Training in progress, epoch 6, checkpoint

checkpoint-2604/config.json

@@ -0,0 +1,73 @@
+{
+  "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": null,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "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": null,
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_beams": null,
+  "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": "4.53.2",
+  "use_cache": true,
+  "vocab_size": 50265
+}

checkpoint-2604/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": "4.53.2"
+}

checkpoint-2604/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb364ba3a81e6d6b7e7502f33e4302a090c65138d8883980e7edc2d05a076270
+size 557912620

checkpoint-2604/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6de0378013aff3173011b73ea1423b460d0f7d56258e66e36f5954b8f616238
+size 1115579898

checkpoint-2604/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dc6df431e7f5f976573ed400d7b0c241a355e0df0f3f4f2f8199aaf5584775a
+size 14244

checkpoint-2604/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50be94514da39e154e1a7bfecbf664ec70bb10c16adf524003780a3d2c1d5cd9
+size 988

checkpoint-2604/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f650d84fccfee72305992918296b6fe19cd08fb93f0627ba4a737fcde578bcca
+size 1064

checkpoint-2604/special_tokens_map.json

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

checkpoint-2604/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

checkpoint-2604/trainer_state.json

@@ -0,0 +1,123 @@
+{
+  "best_global_step": 1736,
+  "best_metric": 0.027611982077360153,
+  "best_model_checkpoint": "coedit-gec-output/checkpoint-1736",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 2604,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_gleu": 0.5903191424034809,
+      "eval_loss": 0.05094386264681816,
+      "eval_runtime": 274.5123,
+      "eval_samples_per_second": 21.664,
+      "eval_steps_per_second": 1.355,
+      "step": 434
+    },
+    {
+      "epoch": 1.1520737327188941,
+      "grad_norm": 2.6467134952545166,
+      "learning_rate": 1.707373271889401e-05,
+      "loss": 4.5342,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_gleu": 0.6136322248136682,
+      "eval_loss": 0.02894793264567852,
+      "eval_runtime": 275.4106,
+      "eval_samples_per_second": 21.593,
+      "eval_steps_per_second": 1.351,
+      "step": 868
+    },
+    {
+      "epoch": 2.3041474654377883,
+      "grad_norm": 0.17931102216243744,
+      "learning_rate": 2.998074760756579e-05,
+      "loss": 0.0337,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_gleu": 0.6180397543384626,
+      "eval_loss": 0.028022393584251404,
+      "eval_runtime": 273.5891,
+      "eval_samples_per_second": 21.737,
+      "eval_steps_per_second": 1.36,
+      "step": 1302
+    },
+    {
+      "epoch": 3.456221198156682,
+      "grad_norm": 0.14635759592056274,
+      "learning_rate": 2.9527185981891282e-05,
+      "loss": 0.0252,
+      "step": 1500
+    },
+    {
+      "epoch": 4.0,
+      "eval_gleu": 0.6192281963833357,
+      "eval_loss": 0.027611982077360153,
+      "eval_runtime": 273.2697,
+      "eval_samples_per_second": 21.762,
+      "eval_steps_per_second": 1.361,
+      "step": 1736
+    },
+    {
+      "epoch": 4.6082949308755765,
+      "grad_norm": 0.17265909910202026,
+      "learning_rate": 2.848825088217165e-05,
+      "loss": 0.0198,
+      "step": 2000
+    },
+    {
+      "epoch": 5.0,
+      "eval_gleu": 0.6200457559492605,
+      "eval_loss": 0.0288274884223938,
+      "eval_runtime": 272.9767,
+      "eval_samples_per_second": 21.786,
+      "eval_steps_per_second": 1.363,
+      "step": 2170
+    },
+    {
+      "epoch": 5.76036866359447,
+      "grad_norm": 0.1576840579509735,
+      "learning_rate": 2.690580623507435e-05,
+      "loss": 0.0156,
+      "step": 2500
+    },
+    {
+      "epoch": 6.0,
+      "eval_gleu": 0.6213319360800468,
+      "eval_loss": 0.029072603210806847,
+      "eval_runtime": 275.004,
+      "eval_samples_per_second": 21.625,
+      "eval_steps_per_second": 1.353,
+      "step": 2604
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8680,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.269105464180736e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2604/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d51ec6039a1aa7054aa2a4358d5c699e1f6e9437c5b2866be8d6da93dff8ceb
+size 5560