End of training

README.md

@@ -1,5 +1,7 @@
 ---
 library_name: transformers
+license: apache-2.0
+base_model: google/flan-t5-small
 tags:
 - generated_from_trainer
 model-index:
@@ -12,7 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # flan-t5-small-gigatrue
 
-This model was trained from scratch on an unknown dataset.
+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: 2.1229
 
 ## Model description
 
@@ -32,16 +36,36 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0003
-- train_batch_size: 384
-- eval_batch_size: 384
+- train_batch_size: 256
+- eval_batch_size: 256
 - seed: 42
-- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss |
+|:-------------:|:------:|:-----:|:---------------:|
+| 2.5659        | 0.2030 | 3000  | 2.1724          |
+| 2.4802        | 0.4059 | 6000  | 2.1500          |
+| 2.4581        | 0.6089 | 9000  | 2.1390          |
+| 2.4493        | 0.8119 | 12000 | 2.1325          |
+| 2.4436        | 1.0148 | 15000 | 2.1282          |
+| 2.4398        | 1.2178 | 18000 | 2.1255          |
+| 2.437         | 1.4207 | 21000 | 2.1246          |
+| 2.434         | 1.6237 | 24000 | 2.1246          |
+| 2.4337        | 1.8267 | 27000 | 2.1226          |
+| 2.4337        | 2.0296 | 30000 | 2.1228          |
+| 2.4314        | 2.2326 | 33000 | 2.1234          |
+| 2.4332        | 2.4356 | 36000 | 2.1232          |
+| 2.4327        | 2.6385 | 39000 | 2.1230          |
+| 2.4329        | 2.8415 | 42000 | 2.1229          |
+
 
 ### Framework versions
 
-- Transformers 4.48.0.dev0
+- Transformers 4.45.2
 - Pytorch 2.5.1
-- Datasets 3.1.0
-- Tokenizers 0.21.0
+- Datasets 3.2.0
+- Tokenizers 0.20.3

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "out_models/flan-t5-small-gigatrue/checkpoint-30000",
+  "_name_or_path": "google/flan-t5-small",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
@@ -56,7 +56,7 @@
   },
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.48.0.dev0",
+  "transformers_version": "4.45.2",
   "use_cache": true,
   "vocab_size": 32128
 }

coreconfig.json

@@ -0,0 +1,25 @@
+{
+  "out_name": "flan-t5-small-gigatrue",
+  "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",
+  "dataset_tokenized_cache_name": "gigatrue_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

@@ -3,5 +3,5 @@
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.48.0.dev0"
+  "transformers_version": "4.45.2"
 }

logs/events.out.tfevents.1735302432.gna4000.525859.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f851c46a719ea78e60099fa280d40061c0fbda8176d83bf0f4c1efeebfc9736b
+size 13422

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5100139f82169778e467427a787e487fabfd11a17122793ec011956e0d3247a0
+oid sha256:46cd84808c92808adb657558e14514303a2fd1aeeafb163b0a1bed6a41b26c45
 size 153944752

nvidia_smi_early.log

@@ -0,0 +1,21 @@
+Fri Dec 27 13:27:42 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 |
+| 51%   74C    P2            138W /  140W |   14847MiB /  16376MiB |     91%      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    525859      C   ...ik/miniforge3/envs/alpha/bin/python      14832MiB |
++-----------------------------------------------------------------------------------------+

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73ef5eeca8e3dfe9232b166b1bf9cee56e99ab18fea64088392adaea14488865
-size 5432
+oid sha256:0d0165d5a0e9812718de38fae078cd45ae10c9d435df8eb62a31208c5e26e956
+size 5368

training_args.json

@@ -0,0 +1,147 @@
+{
+  "output_dir": "out_models/flan-t5-small-gigatrue",
+  "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/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",
+  "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
+}