End of training

README.md

@@ -0,0 +1,84 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+model-index:
+- name: mt5-gigatrue-embmodtest
+  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-embmodtest
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 6.9342
+
+## 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 |
+|:-------------:|:------:|:-----:|:---------------:|
+| 8.9413        | 0.1015 | 3000  | 7.2691          |
+| 7.9891        | 0.2030 | 6000  | 7.1297          |
+| 7.8872        | 0.3044 | 9000  | 7.0543          |
+| 7.8435        | 0.4059 | 12000 | 7.0230          |
+| 7.8154        | 0.5074 | 15000 | 6.9913          |
+| 7.8           | 0.6089 | 18000 | 6.9889          |
+| 7.7871        | 0.7104 | 21000 | 6.9722          |
+| 7.7788        | 0.8119 | 24000 | 6.9650          |
+| 7.7703        | 0.9133 | 27000 | 6.9571          |
+| 7.7673        | 1.0148 | 30000 | 6.9502          |
+| 7.7648        | 1.1163 | 33000 | 6.9452          |
+| 7.759         | 1.2178 | 36000 | 6.9439          |
+| 7.7526        | 1.3193 | 39000 | 6.9407          |
+| 7.7542        | 1.4207 | 42000 | 6.9415          |
+| 7.7581        | 1.5222 | 45000 | 6.9381          |
+| 7.7523        | 1.6237 | 48000 | 6.9360          |
+| 7.7533        | 1.7252 | 51000 | 6.9367          |
+| 7.7484        | 1.8267 | 54000 | 6.9364          |
+| 7.7508        | 1.9282 | 57000 | 6.9341          |
+| 7.7513        | 2.0296 | 60000 | 6.9370          |
+| 7.7527        | 2.1311 | 63000 | 6.9352          |
+| 7.7497        | 2.2326 | 66000 | 6.9347          |
+| 7.7499        | 2.3341 | 69000 | 6.9355          |
+| 7.7476        | 2.4356 | 72000 | 6.9353          |
+| 7.7498        | 2.5370 | 75000 | 6.9355          |
+| 7.7509        | 2.6385 | 78000 | 6.9350          |
+| 7.7484        | 2.7400 | 81000 | 6.9341          |
+| 7.7488        | 2.8415 | 84000 | 6.9343          |
+| 7.7486        | 2.9430 | 87000 | 6.9342          |
+
+
+### 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": "../embedding_prune/mod",
+  "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": 160906
+}

coreconfig.json

@@ -0,0 +1,28 @@
+{
+  "out_name": "mt5-gigatrue-embmodtest",
+  "remove_layers": false,
+  "model_archetype": "mt5",
+  "model_name": "../embedding_prune/mod",
+  "tokenizer_name": "../embedding_prune/mod",
+  "model_torch_dtype": "bfloat16",
+  "dataset_lang": "en",
+  "dataset_name": "Plasmoxy/gigatrue",
+  "cache_tokens": false,
+  "dataset_tokenized_cache_name": "gigatrue_tokenized_mt5_embmodtest-default_110-35",
+  "use_half_val_dataset": true,
+  "vocab_size": 160906,
+  "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.1745704261.gna4000.1502295.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e5ae5d054860d1b8c74c9790e12860858f9a9ea833056a0d762d394c505c86e
+size 6447

logs/events.out.tfevents.1745709204.gna4000.1505139.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f119f9f520301ec6ce62d52504de3d02907763f38dfb893d4f6881e54bb5e725
+size 6453

logs/events.out.tfevents.1745711559.gna4000.1505732.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f9ad019b4b2b7458547829252358eff452384b33541d88f27d5838bd8de29fd
+size 20043

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33aac971af3cebbb6e9652c4de0402f44677e55ec7bcbb3b1862819292ad88c1
+size 417682096

nvidia_smi_early.log

@@ -0,0 +1,22 @@
+Sun Apr 27 01:53:08 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 |
+| 65%   87C    P2            136W /  140W |   14367MiB /  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   1504681      C   ...ik/miniforge3/envs/alpha/bin/python       1978MiB |
+|    0   N/A  N/A   1505732      C   ...ik/miniforge3/envs/alpha/bin/python      12372MiB |
++-----------------------------------------------------------------------------------------+

