Training in progress, epoch 1, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,62 @@
+{
+  "_name_or_path": "google/flan-t5-small",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 1024,
+  "d_kv": 64,
+  "d_model": 512,
+  "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": 8,
+  "num_heads": 6,
+  "num_layers": 8,
+  "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": "4.34.1",
+  "use_cache": true,
+  "vocab_size": 32128
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.34.1"
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6572cff3e430f8b0e0f3bfe09bda75d381065141e40f8356aaa310fb90c7873f
+size 615849402

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31b14e4ef7f5c18880871f1b949d5c359189c01c9ba1b30b28a4c924aea76264
+size 307910594

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b83f92ac0720a2f5b4067d4a2963eca724e17ccedc67dfc75b3a214117b809a
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8be8a36beb1fc6b551ca68200e840d60a17bf929b3ef96882ca0e28d8e324966
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,50 @@
+{
+  "best_metric": 0.01884176954627037,
+  "best_model_checkpoint": "flan-search-terms/checkpoint-1500",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 3.6415,
+      "step": 500
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 0.0455,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 4e-05,
+      "loss": 0.0301,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 4.940333333333333,
+      "eval_loss": 0.01884176954627037,
+      "eval_rouge1": 6.3132,
+      "eval_rouge2": 5.5233,
+      "eval_rougeL": 5.9306,
+      "eval_rougeLsum": 5.9285,
+      "eval_runtime": 220.0768,
+      "eval_samples_per_second": 13.632,
+      "eval_steps_per_second": 1.704,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7500,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 2230686056448000.0,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1273900ee8c6a616bf319717a7ecf5d7d198e1660ad1a1bfd22ca4bce11365b0
+size 4664