Training in progress, epoch 1

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "facebook/bart-base",
+  "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": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "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,
+  "normalize_embedding": true,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "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": "4.28.1",
+  "use_cache": true,
+  "vocab_size": 50265
+}

last-checkpoint/config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "facebook/bart-base",
+  "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": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "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,
+  "normalize_embedding": true,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "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": "4.28.1",
+  "use_cache": true,
+  "vocab_size": 50265
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.28.1"
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62af640d9257316aa7e0df1d54cc2ad0b08934ef57ffe1fdc3abf2b823297d68
+size 1115579397

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1c5289a63bf439de3568339bd081b734c56752900b28f5111ae7e395aabb087
+size 557971229

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac8fa45c1c9c80e32b4ab950e0fa6abb4c55eda437b8c409872ce7874a5a6455
+size 15597

last-checkpoint/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:786ba050f033778cbd2d0b326163925a6e269b1b789ffb02f138cfca2421065a
+size 557

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e395ed78ce282b12f543cf478f7b69637fa7676c695ce68991b12bea8178ef1f
+size 627

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,164 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 8004,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00019938030984507747,
+      "loss": 2.3666,
+      "step": 500
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00019875562218890554,
+      "loss": 2.2401,
+      "step": 1000
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00019813093453273364,
+      "loss": 2.2594,
+      "step": 1500
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00019750624687656172,
+      "loss": 2.188,
+      "step": 2000
+    },
+    {
+      "epoch": 0.25,
+      "eval_gen_len": 19.7309,
+      "eval_loss": 1.732377529144287,
+      "eval_rouge1": 1.8382,
+      "eval_rouge2": 1.4953,
+      "eval_rougeL": 1.7944,
+      "eval_rougeLsum": 1.8021,
+      "eval_runtime": 5362.1484,
+      "eval_samples_per_second": 7.462,
+      "eval_steps_per_second": 0.373,
+      "step": 2000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00019688155922038982,
+      "loss": 2.1778,
+      "step": 2500
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00019625812093953024,
+      "loss": 2.185,
+      "step": 3000
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00019563343328335832,
+      "loss": 2.1511,
+      "step": 3500
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00019500874562718642,
+      "loss": 2.1531,
+      "step": 4000
+    },
+    {
+      "epoch": 0.5,
+      "eval_gen_len": 19.7056,
+      "eval_loss": 1.7064495086669922,
+      "eval_rouge1": 1.6395,
+      "eval_rouge2": 1.3247,
+      "eval_rougeL": 1.6037,
+      "eval_rougeLsum": 1.6108,
+      "eval_runtime": 5328.3896,
+      "eval_samples_per_second": 7.51,
+      "eval_steps_per_second": 0.376,
+      "step": 4000
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00019438405797101452,
+      "loss": 2.192,
+      "step": 4500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0001937593703148426,
+      "loss": 2.1542,
+      "step": 5000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00019313468265867067,
+      "loss": 2.1115,
+      "step": 5500
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00019250999500249877,
+      "loss": 2.147,
+      "step": 6000
+    },
+    {
+      "epoch": 0.75,
+      "eval_gen_len": 19.4502,
+      "eval_loss": 1.7010632753372192,
+      "eval_rouge1": 1.3881,
+      "eval_rouge2": 1.1271,
+      "eval_rougeL": 1.3515,
+      "eval_rougeLsum": 1.3593,
+      "eval_runtime": 5340.8815,
+      "eval_samples_per_second": 7.492,
+      "eval_steps_per_second": 0.375,
+      "step": 6000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00019188530734632684,
+      "loss": 2.1467,
+      "step": 6500
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00019126061969015494,
+      "loss": 2.1084,
+      "step": 7000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.000190635932033983,
+      "loss": 2.1552,
+      "step": 7500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0001900112443778111,
+      "loss": 2.1152,
+      "step": 8000
+    },
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 19.6288,
+      "eval_loss": 1.692185401916504,
+      "eval_rouge1": 1.4518,
+      "eval_rouge2": 1.1955,
+      "eval_rougeL": 1.4252,
+      "eval_rougeLsum": 1.4308,
+      "eval_runtime": 5347.9231,
+      "eval_samples_per_second": 7.482,
+      "eval_steps_per_second": 0.374,
+      "step": 8000
+    }
+  ],
+  "max_steps": 160080,
+  "num_train_epochs": 20,
+  "total_flos": 9.756207646488576e+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 sha256:7110166d952c969185f8550fd2df2892ce3dd876f742b4e7ff7738f01183fd80
+size 3771

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1c5289a63bf439de3568339bd081b734c56752900b28f5111ae7e395aabb087
+size 557971229

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7110166d952c969185f8550fd2df2892ce3dd876f742b4e7ff7738f01183fd80
+size 3771