End of training

README.md

@@ -0,0 +1,71 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/flan-t5-small
+tags:
+- generated_from_trainer
+model-index:
+- name: flan-t5-small-gigatrue-AU-D-456
+  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. -->
+
+# flan-t5-small-gigatrue-AU-D-456
+
+This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.5591
+
+## 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: 256
+- eval_batch_size: 256
+- 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 |
+|:-------------:|:------:|:-----:|:---------------:|
+| 3.1476        | 0.2030 | 3000  | 2.6159          |
+| 3.0318        | 0.4059 | 6000  | 2.5882          |
+| 3.0079        | 0.6089 | 9000  | 2.5750          |
+| 3.0           | 0.8119 | 12000 | 2.5675          |
+| 2.9932        | 1.0148 | 15000 | 2.5650          |
+| 2.9891        | 1.2178 | 18000 | 2.5632          |
+| 2.9869        | 1.4207 | 21000 | 2.5603          |
+| 2.9846        | 1.6237 | 24000 | 2.5608          |
+| 2.9831        | 1.8267 | 27000 | 2.5591          |
+| 2.9832        | 2.0296 | 30000 | 2.5592          |
+| 2.9811        | 2.2326 | 33000 | 2.5591          |
+| 2.9841        | 2.4356 | 36000 | 2.5594          |
+| 2.9836        | 2.6385 | 39000 | 2.5589          |
+| 2.9827        | 2.8415 | 42000 | 2.5591          |
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.5.1
+- Datasets 3.2.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,62 @@
+{
+  "_name_or_path": "google/flan-t5-small",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "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": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 5,
+  "num_heads": 6,
+  "num_layers": 8,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": true,
+  "vocab_size": 32128
+}

coreconfig.json

@@ -0,0 +1,26 @@
+{
+  "out_name": "flan-t5-small-gigatrue-AU-D-456",
+  "remove_layers": true,
+  "model_archetype": "flan-t5",
+  "model_name": "google/flan-t5-small",
+  "tokenizer_name": "google/flan-t5-small",
+  "model_torch_dtype": "bfloat16",
+  "dataset_lang": "en",
+  "dataset_name": "Plasmoxy/gigatrue-abstract-unaware",
+  "dataset_tokenized_cache_name": "gigatrue-AU_tokenized_flan_t5_110-35",
+  "use_half_val_dataset": true,
+  "max_input_length": 110,
+  "max_target_length": 35,
+  "batch_size": 256,
+  "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.1736284546.gna4000.742540.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc78a0e2a420f8aecd3b64fb924c5524abf7ddd0b46f2601c4e41b1ce8ff722e
+size 13449

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5194c9c5c334179ce5d8fc4100177239951453b796f330f37ddd42281937c6fc
+size 135056184

nvidia_smi_early.log

@@ -0,0 +1,21 @@
+Tue Jan  7 22:16:16 2025       
++-----------------------------------------------------------------------------------------+
+| 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%   65C    P2            138W /  140W |   13177MiB /  16376MiB |     92%      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    742540      C   ...ik/miniforge3/envs/alpha/bin/python      13162MiB |
++-----------------------------------------------------------------------------------------+

