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:e69e042d6d3b03ddc75479575c7ca868bdd7547b2bf1e1a2cb7f3c3cb28f5d85
+size 615849402

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0010023a4997d0eaa9bb8effc8302b045d55300a866c3e4bcbdbb449cd2b2355
+size 307910594

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6408fb68f7dcfd8a9d8a2dca2b8fb472869857e97938d60fbd2ee9fd8b06fb74
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0faf156c918035c928b7e66ac5b836f532647c6fbaa9924493f4d76f9cc0dbf
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,32 @@
+{
+  "best_metric": 3.9618124961853027,
+  "best_model_checkpoint": "flanT5-description-generation/checkpoint-99",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 99,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 2.5583756345177666,
+      "eval_loss": 3.9618124961853027,
+      "eval_rouge1": 7.0636,
+      "eval_rouge2": 6.3199,
+      "eval_rougeL": 6.6804,
+      "eval_rougeLsum": 6.6812,
+      "eval_runtime": 21.3435,
+      "eval_samples_per_second": 9.23,
+      "eval_steps_per_second": 1.171,
+      "step": 99
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 495,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 146295827202048.0,
+  "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:b898256e70cabf1cfb831d10e14b3ad5a1047518f81856de61aca7d2414a7ace
+size 4728