Upload 4 files

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "philschmid/flan-t5-base-samsum",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "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": "4.26.1",
+  "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": "4.26.1"
+}

trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_metric": 2.5199410915374756,
+  "best_model_checkpoint": "flan-t5-base-samsum-Amalq/shared_TaskA/checkpoint-453",
+  "epoch": 3.0,
+  "global_step": 453,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 18.97,
+      "eval_loss": 2.5625901222229004,
+      "eval_rouge1": 28.4776,
+      "eval_rouge2": 14.7774,
+      "eval_rougeL": 28.0326,
+      "eval_rougeLsum": 28.0975,
+      "eval_runtime": 63.2726,
+      "eval_samples_per_second": 1.58,
+      "eval_steps_per_second": 0.205,
+      "step": 151
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 18.88,
+      "eval_loss": 2.539769172668457,
+      "eval_rouge1": 27.1318,
+      "eval_rouge2": 13.7771,
+      "eval_rougeL": 26.658,
+      "eval_rougeLsum": 26.7023,
+      "eval_runtime": 63.4889,
+      "eval_samples_per_second": 1.575,
+      "eval_steps_per_second": 0.205,
+      "step": 302
+    },
+    {
+      "epoch": 3.0,
+      "eval_gen_len": 18.8,
+      "eval_loss": 2.5199410915374756,
+      "eval_rouge1": 28.3352,
+      "eval_rouge2": 14.5989,
+      "eval_rougeL": 27.719,
+      "eval_rougeLsum": 27.8475,
+      "eval_runtime": 64.2752,
+      "eval_samples_per_second": 1.556,
+      "eval_steps_per_second": 0.202,
+      "step": 453
+    }
+  ],
+  "max_steps": 755,
+  "num_train_epochs": 5,
+  "total_flos": 2467180740870144.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b323e75586fbb3139afb14feb40aa14fc37b093de4f363400e89cca90fdf93a6
+size 3631