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 sha256:77ee03a1d0311a29793f120677b5bfc69e1e8781bc96853c8e9c88c8166c16e4
+size 1115579397

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64abc4de3991cbdfd5ff0c316e2fac01273b5b67804a7c101f49a609279180f1
+size 557971229

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a45b7b77b12af6e89720c582cf4778d8f486d6946f3e82947292c4d5038406f7
+size 15597

last-checkpoint/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03c25bfe5cf11a212342871a1fefb1e71d639bd1297dd40b8d896a9d5808de6b
+size 557

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0801195a6d147316da17a810626a833a27ae6da4b2ee1058dbb32488537477c
+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 +1,108 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 5534,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00019550957715937838,
+      "loss": 2.3378,
+      "step": 500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0001910010842067221,
+      "loss": 2.1947,
+      "step": 1000
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00018648355619804843,
+      "loss": 2.2007,
+      "step": 1500
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00018196602818937478,
+      "loss": 2.1432,
+      "step": 2000
+    },
+    {
+      "epoch": 0.36,
+      "eval_gen_len": 19.3746,
+      "eval_loss": 1.6908528804779053,
+      "eval_rouge1": 1.4992,
+      "eval_rouge2": 1.2323,
+      "eval_rougeL": 1.4723,
+      "eval_rougeLsum": 1.4796,
+      "eval_runtime": 3876.1085,
+      "eval_samples_per_second": 7.137,
+      "eval_steps_per_second": 0.357,
+      "step": 2000
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00017744850018070114,
+      "loss": 2.1445,
+      "step": 2500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00017293097217202746,
+      "loss": 2.1092,
+      "step": 3000
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00016842247921937118,
+      "loss": 2.1179,
+      "step": 3500
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0001639049512106975,
+      "loss": 2.0722,
+      "step": 4000
+    },
+    {
+      "epoch": 0.72,
+      "eval_gen_len": 19.5628,
+      "eval_loss": 1.6098366975784302,
+      "eval_rouge1": 1.6384,
+      "eval_rouge2": 1.3622,
+      "eval_rougeL": 1.6052,
+      "eval_rougeLsum": 1.614,
+      "eval_runtime": 3853.4353,
+      "eval_samples_per_second": 7.179,
+      "eval_steps_per_second": 0.359,
+      "step": 4000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00015938742320202386,
+      "loss": 2.0354,
+      "step": 4500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0001548698951933502,
+      "loss": 2.0153,
+      "step": 5000
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00015035236718467654,
+      "loss": 2.0776,
+      "step": 5500
+    }
+  ],
+  "max_steps": 22136,
+  "num_train_epochs": 4,
+  "total_flos": 6.744738452594688e+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 sha256:401f426af52bf66ad8eb84ab09e8bf854484742ea37fc35a06bc40ef7a256fe5
+size 3771

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64abc4de3991cbdfd5ff0c316e2fac01273b5b67804a7c101f49a609279180f1
+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 sha256:401f426af52bf66ad8eb84ab09e8bf854484742ea37fc35a06bc40ef7a256fe5
+size 3771