Training in progress, step 500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f63de6b452244fcd86ba168d9250529c4b9dd34587098ff5ff9e98d94046ff95
+oid sha256:13588ccaca7863933ec8339195f9f63fde9751d81648643a441823588be97d2b
 size 560837164

runs/Jan24_19-31-27_william-gpu-3090-10-8vlnc/events.out.tfevents.1706124688.william-gpu-3090-10-8vlnc.4125.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44ecf8202a5876fec5fd107f6b2e338f7837bfb1d2b15aa799b457d309932130
-size 14488
+oid sha256:0f2283067947411da78f3146d700d05c23a931616f510cddc2f42e8a86d67ca0
+size 15695

runs/Jan24_20-07-13_william-gpu-3090-10-8vlnc/events.out.tfevents.1706126835.william-gpu-3090-10-8vlnc.4362.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bda0bd8c5c851d769c859d73f9b890378407891f1ce61afff79b7d3df8729a1
+size 6407

tmp-checkpoint-5000/config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "GanjinZero/biobart-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_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_length": 256,
+  "max_position_embeddings": 1500,
+  "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": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 50265
+}

tmp-checkpoint-5000/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "max_length": 256,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.36.2"
+}

tmp-checkpoint-5000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2d66fab2834e74b4cd13d35b2cfcad39d0308cb263884004288bda37df8c53c
+size 560837164

tmp-checkpoint-5000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43f8314bc414d836f6f1805d0fa0b07dd1540077459979bfdd6e57c3149e0ab4
+size 1121426543

tmp-checkpoint-5000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3a969f69ace2a9fde6bc6a6c6a4d8cb016999f22fc9568d6f8b45381cc6b53d
+size 14503

tmp-checkpoint-5000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3150b7c15891230da7b0f4bb1993e9da93664827e9fb35fc57ca9e26eb3fb9de
+size 623

tmp-checkpoint-5000/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tmp-checkpoint-5000/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BartTokenizer",
+  "unk_token": "<unk>"
+}