trainer_state.json

@@ -0,0 +1,259 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 3000,
+  "global_step": 44343,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 6.76544212164265e-05,
+      "grad_norm": 13.6875,
+      "learning_rate": 0.0002999932345578783,
+      "loss": 4.8125,
+      "step": 1
+    },
+    {
+      "epoch": 0.20296326364927947,
+      "grad_norm": 0.9453125,
+      "learning_rate": 0.000279703673635072,
+      "loss": 3.1476,
+      "step": 3000
+    },
+    {
+      "epoch": 0.20296326364927947,
+      "eval_loss": 2.6158535480499268,
+      "eval_runtime": 54.7052,
+      "eval_samples_per_second": 1725.705,
+      "eval_steps_per_second": 6.745,
+      "step": 3000
+    },
+    {
+      "epoch": 0.40592652729855894,
+      "grad_norm": 0.98046875,
+      "learning_rate": 0.0002594073472701441,
+      "loss": 3.0318,
+      "step": 6000
+    },
+    {
+      "epoch": 0.40592652729855894,
+      "eval_loss": 2.588202953338623,
+      "eval_runtime": 54.5614,
+      "eval_samples_per_second": 1730.252,
+      "eval_steps_per_second": 6.763,
+      "step": 6000
+    },
+    {
+      "epoch": 0.6088897909478385,
+      "grad_norm": 0.8203125,
+      "learning_rate": 0.0002391110209052161,
+      "loss": 3.0079,
+      "step": 9000
+    },
+    {
+      "epoch": 0.6088897909478385,
+      "eval_loss": 2.5750339031219482,
+      "eval_runtime": 54.4102,
+      "eval_samples_per_second": 1735.062,
+      "eval_steps_per_second": 6.782,
+      "step": 9000
+    },
+    {
+      "epoch": 0.8118530545971179,
+      "grad_norm": 1.09375,
+      "learning_rate": 0.0002188146945402882,
+      "loss": 3.0,
+      "step": 12000
+    },
+    {
+      "epoch": 0.8118530545971179,
+      "eval_loss": 2.5675389766693115,
+      "eval_runtime": 54.4389,
+      "eval_samples_per_second": 1734.145,
+      "eval_steps_per_second": 6.778,
+      "step": 12000
+    },
+    {
+      "epoch": 1.0148163182463974,
+      "grad_norm": 0.99609375,
+      "learning_rate": 0.00019851836817536025,
+      "loss": 2.9932,
+      "step": 15000
+    },
+    {
+      "epoch": 1.0148163182463974,
+      "eval_loss": 2.564955949783325,
+      "eval_runtime": 54.5924,
+      "eval_samples_per_second": 1729.27,
+      "eval_steps_per_second": 6.759,
+      "step": 15000
+    },
+    {
+      "epoch": 1.217779581895677,
+      "grad_norm": 1.3125,
+      "learning_rate": 0.0001782220418104323,
+      "loss": 2.9891,
+      "step": 18000
+    },
+    {
+      "epoch": 1.217779581895677,
+      "eval_loss": 2.5631775856018066,
+      "eval_runtime": 54.5754,
+      "eval_samples_per_second": 1729.81,
+      "eval_steps_per_second": 6.761,
+      "step": 18000
+    },
+    {
+      "epoch": 1.4207428455449564,
+      "grad_norm": 1.234375,
+      "learning_rate": 0.00015792571544550436,
+      "loss": 2.9869,
+      "step": 21000
+    },
+    {
+      "epoch": 1.4207428455449564,
+      "eval_loss": 2.560298204421997,
+      "eval_runtime": 54.5785,
+      "eval_samples_per_second": 1729.709,
+      "eval_steps_per_second": 6.761,
+      "step": 21000
+    },
+    {
+      "epoch": 1.6237061091942357,
+      "grad_norm": 1.2890625,
+      "learning_rate": 0.0001376293890805764,
+      "loss": 2.9846,
+      "step": 24000
+    },
+    {
+      "epoch": 1.6237061091942357,
+      "eval_loss": 2.5608062744140625,
+      "eval_runtime": 54.7118,
+      "eval_samples_per_second": 1725.495,
+      "eval_steps_per_second": 6.744,
+      "step": 24000
+    },
+    {
+      "epoch": 1.8266693728435153,
+      "grad_norm": 1.15625,
+      "learning_rate": 0.00011733306271564845,
+      "loss": 2.9831,
+      "step": 27000
+    },
+    {
+      "epoch": 1.8266693728435153,
+      "eval_loss": 2.559070110321045,
+      "eval_runtime": 54.5867,
+      "eval_samples_per_second": 1729.449,
+      "eval_steps_per_second": 6.76,
+      "step": 27000
+    },
+    {
+      "epoch": 2.029632636492795,
+      "grad_norm": 1.15625,
+      "learning_rate": 9.703673635072052e-05,
+      "loss": 2.9832,
+      "step": 30000
+    },
+    {
+      "epoch": 2.029632636492795,
+      "eval_loss": 2.559154748916626,
+      "eval_runtime": 54.5764,
+      "eval_samples_per_second": 1729.778,
+      "eval_steps_per_second": 6.761,
+      "step": 30000
+    },
+    {
+      "epoch": 2.232595900142074,
+      "grad_norm": 1.1953125,
+      "learning_rate": 7.674040998579256e-05,
+      "loss": 2.9811,
+      "step": 33000
+    },
+    {
+      "epoch": 2.232595900142074,
+      "eval_loss": 2.559070110321045,
+      "eval_runtime": 54.4327,
+      "eval_samples_per_second": 1734.344,
+      "eval_steps_per_second": 6.779,
+      "step": 33000
+    },
+    {
+      "epoch": 2.435559163791354,
+      "grad_norm": 1.203125,
+      "learning_rate": 5.644408362086462e-05,
+      "loss": 2.9841,
+      "step": 36000
+    },
+    {
+      "epoch": 2.435559163791354,
+      "eval_loss": 2.559366464614868,
+      "eval_runtime": 54.4466,
+      "eval_samples_per_second": 1733.901,
+      "eval_steps_per_second": 6.777,
+      "step": 36000
+    },
+    {
+      "epoch": 2.638522427440633,
+      "grad_norm": 1.140625,
+      "learning_rate": 3.614775725593667e-05,
+      "loss": 2.9836,
+      "step": 39000
+    },
+    {
+      "epoch": 2.638522427440633,
+      "eval_loss": 2.558900833129883,
+      "eval_runtime": 54.4453,
+      "eval_samples_per_second": 1733.941,
+      "eval_steps_per_second": 6.777,
+      "step": 39000
+    },
+    {
+      "epoch": 2.841485691089913,
+      "grad_norm": 1.578125,
+      "learning_rate": 1.5851430891008727e-05,
+      "loss": 2.9827,
+      "step": 42000
+    },
+    {
+      "epoch": 2.841485691089913,
+      "eval_loss": 2.559112548828125,
+      "eval_runtime": 54.4302,
+      "eval_samples_per_second": 1734.422,
+      "eval_steps_per_second": 6.779,
+      "step": 42000
+    },
+    {
+      "epoch": 3.0,
+      "step": 44343,
+      "total_flos": 3.8956704097296384e+17,
+      "train_loss": 3.0017653575536163,
+      "train_runtime": 20075.3447,
+      "train_samples_per_second": 565.443,
+      "train_steps_per_second": 2.209
+    }
+  ],
+  "logging_steps": 3000,
+  "max_steps": 44343,
+  "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": 3.8956704097296384e+17,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0daa94fbe297617ff9872da7b5dd558cda8aa955d1b76e36ff1f43020e95fa52
+size 5368

training_args.json

@@ -0,0 +1,147 @@
+{
+  "output_dir": "out_models/flan-t5-small-gigatrue-AU-D-456",
+  "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": 256,
+  "per_device_eval_batch_size": 256,
+  "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/flan-t5-small-gigatrue-AU-D-456/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/flan-t5-small-gigatrue-AU-D-456",
+  "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
+}