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": 79.0,
+      "learning_rate": 0.00029999661727893914,
+      "loss": 46.75,
+      "step": 1
+    },
+    {
+      "epoch": 0.10148163182463973,
+      "grad_norm": 1.6875,
+      "learning_rate": 0.000289851836817536,
+      "loss": 8.9413,
+      "step": 3000
+    },
+    {
+      "epoch": 0.10148163182463973,
+      "eval_loss": 7.269054889678955,
+      "eval_runtime": 84.8535,
+      "eval_samples_per_second": 1112.565,
+      "eval_steps_per_second": 8.697,
+      "step": 3000
+    },
+    {
+      "epoch": 0.20296326364927947,
+      "grad_norm": 2.109375,
+      "learning_rate": 0.000279703673635072,
+      "loss": 7.9891,
+      "step": 6000
+    },
+    {
+      "epoch": 0.20296326364927947,
+      "eval_loss": 7.129700183868408,
+      "eval_runtime": 84.9004,
+      "eval_samples_per_second": 1111.95,
+      "eval_steps_per_second": 8.693,
+      "step": 6000
+    },
+    {
+      "epoch": 0.30444489547391923,
+      "grad_norm": 1.609375,
+      "learning_rate": 0.00026955551045260807,
+      "loss": 7.8872,
+      "step": 9000
+    },
+    {
+      "epoch": 0.30444489547391923,
+      "eval_loss": 7.054327487945557,
+      "eval_runtime": 84.8699,
+      "eval_samples_per_second": 1112.349,
+      "eval_steps_per_second": 8.696,
+      "step": 9000
+    },
+    {
+      "epoch": 0.40592652729855894,
+      "grad_norm": 1.7734375,
+      "learning_rate": 0.0002594073472701441,
+      "loss": 7.8435,
+      "step": 12000
+    },
+    {
+      "epoch": 0.40592652729855894,
+      "eval_loss": 7.023035049438477,
+      "eval_runtime": 84.8887,
+      "eval_samples_per_second": 1112.103,
+      "eval_steps_per_second": 8.694,
+      "step": 12000
+    },
+    {
+      "epoch": 0.5074081591231987,
+      "grad_norm": 1.5703125,
+      "learning_rate": 0.0002492591840876801,
+      "loss": 7.8154,
+      "step": 15000
+    },
+    {
+      "epoch": 0.5074081591231987,
+      "eval_loss": 6.99131965637207,
+      "eval_runtime": 84.8972,
+      "eval_samples_per_second": 1111.992,
+      "eval_steps_per_second": 8.693,
+      "step": 15000
+    },
+    {
+      "epoch": 0.6088897909478385,
+      "grad_norm": 1.515625,
+      "learning_rate": 0.0002391110209052161,
+      "loss": 7.8,
+      "step": 18000
+    },
+    {
+      "epoch": 0.6088897909478385,
+      "eval_loss": 6.988863468170166,
+      "eval_runtime": 84.8916,
+      "eval_samples_per_second": 1112.065,
+      "eval_steps_per_second": 8.693,
+      "step": 18000
+    },
+    {
+      "epoch": 0.7103714227724782,
+      "grad_norm": 1.8359375,
+      "learning_rate": 0.00022896285772275215,
+      "loss": 7.7871,
+      "step": 21000
+    },
+    {
+      "epoch": 0.7103714227724782,
+      "eval_loss": 6.972222328186035,
+      "eval_runtime": 84.8906,
+      "eval_samples_per_second": 1112.078,
+      "eval_steps_per_second": 8.694,
+      "step": 21000
+    },
+    {
+      "epoch": 0.8118530545971179,
+      "grad_norm": 1.6328125,
+      "learning_rate": 0.0002188146945402882,
+      "loss": 7.7788,
+      "step": 24000
+    },
+    {
+      "epoch": 0.8118530545971179,
+      "eval_loss": 6.965023517608643,
+      "eval_runtime": 85.0087,
+      "eval_samples_per_second": 1110.533,
+      "eval_steps_per_second": 8.681,
+      "step": 24000
+    },
+    {
+      "epoch": 0.9133346864217576,
+      "grad_norm": 1.7421875,
+      "learning_rate": 0.00020866653135782423,
+      "loss": 7.7703,
+      "step": 27000
+    },
+    {
+      "epoch": 0.9133346864217576,
+      "eval_loss": 6.9570631980896,
+      "eval_runtime": 84.9952,
+      "eval_samples_per_second": 1110.71,
+      "eval_steps_per_second": 8.683,
+      "step": 27000
+    },
+    {
+      "epoch": 1.0148163182463974,
+      "grad_norm": 1.8359375,
+      "learning_rate": 0.00019851836817536025,
+      "loss": 7.7673,
+      "step": 30000
+    },
+    {
+      "epoch": 1.0148163182463974,
+      "eval_loss": 6.950160980224609,
+      "eval_runtime": 84.9886,
+      "eval_samples_per_second": 1110.796,
+      "eval_steps_per_second": 8.684,
+      "step": 30000
+    },
+    {
