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": "float32",
+  "transformers_version": "4.27.4",
+  "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": "4.27.4"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc447d3128d384f4763b0ba438f963a9a0a1c108eedb6a422d56a6c47ed18b74
+size 1980790149

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c05eb1790e28aabd51bcc067e17000f70539972fe6b1c148d03fa831de6e9956
+size 990408885

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d364961fd41257fd9e5e4f8e623af755a4ec8ea4459987ad0f0d186e5bec9f80
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:991f3abde745b4b10cc13ea33a9d402812630a3981fb5f9b03b850aee28cedfc
+size 627

trainer_state.json

@@ -0,0 +1,201 @@
+{
+  "best_metric": 1.9500832557678223,
+  "best_model_checkpoint": "flan-t5-qa/checkpoint-10000",
+  "epoch": 5.0,
+  "global_step": 10000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.75e-05,
+      "loss": 3.0646,
+      "step": 500
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.5e-05,
+      "loss": 2.5167,
+      "step": 1000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.25e-05,
+      "loss": 2.3151,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 4e-05,
+      "loss": 2.2112,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 17.726,
+      "eval_loss": 2.2397749423980713,
+      "eval_rouge1": 31.2944,
+      "eval_rouge2": 16.8097,
+      "eval_rougeL": 29.7158,
+      "eval_rougeLsum": 29.856,
+      "eval_runtime": 111.783,
+      "eval_samples_per_second": 8.946,
+      "eval_steps_per_second": 1.789,
+      "step": 2000
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 2.0983,
+      "step": 2500
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 3.5e-05,
+      "loss": 2.0534,
+      "step": 3000
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 3.2500000000000004e-05,
+      "loss": 2.0071,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3e-05,
+      "loss": 1.9424,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 17.264,
+      "eval_loss": 2.061356544494629,
+      "eval_rouge1": 32.2914,
+      "eval_rouge2": 17.2352,
+      "eval_rougeL": 30.6559,
+      "eval_rougeLsum": 30.7999,
+      "eval_runtime": 109.8715,
+      "eval_samples_per_second": 9.102,
+      "eval_steps_per_second": 1.82,
+      "step": 4000
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 2.7500000000000004e-05,
+      "loss": 1.9267,
+      "step": 4500
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 2.5e-05,
+      "loss": 1.8592,
+      "step": 5000
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 2.25e-05,
+      "loss": 1.8036,
+      "step": 5500
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 2e-05,
+      "loss": 1.8168,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_gen_len": 17.385,
+      "eval_loss": 1.995050072669983,
+      "eval_rouge1": 32.1343,
+      "eval_rouge2": 17.6839,
+      "eval_rougeL": 30.9136,
+      "eval_rougeLsum": 31.0279,
+      "eval_runtime": 110.3548,
+      "eval_samples_per_second": 9.062,
+      "eval_steps_per_second": 1.812,
+      "step": 6000
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 1.75e-05,
+      "loss": 1.7743,
+      "step": 6500
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 1.5e-05,
+      "loss": 1.788,
+      "step": 7000
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 1.25e-05,
+      "loss": 1.7067,
+      "step": 7500
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1e-05,
+      "loss": 1.7924,
+      "step": 8000
+    },
+    {
+      "epoch": 4.0,
+      "eval_gen_len": 17.302,
+      "eval_loss": 1.9565637111663818,
+      "eval_rouge1": 32.6305,
+      "eval_rouge2": 18.4737,
+      "eval_rougeL": 31.4423,
+      "eval_rougeLsum": 31.5984,
+      "eval_runtime": 111.5662,
+      "eval_samples_per_second": 8.963,
+      "eval_steps_per_second": 1.793,
+      "step": 8000
+    },
+    {
+      "epoch": 4.25,
+      "learning_rate": 7.5e-06,
+      "loss": 1.7113,
+      "step": 8500
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 5e-06,
+      "loss": 1.7379,
+      "step": 9000
+    },
+    {
+      "epoch": 4.75,
+      "learning_rate": 2.5e-06,
+      "loss": 1.7181,
+      "step": 9500
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 1.6977,
+      "step": 10000
+    },
+    {
+      "epoch": 5.0,
+      "eval_gen_len": 17.333,
+      "eval_loss": 1.9500832557678223,
+      "eval_rouge1": 32.6382,
+      "eval_rouge2": 18.8113,
+      "eval_rougeL": 31.4434,
+      "eval_rougeLsum": 31.55,
+      "eval_runtime": 111.7348,
+      "eval_samples_per_second": 8.95,
+      "eval_steps_per_second": 1.79,
+      "step": 10000
+    }
+  ],
+  "max_steps": 10000,
+  "num_train_epochs": 5,
+  "total_flos": 1.65839671296e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfa1bc2238d8d154910e52f1c748f7d4ca324a3fb8a199c64258e783d7e06ac2
+size 3643