Upload model files

config.json

@@ -0,0 +1,61 @@
+{
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "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": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "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": "float32",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 32128
+}

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": "4.52.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b4b73713a370c1608044b07bf4c02f3008cc7a2f204e481e6f67f6f3391b0cd
+size 990345064

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b40e29cd664386339446bdf1d1ad5175ec9d44ac171361fe40988f77af340ff4
+size 1980860410

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af31f86f3388abfa5b91b3d55dab6c79562c22ff02e4f44b8c52a86acb6ca100
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:126e8cb42a7d71fa1c7a67cb29aa5216afa982e0e5306a10e4d09b944176db05
+size 1064

trainer_state.json

@@ -0,0 +1,291 @@
+{
+  "best_global_step": 326,
+  "best_metric": 1.5841516256332397,
+  "best_model_checkpoint": "results_t5base/checkpoint-326",
+  "epoch": 2.0,
+  "eval_steps": 200,
+  "global_step": 326,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06134969325153374,
+      "grad_norm": 116.47437286376953,
+      "learning_rate": 1.8e-05,
+      "loss": 15.8526,
+      "step": 10
+    },
+    {
+      "epoch": 0.12269938650306748,
+      "grad_norm": 36.57353591918945,
+      "learning_rate": 3.8e-05,
+      "loss": 11.7488,
+      "step": 20
+    },
+    {
+      "epoch": 0.18404907975460122,
+      "grad_norm": 32.9762077331543,
+      "learning_rate": 5.800000000000001e-05,
+      "loss": 10.3287,
+      "step": 30
+    },
+    {
+      "epoch": 0.24539877300613497,
+      "grad_norm": 23.83042335510254,
+      "learning_rate": 7.8e-05,
+      "loss": 6.4168,
+      "step": 40
+    },
+    {
+      "epoch": 0.3067484662576687,
+      "grad_norm": 4.865868091583252,
+      "learning_rate": 9.800000000000001e-05,
+      "loss": 3.5254,
+      "step": 50
+    },
+    {
+      "epoch": 0.36809815950920244,
+      "grad_norm": 12.269708633422852,
+      "learning_rate": 0.000118,
+      "loss": 3.0389,
+      "step": 60
+    },
+    {
+      "epoch": 0.4294478527607362,
+      "grad_norm": 7.369626998901367,
+      "learning_rate": 0.00013800000000000002,
+      "loss": 2.5275,
+      "step": 70
+    },
+    {
+      "epoch": 0.49079754601226994,
+      "grad_norm": 2.0186314582824707,
+      "learning_rate": 0.000158,
+      "loss": 2.1442,
+      "step": 80
+    },
+    {
+      "epoch": 0.5521472392638037,
+      "grad_norm": 1.231919527053833,
+      "learning_rate": 0.000178,
+      "loss": 1.8347,
+      "step": 90
+    },
+    {
+      "epoch": 0.6134969325153374,
+      "grad_norm": 1.3266997337341309,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 1.7494,
+      "step": 100
+    },
+    {
+      "epoch": 0.6748466257668712,
+      "grad_norm": 1.498828649520874,
+      "learning_rate": 0.000218,
+      "loss": 1.8056,
+      "step": 110
+    },
+    {
+      "epoch": 0.7361963190184049,
+      "grad_norm": 0.9476116299629211,
+      "learning_rate": 0.00023799999999999998,
+      "loss": 1.7621,
+      "step": 120
+    },
+    {
+      "epoch": 0.7975460122699386,
+      "grad_norm": 1.154313564300537,
+      "learning_rate": 0.00025800000000000004,
+      "loss": 1.7556,
+      "step": 130
+    },
+    {
+      "epoch": 0.8588957055214724,
+      "grad_norm": 0.7778469920158386,
+      "learning_rate": 0.00027800000000000004,
+      "loss": 1.7215,
+      "step": 140
+    },
+    {
+      "epoch": 0.9202453987730062,
+      "grad_norm": 0.8308514356613159,
+      "learning_rate": 0.000298,
+      "loss": 1.6761,
+      "step": 150
+    },
+    {
+      "epoch": 0.9815950920245399,