+      "epoch": 1.116297950071037,
+      "grad_norm": 1.859375,
+      "learning_rate": 0.0001883702049928963,
+      "loss": 7.7648,
+      "step": 33000
+    },
+    {
+      "epoch": 1.116297950071037,
+      "eval_loss": 6.945206642150879,
+      "eval_runtime": 84.9336,
+      "eval_samples_per_second": 1111.515,
+      "eval_steps_per_second": 8.689,
+      "step": 33000
+    },
+    {
+      "epoch": 1.217779581895677,
+      "grad_norm": 1.7421875,
+      "learning_rate": 0.0001782220418104323,
+      "loss": 7.759,
+      "step": 36000
+    },
+    {
+      "epoch": 1.217779581895677,
+      "eval_loss": 6.943936347961426,
+      "eval_runtime": 85.0015,
+      "eval_samples_per_second": 1110.627,
+      "eval_steps_per_second": 8.682,
+      "step": 36000
+    },
+    {
+      "epoch": 1.3192612137203166,
+      "grad_norm": 1.671875,
+      "learning_rate": 0.00016807387862796832,
+      "loss": 7.7526,
+      "step": 39000
+    },
+    {
+      "epoch": 1.3192612137203166,
+      "eval_loss": 6.940675735473633,
+      "eval_runtime": 85.0105,
+      "eval_samples_per_second": 1110.51,
+      "eval_steps_per_second": 8.681,
+      "step": 39000
+    },
+    {
+      "epoch": 1.4207428455449564,
+      "grad_norm": 1.6640625,
+      "learning_rate": 0.00015792571544550436,
+      "loss": 7.7542,
+      "step": 42000
+    },
+    {
+      "epoch": 1.4207428455449564,
+      "eval_loss": 6.941522598266602,
+      "eval_runtime": 84.8589,
+      "eval_samples_per_second": 1112.494,
+      "eval_steps_per_second": 8.697,
+      "step": 42000
+    },
+    {
+      "epoch": 1.522224477369596,
+      "grad_norm": 1.640625,
+      "learning_rate": 0.00014777755226304037,
+      "loss": 7.7581,
+      "step": 45000
+    },
+    {
+      "epoch": 1.522224477369596,
+      "eval_loss": 6.938050270080566,
+      "eval_runtime": 84.8679,
+      "eval_samples_per_second": 1112.375,
+      "eval_steps_per_second": 8.696,
+      "step": 45000
+    },
+    {
+      "epoch": 1.6237061091942357,
+      "grad_norm": 1.6640625,
+      "learning_rate": 0.0001376293890805764,
+      "loss": 7.7523,
+      "step": 48000
+    },
+    {
+      "epoch": 1.6237061091942357,
+      "eval_loss": 6.935975551605225,
+      "eval_runtime": 84.8729,
+      "eval_samples_per_second": 1112.31,
+      "eval_steps_per_second": 8.695,
+      "step": 48000
+    },
+    {
+      "epoch": 1.7251877410188756,
+      "grad_norm": 1.75,
+      "learning_rate": 0.00012748122589811243,
+      "loss": 7.7533,
+      "step": 51000
+    },
+    {
+      "epoch": 1.7251877410188756,
+      "eval_loss": 6.936653137207031,
+      "eval_runtime": 84.9125,
+      "eval_samples_per_second": 1111.791,
+      "eval_steps_per_second": 8.691,
+      "step": 51000
+    },
+    {
+      "epoch": 1.8266693728435153,
+      "grad_norm": 1.59375,
+      "learning_rate": 0.00011733306271564845,
+      "loss": 7.7484,
+      "step": 54000
+    },
+    {
+      "epoch": 1.8266693728435153,
+      "eval_loss": 6.936398983001709,
+      "eval_runtime": 84.9096,
+      "eval_samples_per_second": 1111.83,
+      "eval_steps_per_second": 8.692,
+      "step": 54000
+    },
+    {
+      "epoch": 1.928151004668155,
+      "grad_norm": 1.5390625,
+      "learning_rate": 0.00010718489953318448,
+      "loss": 7.7508,
+      "step": 57000
+    },
+    {
+      "epoch": 1.928151004668155,
+      "eval_loss": 6.934112548828125,
+      "eval_runtime": 84.9086,
+      "eval_samples_per_second": 1111.843,
+      "eval_steps_per_second": 8.692,
+      "step": 57000
+    },
+    {
+      "epoch": 2.029632636492795,
+      "grad_norm": 1.7578125,
+      "learning_rate": 9.703673635072052e-05,
+      "loss": 7.7513,
+      "step": 60000
+    },
+    {
+      "epoch": 2.029632636492795,
+      "eval_loss": 6.9370341300964355,
+      "eval_runtime": 84.9523,
+      "eval_samples_per_second": 1111.271,
+      "eval_steps_per_second": 8.687,
+      "step": 60000
+    },
+    {
+      "epoch": 2.1311142683174347,
+      "grad_norm": 1.6328125,
+      "learning_rate": 8.688857316825655e-05,
+      "loss": 7.7527,
+      "step": 63000
+    },
+    {
