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": "4.33.3",
+  "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": "4.33.3"
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:388da872d82d8bf8f979834491f78ea4bd6dedff69427e6a7ba4a840cb1a4443
+size 1980859973

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:737b604d0989a476aaaf7bc51015c3d70d7a9fd676886411233581ce90937b6e
+size 990408885

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18aaadf79b8d01e8a6c0f3774222adc6e3df67df68c2dc1c4798fdded1a20f99
+size 14575

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4543d2ba62279450425b9794eeb0ad96fbe6e9679dc62caa4603df033dc6d61
+size 627

last-checkpoint/trainer_state.json

@@ -0,0 +1,122 @@
+{
+  "best_metric": 2.667262077331543,
+  "best_model_checkpoint": "dq158/morbius/checkpoint-7626",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 7626,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.967217414109625e-05,
+      "loss": 3.7107,
+      "step": 500
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.93443482821925e-05,
+      "loss": 3.3427,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.901652242328875e-05,
+      "loss": 3.2257,
+      "step": 1500
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.8688696564385e-05,
+      "loss": 3.2065,
+      "step": 2000
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.836087070548125e-05,
+      "loss": 3.0998,
+      "step": 2500
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.80330448465775e-05,
+      "loss": 3.0696,
+      "step": 3000
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 4.770521898767375e-05,
+      "loss": 3.0594,
+      "step": 3500
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.737739312877e-05,
+      "loss": 3.0052,
+      "step": 4000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.704956726986625e-05,
+      "loss": 2.9479,
+      "step": 4500
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 4.67217414109625e-05,
+      "loss": 2.911,
+      "step": 5000
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 4.639391555205875e-05,
+      "loss": 2.911,
+      "step": 5500
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 4.6066089693155e-05,
+      "loss": 2.8922,
+      "step": 6000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 4.573826383425125e-05,
+      "loss": 2.852,
+      "step": 6500
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 4.54104379753475e-05,
+      "loss": 2.9084,
+      "step": 7000
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 4.508261211644375e-05,
+      "loss": 2.8791,
+      "step": 7500
+    },
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 7.44762466804367,
+      "eval_loss": 2.667262077331543,
+      "eval_rouge1": 2.5782,
+      "eval_rouge2": 0.2276,
+      "eval_rougeL": 2.5795,
+      "eval_rougeLsum": 2.5803,
+      "eval_runtime": 426.361,
+      "eval_samples_per_second": 15.897,
+      "eval_steps_per_second": 1.989,
+      "step": 7626
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 76260,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 4.177088325668045e+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:c1b7eb9119e6b6970259bd4af693390a889e4f93631d18dc610ee909274db068
+size 4219