Training in progress, epoch 8

checkpoint-1215/added_tokens.json

@@ -0,0 +1 @@
+{"<CSD>": 50265}

checkpoint-1215/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": "4.16.2",
+  "use_cache": false,
+  "vocab_size": 50266
+}

checkpoint-1215/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea16840959aff3a5aec7d0cdb152cfbb689d04ed2a27c1b401bd61984c0ba80a
+size 1115518581

checkpoint-1215/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28ecf1367d99bd7cf38647cf0e6aa0fa554b592253e98b60c85a4d15ac1a5e32
+size 557982265

checkpoint-1215/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:098a87a7f771dc71478f704a815de56e77c149560d17fd98cd2bd79ef12e388e
+size 14503

checkpoint-1215/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ee64f81e11fb4023ccce5a8bcfb0e976197229db0e4af837461055e0a9d041
+size 559

checkpoint-1215/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e8ecd5f11582254ff8261c1079e7303c245c2c8e70e2e4719aa35e66b723397
+size 623

checkpoint-1215/special_tokens_map.json

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

checkpoint-1215/tokenizer_config.json

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

checkpoint-1215/trainer_state.json

@@ -0,0 +1,142 @@
+{
+  "best_metric": 0.1867838054895401,
+  "best_model_checkpoint": "outputs/bart-base-detox/checkpoint-1080",
+  "epoch": 8.995391705069125,
+  "global_step": 1215,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 9e-06,
+      "loss": 0.5633,
+      "step": 135
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.25235414505004883,
+      "eval_runtime": 12.2006,
+      "eval_samples_per_second": 254.085,
+      "eval_steps_per_second": 31.802,
+      "step": 135
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.2589,
+      "step": 270
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.21927106380462646,
+      "eval_runtime": 11.2792,
+      "eval_samples_per_second": 274.842,
+      "eval_steps_per_second": 34.4,
+      "step": 270
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 7e-06,
+      "loss": 0.2307,
+      "step": 405
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.19929151237010956,
+      "eval_runtime": 11.2313,
+      "eval_samples_per_second": 276.016,
+      "eval_steps_per_second": 34.546,
+      "step": 405
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 6e-06,
+      "loss": 0.2171,
+      "step": 540
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.20016591250896454,
+      "eval_runtime": 11.0923,
+      "eval_samples_per_second": 279.473,
+      "eval_steps_per_second": 34.979,
+      "step": 540
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 5e-06,
+      "loss": 0.2027,
+      "step": 675
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.19366399943828583,
+      "eval_runtime": 11.2232,
+      "eval_samples_per_second": 276.213,
+      "eval_steps_per_second": 34.571,
+      "step": 675
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.1946,
+      "step": 810
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.19715721905231476,
+      "eval_runtime": 11.2739,
+      "eval_samples_per_second": 274.973,
+      "eval_steps_per_second": 34.416,
+      "step": 810
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 3e-06,
+      "loss": 0.1874,
+      "step": 945
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.19172348082065582,
+      "eval_runtime": 11.1804,
+      "eval_samples_per_second": 277.27,
+      "eval_steps_per_second": 34.704,
+      "step": 945
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.1853,
+      "step": 1080
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.1867838054895401,
+      "eval_runtime": 11.2543,
+      "eval_samples_per_second": 275.451,
+      "eval_steps_per_second": 34.476,
+      "step": 1080
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.1811,
+      "step": 1215
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.18896569311618805,
+      "eval_runtime": 11.6639,
+      "eval_samples_per_second": 265.777,
+      "eval_steps_per_second": 33.265,
+      "step": 1215
+    }
+  ],
+  "max_steps": 1350,
+  "num_train_epochs": 10,
+  "total_flos": 4836777327083520.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1215/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd8019ba81e4d8cd7e878f72b37c14bf5f28f7f6b5acd2cf343bb5ba08c77b6a
+size 3183

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e78009b7380a508eacef2c1224b4a5f4961b5d24f5b1661c820889dd44c2e817
+oid sha256:28ecf1367d99bd7cf38647cf0e6aa0fa554b592253e98b60c85a4d15ac1a5e32
 size 557982265