Training in progress, step 6000, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,74 @@
+{
+  "_name_or_path": "facebook/bart-large",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "num_beams": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "length_penalty": 1.0,
+      "max_length": 128,
+      "min_length": 12,
+      "num_beams": 4
+    },
+    "summarization_cnn": {
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "num_beams": 4
+    },
+    "summarization_xsum": {
+      "length_penalty": 1.0,
+      "max_length": 62,
+      "min_length": 11,
+      "num_beams": 6
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 50265
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,24 @@
+{
+  "bos_token_id": 0,
+  "clean_up_tokenization_spaces": true,
+  "decoder_start_token_id": 2,
+  "do_sample": true,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "max_new_tokens": 64,
+  "n_examples": null,
+  "no_repeat_ngram_size": 2,
+  "num_beams": 4,
+  "pad_to_max_length": true,
+  "pad_token_id": 2,
+  "padding": "max_length",
+  "renormalize_logits": true,
+  "skip_special_tokens": true,
+  "temperature": 0.85,
+  "top_k": 0,
+  "top_p": 0.9,
+  "transformers_version": "4.38.2",
+  "truncation": true
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c5270cae67729e5f72f64728aa1f1d7ac16d2fc18c36801678df98e971c37f0
+size 1625426996

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74f0a7cebd57bbb6d50e9cc12573df96fd09011c7a41f5cee6a7e1c1d0a07ff4
+size 3250759951

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0370dcb19078e64fd7d65e2ac922991c63ea528fbb1866fcb89c1963bfd98a4e
+size 14308

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dbd1e59f3ea5a942bc97d27cd582a370a35c87cc917c27bb1ca86d52f82aefc
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,201 @@
+{
+  "best_metric": 0.18144695460796356,
+  "best_model_checkpoint": "/content/drive/MyDrive/W210 Capstone - Lyric Generation with Melody/loaf/models/kwsylgen/bart/bart-finetuned-kwsylgen-64-simple_input_BARTlarge/checkpoint-6000",
+  "epoch": 2.1528525296017222,
+  "eval_steps": 500,
+  "global_step": 6000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.9277993440628052,
+      "learning_rate": 1.8815931108719056e-05,
+      "loss": 2.0641,
+      "step": 500
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 0.24505409598350525,
+      "eval_runtime": 128.1235,
+      "eval_samples_per_second": 184.845,
+      "eval_steps_per_second": 2.896,
+      "step": 500
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.0129226446151733,
+      "learning_rate": 1.7619901925606986e-05,
+      "loss": 0.2194,
+      "step": 1000
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 0.22281154990196228,
+      "eval_runtime": 128.9637,
+      "eval_samples_per_second": 183.641,
+      "eval_steps_per_second": 2.877,
+      "step": 1000
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.0302517414093018,
+      "learning_rate": 1.6423872742494916e-05,
+      "loss": 0.1989,
+      "step": 1500
+    },
+    {
+      "epoch": 0.54,
+      "eval_loss": 0.20858530700206757,
+      "eval_runtime": 129.0216,
+      "eval_samples_per_second": 183.558,
+      "eval_steps_per_second": 2.875,
+      "step": 1500
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 176.42080688476562,
+      "learning_rate": 1.5227843559382852e-05,
+      "loss": 0.1888,
+      "step": 2000
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 0.20265720784664154,
+      "eval_runtime": 129.0285,
+      "eval_samples_per_second": 183.549,
+      "eval_steps_per_second": 2.875,
+      "step": 2000
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.7003317475318909,
+      "learning_rate": 1.4031814376270783e-05,
+      "loss": 0.177,
+      "step": 2500
+    },
+    {
+      "epoch": 0.9,
+      "eval_loss": 0.19755715131759644,
+      "eval_runtime": 129.1437,
+      "eval_samples_per_second": 183.385,
+      "eval_steps_per_second": 2.873,
+      "step": 2500
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.9357886910438538,
+      "learning_rate": 1.2835785193158714e-05,
+      "loss": 0.1703,
+      "step": 3000
+    },
+    {
+      "epoch": 1.08,
+      "eval_loss": 0.19327057898044586,
+      "eval_runtime": 128.8805,
+      "eval_samples_per_second": 183.759,
+      "eval_steps_per_second": 2.879,
+      "step": 3000
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.7597601413726807,
+      "learning_rate": 1.1639756010046645e-05,
+      "loss": 0.1647,
+      "step": 3500
+    },
+    {
+      "epoch": 1.26,
+      "eval_loss": 0.19279009103775024,
+      "eval_runtime": 130.5884,
+      "eval_samples_per_second": 181.356,
+      "eval_steps_per_second": 2.841,
+      "step": 3500
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.7547380924224854,
+      "learning_rate": 1.0443726826934577e-05,
+      "loss": 0.159,
+      "step": 4000
+    },
+    {
+      "epoch": 1.44,
+      "eval_loss": 0.1890030950307846,
+      "eval_runtime": 130.7667,
+      "eval_samples_per_second": 181.109,
+      "eval_steps_per_second": 2.837,
+      "step": 4000
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 1.0234203338623047,
+      "learning_rate": 9.24769764382251e-06,
+      "loss": 0.1538,
+      "step": 4500
+    },
+    {
+      "epoch": 1.61,
+      "eval_loss": 0.18637944757938385,
+      "eval_runtime": 129.4971,
+      "eval_samples_per_second": 182.884,
+      "eval_steps_per_second": 2.865,
+      "step": 4500
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 0.8639469742774963,
+      "learning_rate": 8.051668460710443e-06,
+      "loss": 0.151,
+      "step": 5000
+    },
+    {
+      "epoch": 1.79,
+      "eval_loss": 0.18570180237293243,
+      "eval_runtime": 130.9952,
+      "eval_samples_per_second": 180.793,
+      "eval_steps_per_second": 2.832,
+      "step": 5000
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 1.0679283142089844,
+      "learning_rate": 6.855639277598374e-06,
+      "loss": 0.1471,
+      "step": 5500
+    },
+    {
+      "epoch": 1.97,
+      "eval_loss": 0.1828351765871048,
+      "eval_runtime": 130.7048,
+      "eval_samples_per_second": 181.195,
+      "eval_steps_per_second": 2.838,
+      "step": 5500
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 0.7938817143440247,
+      "learning_rate": 5.6596100944863066e-06,
+      "loss": 0.1436,
+      "step": 6000
+    },
+    {
+      "epoch": 2.15,
+      "eval_loss": 0.18144695460796356,
+      "eval_runtime": 129.7461,
+      "eval_samples_per_second": 182.533,
+      "eval_steps_per_second": 2.859,
+      "step": 6000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8361,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 5.20067180176343e+16,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c304f08edfed1a569691d5a0dd2d129c85a7d0647dd717e3bb46ccdb2338184
+size 5432