Training in progress, epoch 2

checkpoint-405/added_tokens.json

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

checkpoint-405/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-405/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e77c8a2a5fad17d46427af1d8a570e4d5fd98c6b9ed138860d70a3bfe45c497a
+size 1115518581

checkpoint-405/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b214a195ba865a570b4c0ca7858a07d3cdf972c6a40b69118e204806f82334d3
+size 557982265

checkpoint-405/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:875d98419989fd9f35e5ee62e99d0916b3a83d7831ab9c82bfe7932e0fbcce39
+size 14503

checkpoint-405/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ffa040a21ec017e5ea54c9032cf626519fb2b7b7f3a6115d289bd42d3f21a66
+size 559

checkpoint-405/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:361b412c6099209dd7c32c3cf59809aa5d7b27574edb1597b9b27827ea576a15
+size 623

checkpoint-405/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-405/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-405/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": 0.1801992505788803,
+  "best_model_checkpoint": "outputs/bart-base-detox/checkpoint-405",
+  "epoch": 2.9953917050691246,
+  "global_step": 405,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 9e-05,
+      "loss": 0.3171,
+      "step": 135
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.20179320871829987,
+      "eval_runtime": 11.3072,
+      "eval_samples_per_second": 274.16,
+      "eval_steps_per_second": 34.314,
+      "step": 135
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 8e-05,
+      "loss": 0.1852,
+      "step": 270
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.18728719651699066,
+      "eval_runtime": 11.1563,
+      "eval_samples_per_second": 277.869,
+      "eval_steps_per_second": 34.778,
+      "step": 270
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 7e-05,
+      "loss": 0.1559,
+      "step": 405
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.1801992505788803,
+      "eval_runtime": 11.3199,
+      "eval_samples_per_second": 273.853,
+      "eval_steps_per_second": 34.276,
+      "step": 405
+    }
+  ],
+  "max_steps": 1350,
+  "num_train_epochs": 10,
+  "total_flos": 1612929183989760.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-405/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6779c0d7bfc5cc8b7f502411db449902ffdb3fd6d5cc4758f90defaa037cdfa
+size 3183

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cda356bb2460d5eb07d886f9da9cae5d5a5e81b62d6724fcbbed4dcb5ea98aa
+oid sha256:b214a195ba865a570b4c0ca7858a07d3cdf972c6a40b69118e204806f82334d3
 size 557982265