+      "grad_norm": 1.156718373298645,
+      "learning_rate": 0.00031800000000000003,
+      "loss": 1.6865,
+      "step": 160
+    },
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 187.0146,
+      "eval_loss": 1.5963470935821533,
+      "eval_rouge1": 0.6129,
+      "eval_rouge2": 0.2686,
+      "eval_rougeL": 0.4794,
+      "eval_runtime": 30.837,
+      "eval_samples_per_second": 8.885,
+      "eval_steps_per_second": 1.135,
+      "step": 163
+    },
+    {
+      "epoch": 1.0429447852760736,
+      "grad_norm": 0.8923042416572571,
+      "learning_rate": 0.00033800000000000003,
+      "loss": 1.6244,
+      "step": 170
+    },
+    {
+      "epoch": 1.1042944785276074,
+      "grad_norm": 1.0038191080093384,
+      "learning_rate": 0.000358,
+      "loss": 1.6075,
+      "step": 180
+    },
+    {
+      "epoch": 1.165644171779141,
+      "grad_norm": 0.9305262565612793,
+      "learning_rate": 0.000378,
+      "loss": 1.6722,
+      "step": 190
+    },
+    {
+      "epoch": 1.2269938650306749,
+      "grad_norm": 1.2464691400527954,
+      "learning_rate": 0.000398,
+      "loss": 1.5723,
+      "step": 200
+    },
+    {
+      "epoch": 1.2883435582822087,
+      "grad_norm": 1.017632246017456,
+      "learning_rate": 0.00041799999999999997,
+      "loss": 1.5711,
+      "step": 210
+    },
+    {
+      "epoch": 1.3496932515337423,
+      "grad_norm": 1.2981927394866943,
+      "learning_rate": 0.000438,
+      "loss": 1.5017,
+      "step": 220
+    },
+    {
+      "epoch": 1.4110429447852761,
+      "grad_norm": 0.7919584512710571,
+      "learning_rate": 0.000458,
+      "loss": 1.5671,
+      "step": 230
+    },
+    {
+      "epoch": 1.4723926380368098,
+      "grad_norm": 1.0223811864852905,
+      "learning_rate": 0.00047799999999999996,
+      "loss": 1.5162,
+      "step": 240
+    },
+    {
+      "epoch": 1.5337423312883436,
+      "grad_norm": 0.8784969449043274,
+      "learning_rate": 0.000498,
+      "loss": 1.5689,
+      "step": 250
+    },
+    {
+      "epoch": 1.5950920245398774,
+      "grad_norm": 0.8144865036010742,
+      "learning_rate": 0.000518,
+      "loss": 1.6243,
+      "step": 260
+    },
+    {
+      "epoch": 1.656441717791411,
+      "grad_norm": 0.846225380897522,
+      "learning_rate": 0.0005380000000000001,
+      "loss": 1.5596,
+      "step": 270
+    },
+    {
+      "epoch": 1.7177914110429446,
+      "grad_norm": 0.9448590278625488,
+      "learning_rate": 0.000558,
+      "loss": 1.399,
+      "step": 280
+    },
+    {
+      "epoch": 1.7791411042944785,
+      "grad_norm": 0.9131848812103271,
+      "learning_rate": 0.000578,
+      "loss": 1.6336,
+      "step": 290
+    },
+    {
+      "epoch": 1.8404907975460123,
+      "grad_norm": 0.8644697070121765,
+      "learning_rate": 0.000598,
+      "loss": 1.6112,
+      "step": 300
+    },
+    {
+      "epoch": 1.9018404907975461,
+      "grad_norm": 0.964495062828064,
+      "learning_rate": 0.0006180000000000001,
+      "loss": 1.5901,
+      "step": 310
+    },
+    {
+      "epoch": 1.9631901840490797,
+      "grad_norm": 0.8454228043556213,
+      "learning_rate": 0.000638,
+      "loss": 1.609,
+      "step": 320
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 187.0146,
+      "eval_loss": 1.5841516256332397,
+      "eval_rouge1": 0.6218,
+      "eval_rouge2": 0.2773,
+      "eval_rougeL": 0.4814,
+      "eval_runtime": 30.1539,
+      "eval_samples_per_second": 9.087,
+      "eval_steps_per_second": 1.161,
+      "step": 326
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 815,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 2,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1780369116364800.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7754bd4e83bed7b96855efa35789508d4de02653b5f8d39fee4dc8e79aa7cef3
+size 5240