First model version

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "/content/drive/MyDrive/results6/checkpoint-12460",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "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: "
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.0",
+  "use_cache": true,
+  "vocab_size": 32128
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.27.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f19c703280faab8db6875a6720b2083c60ea74facb7217a9af5c52ce4f013ca
+size 891702929

trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": 1.2918661832809448,
+  "epoch": 5.0,
+  "global_step": 6230,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 4.08,
+      "learning_rate": 9.866238630283575e-06,
+      "loss": 0.8765,
+      "step": 500
+    },
+    {
+      "epoch": 4.16,
+      "learning_rate": 9.73247726056715e-06,
+      "loss": 0.8865,
+      "step": 1000
+    },
+    {
+      "epoch": 4.24,
+      "learning_rate": 9.598715890850723e-06,
+      "loss": 0.8513,
+      "step": 1500
+    },
+    {
+      "epoch": 4.32,
+      "learning_rate": 9.464954521134298e-06,
+      "loss": 0.8626,
+      "step": 2000
+    },
+    {
+      "epoch": 4.4,
+      "learning_rate": 9.331193151417872e-06,
+      "loss": 0.8445,
+      "step": 2500
+    },
+    {
+      "epoch": 4.48,
+      "learning_rate": 9.197431781701446e-06,
+      "loss": 0.8685,
+      "step": 3000
+    },
+    {
+      "epoch": 4.56,
+      "learning_rate": 9.06367041198502e-06,
+      "loss": 0.8664,
+      "step": 3500
+    },
+    {
+      "epoch": 4.64,
+      "learning_rate": 8.929909042268593e-06,
+      "loss": 0.8514,
+      "step": 4000
+    },
+    {
+      "epoch": 4.72,
+      "learning_rate": 8.796147672552167e-06,
+      "loss": 0.8476,
+      "step": 4500
+    },
+    {
+      "epoch": 4.8,
+      "learning_rate": 8.662386302835741e-06,
+      "loss": 0.8252,
+      "step": 5000
+    },
+    {
+      "epoch": 4.88,
+      "learning_rate": 8.528624933119315e-06,
+      "loss": 0.8658,
+      "step": 5500
+    },
+    {
+      "epoch": 4.96,
+      "learning_rate": 8.39486356340289e-06,
+      "loss": 0.8453,
+      "step": 6000
+    },
+    {
+      "epoch": 5.0,
+      "eval_gen_len": 18.796,
+      "eval_loss": 1.2918661832809448,
+      "eval_rouge1": 39.8436,
+      "eval_rouge2": 15.5632,
+      "eval_rougeL": 33.522,
+      "eval_rougeLsum": 35.2901,
+      "eval_runtime": 722.0768,
+      "eval_samples_per_second": 2.077,
+      "eval_steps_per_second": 1.039,
+      "step": 6230
+    }
+  ],
+  "max_steps": 37380,
+  "num_train_epochs": 6,
+  "total_flos": 1.48195611648e+16,
+  "trial_name": null,
+  "trial_params": null
+}