End of training

README.md

@@ -0,0 +1,86 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/mt5-small
+tags:
+- generated_from_trainer
+model-index:
+- name: mt5-small-gigatrue-layercut-D5
+  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-small-gigatrue-layercut-D5
+
+This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.4092
+
+## 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 |
+|:-------------:|:------:|:-----:|:---------------:|
+| 3.6665        | 0.1015 | 3000  | 2.5503          |
+| 3.1237        | 0.2030 | 6000  | 2.4814          |
+| 3.0657        | 0.3044 | 9000  | 2.4631          |
+| 3.0389        | 0.4059 | 12000 | 2.4435          |
+| 3.0188        | 0.5074 | 15000 | 2.4455          |
+| 3.0112        | 0.6089 | 18000 | 2.4229          |
+| 3.0059        | 0.7104 | 21000 | 2.4302          |
+| 3.0001        | 0.8119 | 24000 | 2.4221          |
+| 2.994         | 0.9133 | 27000 | 2.4214          |
+| 2.9932        | 1.0148 | 30000 | 2.4205          |
+| 2.991         | 1.1163 | 33000 | 2.4148          |
+| 2.9857        | 1.2178 | 36000 | 2.4131          |
+| 2.985         | 1.3193 | 39000 | 2.4148          |
+| 2.9831        | 1.4207 | 42000 | 2.4104          |
+| 2.9842        | 1.5222 | 45000 | 2.4128          |
+| 2.9785        | 1.6237 | 48000 | 2.4131          |
+| 2.9817        | 1.7252 | 51000 | 2.4099          |
+| 2.9754        | 1.8267 | 54000 | 2.4114          |
+| 2.977         | 1.9282 | 57000 | 2.4088          |
+| 2.9784        | 2.0296 | 60000 | 2.4082          |
+| 2.9792        | 2.1311 | 63000 | 2.4095          |
+| 2.9768        | 2.2326 | 66000 | 2.4102          |
+| 2.9773        | 2.3341 | 69000 | 2.4096          |
+| 2.9764        | 2.4356 | 72000 | 2.4085          |
+| 2.9771        | 2.5370 | 75000 | 2.4076          |
+| 2.9795        | 2.6385 | 78000 | 2.4085          |
+| 2.9768        | 2.7400 | 81000 | 2.4088          |
+| 2.9762        | 2.8415 | 84000 | 2.4093          |
+| 2.9776        | 2.9430 | 87000 | 2.4092          |
+
+
+### 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": "google/mt5-small",
+  "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": 7,
+  "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": 250112
+}

coreconfig.json

@@ -0,0 +1,25 @@
+{
+  "out_name": "mt5-small-gigatrue-layercut-D5",
+  "model_archetype": "mt5",
+  "model_name": "google/mt5-small",
+  "tokenizer_name": "google/mt5-small",
+  "model_torch_dtype": "bfloat16",
+  "dataset_lang": "en",
+  "dataset_name": "Plasmoxy/gigatrue",
+  "dataset_tokenized_cache_name": "gigatrue_tokenized_mt5_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.1735156050.gna4000.444933.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a3b33997ebbcbc9502ec5496eb3e980845fa7ae4ae66b7120283024825e8048
+size 20058

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55b5c6e7d6e6a7621c5146a30eaf391f79b8fcc26a0684b315af985d0b0da821
+size 594079800

nvidia_smi_early.log

@@ -0,0 +1,21 @@
+Wed Dec 25 20:47:59 2024       
++-----------------------------------------------------------------------------------------+
+| NVIDIA-SMI 550.127.08             Driver Version: 550.127.08     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 |
+| 41%   64C    P2            135W /  140W |   15217MiB /  16376MiB |    100%      Default |
+|                                         |                        |                  N/A |
++-----------------------------------------+------------------------+----------------------+
+                                                                                         
++-----------------------------------------------------------------------------------------+
+| Processes:                                                                              |
+|  GPU   GI   CI        PID   Type   Process name                              GPU Memory |
+|        ID   ID                                                               Usage      |
+|=========================================================================================|
+|    0   N/A  N/A     76833      G   /usr/lib/xorg/Xorg                              4MiB |
+|    0   N/A  N/A    444933      C   ...ik/miniforge3/envs/alpha/bin/python      15202MiB |
++-----------------------------------------------------------------------------------------+

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57314b6f30842281dbcc7a37cf2570a5d52e1f4a957fcd4b79faadf8f8330bbf
+size 5368

training_args.json

@@ -0,0 +1,147 @@
+{
+  "output_dir": "out_models/mt5-small-gigatrue-layercut-D5",
+  "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-small-gigatrue-layercut-D5/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-small-gigatrue-layercut-D5",
+  "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
+}