+      "epoch": 2.1311142683174347,
+      "eval_loss": 6.935213565826416,
+      "eval_runtime": 84.9291,
+      "eval_samples_per_second": 1111.574,
+      "eval_steps_per_second": 8.69,
+      "step": 63000
+    },
+    {
+      "epoch": 2.232595900142074,
+      "grad_norm": 2.015625,
+      "learning_rate": 7.674040998579256e-05,
+      "loss": 7.7497,
+      "step": 66000
+    },
+    {
+      "epoch": 2.232595900142074,
+      "eval_loss": 6.9347052574157715,
+      "eval_runtime": 84.9721,
+      "eval_samples_per_second": 1111.011,
+      "eval_steps_per_second": 8.685,
+      "step": 66000
+    },
+    {
+      "epoch": 2.334077531966714,
+      "grad_norm": 1.609375,
+      "learning_rate": 6.659224680332859e-05,
+      "loss": 7.7499,
+      "step": 69000
+    },
+    {
+      "epoch": 2.334077531966714,
+      "eval_loss": 6.93546724319458,
+      "eval_runtime": 85.0884,
+      "eval_samples_per_second": 1109.493,
+      "eval_steps_per_second": 8.673,
+      "step": 69000
+    },
+    {
+      "epoch": 2.435559163791354,
+      "grad_norm": 1.515625,
+      "learning_rate": 5.644408362086462e-05,
+      "loss": 7.7476,
+      "step": 72000
+    },
+    {
+      "epoch": 2.435559163791354,
+      "eval_loss": 6.935297966003418,
+      "eval_runtime": 85.0655,
+      "eval_samples_per_second": 1109.791,
+      "eval_steps_per_second": 8.676,
+      "step": 72000
+    },
+    {
+      "epoch": 2.5370407956159937,
+      "grad_norm": 1.6875,
+      "learning_rate": 4.629592043840065e-05,
+      "loss": 7.7498,
+      "step": 75000
+    },
+    {
+      "epoch": 2.5370407956159937,
+      "eval_loss": 6.93550968170166,
+      "eval_runtime": 85.1217,
+      "eval_samples_per_second": 1109.059,
+      "eval_steps_per_second": 8.67,
+      "step": 75000
+    },
+    {
+      "epoch": 2.638522427440633,
+      "grad_norm": 1.5625,
+      "learning_rate": 3.614775725593667e-05,
+      "loss": 7.7509,
+      "step": 78000
+    },
+    {
+      "epoch": 2.638522427440633,
+      "eval_loss": 6.935043811798096,
+      "eval_runtime": 85.1168,
+      "eval_samples_per_second": 1109.123,
+      "eval_steps_per_second": 8.67,
+      "step": 78000
+    },
+    {
+      "epoch": 2.740004059265273,
+      "grad_norm": 1.6171875,
+      "learning_rate": 2.59995940734727e-05,
+      "loss": 7.7484,
+      "step": 81000
+    },
+    {
+      "epoch": 2.740004059265273,
+      "eval_loss": 6.934070110321045,
+      "eval_runtime": 85.1525,
+      "eval_samples_per_second": 1108.658,
+      "eval_steps_per_second": 8.667,
+      "step": 81000
+    },
+    {
+      "epoch": 2.841485691089913,
+      "grad_norm": 1.671875,
+      "learning_rate": 1.5851430891008727e-05,
+      "loss": 7.7488,
+      "step": 84000
+    },
+    {
+      "epoch": 2.841485691089913,
+      "eval_loss": 6.934324264526367,
+      "eval_runtime": 85.1433,
+      "eval_samples_per_second": 1108.778,
+      "eval_steps_per_second": 8.668,
+      "step": 84000
+    },
+    {
+      "epoch": 2.9429673229145523,
+      "grad_norm": 1.671875,
+      "learning_rate": 5.703267708544753e-06,
+      "loss": 7.7486,
+      "step": 87000
+    },
+    {
+      "epoch": 2.9429673229145523,
+      "eval_loss": 6.934196949005127,
+      "eval_runtime": 85.1307,
+      "eval_samples_per_second": 1108.941,
+      "eval_steps_per_second": 8.669,
+      "step": 87000
+    },
+    {
+      "epoch": 3.0,
+      "step": 88686,
+      "total_flos": 9.645499494395412e+17,
+      "train_loss": 7.815265022100444,
+      "train_runtime": 33323.0229,
+      "train_samples_per_second": 340.649,
+      "train_steps_per_second": 2.661
+    }
+  ],
+  "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": 9.645499494395412e+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 sha256:7dfa9f6d96f97f77642d772f1add97a44e9d981a1457ef9c6abcac4bd9fae22e
+size 5368

training_args.json

@@ -0,0 +1,147 @@
+{
+  "output_dir": "out_models/mt5-gigatrue-embmodtest",
+  "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-embmodtest/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-embmodtest",
+  "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
+}