Training in progress, epoch 1, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,62 @@
+{
+  "_name_or_path": "google/flan-t5-base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "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": "4.34.1",
+  "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 sha256:5771d626f5f76c2b40ece2e4df39b8bd24efbe70d36c0311ddd3dd81b57e21c1
+size 2371770

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b636a897f64e4794cb84771a349ebd9bde27930ac81d66a20be31aef9dc7faeb
+size 990409330

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cea44ad93fec8c4df820561aaed097d102f17e9be600b9a116f68fe9875b8e4
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4afbee4eef31ae6f0f2f4373f90e6cf49579bddfce99e5131fce75c63b548f86
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": 2.409773349761963,
+  "best_model_checkpoint": "dq158/pingusPongus/checkpoint-1581",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1581,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0001,
+      "loss": 3.1034,
+      "step": 500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 9.993631921956987e-05,
+      "loss": 2.6893,
+      "step": 1000
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 9.974543908795133e-05,
+      "loss": 2.5782,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_bleu": 1.0,
+      "eval_brevity_penalty": 1.0,
+      "eval_length_ratio": 1.0,
+      "eval_loss": 2.409773349761963,
+      "eval_precisions": [
+        1.0,
+        1.0,
+        1.0,
+        1.0
+      ],
+      "eval_reference_length": 52663,
+      "eval_runtime": 589.2444,
+      "eval_samples_per_second": 4.771,
+      "eval_steps_per_second": 0.597,
+      "eval_translation_length": 52663,
+      "step": 1581
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 31620,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "total_flos": 1.7318198200762368e+16,
+  "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:cb48fdc1c4d2c2b6968feccddbbe4b6b4a3bd9d40b837b61c648facfca890857
+size 4664