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 sha256:0524507a435e75807819d0d829021df96fbcd5503948371f6d0c2c58383863a0
+size 990478725

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cce55b10ca1ef81a3b73a0bb792dcd12e6f07b27557c790d3d1c1aede60ce0e9
+size 495253173

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f033d7f8a5dd0eaa3b269a15d129aaebbc11cac0da34c63e97d0f8c8c3b3058d
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffa84e40719b997939d68759cd6081e20cd194a4249148874782150e77884095
+size 627

trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.018017206432142698,
+  "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": 0.00019510565162951537,
+      "loss": 6.2051,
+      "step": 100
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.9004,
+      "step": 200
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 0.7042,
+      "step": 300
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.6277,
+      "step": 400
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0001,
+      "loss": 0.6574,
+      "step": 500
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.6373,
+      "step": 600
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.5668,
+      "step": 700
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.6167,
+      "step": 800
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.5712,
+      "step": 900
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0,
+      "loss": 0.6059,
+      "step": 1000
+    }
+  ],
+  "max_steps": 1000,
+  "num_train_epochs": 1,
+  "total_flos": 2739029409792000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b6cd9e40ee0309e826664f548088f27d5011515ff0361689eff34dfcc9624e9
+size 3643