Upload 8 files

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "google/flan-t5-base",
+  "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": "bfloat16",
+  "transformers_version": "4.27.2",
+  "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": "4.27.2"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9289a02b5cd81b9178f83757c7868963e2b2ff2c690481b0b1950434cb387af
+size 990478725

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67a71f6e9195146293581c5d52805302b4cb792c5d65ef2f62d2f49adb99139d
+size 495253173

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:627ec79a647484b80faeda64c831bc87b3fbae4f47702ce9513eaab97fc57a19
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72613c3db44bc51082dbd8daac1b7493525ab4d2e8ea3698a81b418a19bd4aba
+size 627

trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.036034412864285395,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 10.6517,
+      "step": 100
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 2.1456,
+      "step": 200
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 1.3578,
+      "step": 300
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.0559,
+      "step": 400
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5e-05,
+      "loss": 0.9472,
+      "step": 500
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.8765,
+      "step": 600
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.8402,
+      "step": 700
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.8968,
+      "step": 800
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.8694,
+      "step": 900
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0,
+      "loss": 0.8573,
+      "step": 1000
+    }
+  ],
+  "max_steps": 1000,
+  "num_train_epochs": 1,
+  "total_flos": 5478058819584000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d7fbebf6a75146d577baf878f4050d9c898ee6c309ca3e54d1fd0b41878d0fb
+size 3579