_name": "out_models/mt5-gigatrue-tpb",
+  "disable_tqdm": false,
+  "remove_unused_columns": true,
+  "label_names": null,
+  "load_best_model_at_end": false,
+  "metric_for_best_model": null,
+  "greater_is_better": null,
+  "ignore_data_skip": false,
+  "fsdp": [],
+  "fsdp_min_num_params": 0,
+  "fsdp_config": {
+    "min_num_params": 0,
+    "xla": false,
+    "xla_fsdp_v2": false,
+    "xla_fsdp_grad_ckpt": false
+  },
+  "fsdp_transformer_layer_cls_to_wrap": null,
+  "accelerator_config": "AcceleratorConfig",
+  "deepspeed": null,
+  "label_smoothing_factor": 0.0,
+  "optim": "adamw_torch",
+  "optim_args": null,
+  "adafactor": false,
+  "group_by_length": false,
+  "length_column_name": "length",
+  "report_to": [
+    "tensorboard"
+  ],
+  "ddp_find_unused_parameters": null,
+  "ddp_bucket_cap_mb": null,
+  "ddp_broadcast_buffers": null,
+  "dataloader_pin_memory": true,
+  "dataloader_persistent_workers": false,
+  "skip_memory_metrics": true,
+  "use_legacy_prediction_loop": false,
+  "push_to_hub": false,
+  "resume_from_checkpoint": null,
+  "hub_model_id": null,
+  "hub_strategy": "every_save",
+  "hub_token": null,
+  "hub_private_repo": false,
+  "hub_always_push": false,
+  "gradient_checkpointing": false,
+  "gradient_checkpointing_kwargs": null,
+  "include_inputs_for_metrics": false,
+  "eval_do_concat_batches": true,
+  "fp16_backend": "auto",
+  "evaluation_strategy": null,
+  "push_to_hub_model_id": null,
+  "push_to_hub_organization": null,
+  "push_to_hub_token": null,
+  "mp_parameters": "",
+  "auto_find_batch_size": false,
+  "full_determinism": false,
+  "torchdynamo": null,
+  "ray_scope": "last",
+  "ddp_timeout": 1800,
+  "torch_compile": false,
+  "torch_compile_backend": null,
+  "torch_compile_mode": null,
+  "dispatch_batches": null,
+  "split_batches": null,
+  "include_tokens_per_second": false,
+  "include_num_input_tokens_seen": false,
+  "neftune_noise_alpha": null,
+  "optim_target_modules": null,
+  "batch_eval_metrics": false,
+  "eval_on_start": false,
+  "use_liger_kernel": false,
+  "eval_use_gather_object": false,
+  "sortish_sampler": false,
+  "predict_with_generate": false,
+  "generation_max_length": null,
+  "generation_num_beams": null,
+  "generation_config": null,
+  "distributed_state": "PartialState",
+  "_n_gpu": 1,
+  "__cached__setup_devices": "device",
+  "deepspeed_plugin": null
+}