tmp-checkpoint-5000/trainer_state.json

@@ -0,0 +1,289 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 16.611295681063122,
+  "eval_steps": 500,
+  "global_step": 5000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 7.59,
+      "eval_loss": 2.54074764251709,
+      "eval_rouge1": 0.0058,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0055,
+      "eval_rougeLsum": 0.0054,
+      "eval_runtime": 8.576,
+      "eval_samples_per_second": 11.66,
+      "eval_steps_per_second": 2.915,
+      "step": 301
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 8.305647840531562e-05,
+      "loss": 5.2836,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 52.76,
+      "eval_loss": 1.0132805109024048,
+      "eval_rouge1": 0.1011,
+      "eval_rouge2": 0.0238,
+      "eval_rougeL": 0.0761,
+      "eval_rougeLsum": 0.0751,
+      "eval_runtime": 45.9141,
+      "eval_samples_per_second": 2.178,
+      "eval_steps_per_second": 0.544,
+      "step": 602
+    },
+    {
+      "epoch": 3.0,
+      "eval_gen_len": 9.85,
+      "eval_loss": 0.923646867275238,
+      "eval_rouge1": 0.0549,
+      "eval_rouge2": 0.0088,
+      "eval_rougeL": 0.052,
+      "eval_rougeLsum": 0.0518,
+      "eval_runtime": 15.2679,
+      "eval_samples_per_second": 6.55,
+      "eval_steps_per_second": 1.637,
+      "step": 903
+    },
+    {
+      "epoch": 3.32,
+      "learning_rate": 9.265411590992987e-05,
+      "loss": 0.9572,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_gen_len": 24.49,
+      "eval_loss": 0.8768377900123596,
+      "eval_rouge1": 0.0825,
+      "eval_rouge2": 0.0209,
+      "eval_rougeL": 0.0586,
+      "eval_rougeLsum": 0.058,
+      "eval_runtime": 18.7194,
+      "eval_samples_per_second": 5.342,
+      "eval_steps_per_second": 1.336,
+      "step": 1204
+    },
+    {
+      "epoch": 4.98,
+      "learning_rate": 8.342561830933924e-05,
+      "loss": 0.7658,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_gen_len": 26.0,
+      "eval_loss": 0.8518986701965332,
+      "eval_rouge1": 0.1302,
+      "eval_rouge2": 0.0282,
+      "eval_rougeL": 0.1024,
+      "eval_rougeLsum": 0.1023,
+      "eval_runtime": 18.4105,
+      "eval_samples_per_second": 5.432,
+      "eval_steps_per_second": 1.358,
+      "step": 1505
+    },
+    {
+      "epoch": 6.0,
+      "eval_gen_len": 45.62,
+      "eval_loss": 0.8450735211372375,
+      "eval_rouge1": 0.1689,
+      "eval_rouge2": 0.0362,
+      "eval_rougeL": 0.134,
+      "eval_rougeLsum": 0.1345,
+      "eval_runtime": 26.7906,
+      "eval_samples_per_second": 3.733,
+      "eval_steps_per_second": 0.933,
+      "step": 1806
+    },
+    {
+      "epoch": 6.64,
+      "learning_rate": 7.419712070874863e-05,
+      "loss": 0.5785,
+      "step": 2000
+    },
+    {
+      "epoch": 7.0,
+      "eval_gen_len": 38.25,
+      "eval_loss": 0.8455685377120972,
+      "eval_rouge1": 0.1548,
+      "eval_rouge2": 0.0338,
+      "eval_rougeL": 0.121,
+      "eval_rougeLsum": 0.12,
+      "eval_runtime": 22.2546,
+      "eval_samples_per_second": 4.493,
+      "eval_steps_per_second": 1.123,
+      "step": 2107
+    },
+    {
+      "epoch": 8.0,
+      "eval_gen_len": 29.5,
+      "eval_loss": 0.8484403491020203,
+      "eval_rouge1": 0.1394,
+      "eval_rouge2": 0.0365,
+      "eval_rougeL": 0.1093,
+      "eval_rougeLsum": 0.1095,
+      "eval_runtime": 19.9659,
+      "eval_samples_per_second": 5.009,
+      "eval_steps_per_second": 1.252,
+      "step": 2408
+    },
+    {
+      "epoch": 8.31,
+      "learning_rate": 6.4968623108158e-05,
+      "loss": 0.4638,
+      "step": 2500
+    },
+    {
+      "epoch": 9.0,
+      "eval_gen_len": 32.69,
+      "eval_loss": 0.8562068343162537,
+      "eval_rouge1": 0.1665,
+      "eval_rouge2": 0.0483,
+      "eval_rougeL": 0.13,
+      "eval_rougeLsum": 0.1299,
+      "eval_runtime": 21.4271,
+      "eval_samples_per_second": 4.667,
+      "eval_steps_per_second": 1.167,
+      "step": 2709
+    },
+    {
+      "epoch": 9.97,
+      "learning_rate": 5.574012550756738e-05,
+      "loss": 0.359,
+      "step": 3000
+    },
+    {
+      "epoch": 10.0,
+      "eval_gen_len": 25.89,
+      "eval_loss": 0.878343403339386,
+      "eval_rouge1": 0.1471,
+      "eval_rouge2": 0.0421,
+      "eval_rougeL": 0.1211,
+      "eval_rougeLsum": 0.1192,
+      "eval_runtime": 17.1365,
+      "eval_samples_per_second": 5.836,
+      "eval_steps_per_second": 1.459,
+      "step": 3010
+    },
+    {
+      "epoch": 11.0,
+      "eval_gen_len": 32.17,
+      "eval_loss": 0.874755322933197,
+      "eval_rouge1": 0.1564,
+      "eval_rouge2": 0.0363,
+      "eval_rougeL": 0.1208,
+      "eval_rougeLsum": 0.1183,
+      "eval_runtime": 19.0439,
+      "eval_samples_per_second": 5.251,
+      "eval_steps_per_second": 1.313,
+      "step": 3311
+    },
+    {
+      "epoch": 11.63,
+      "learning_rate": 4.651162790697675e-05,
+      "loss": 0.2639,
+      "step": 3500
+    },
+    {
+      "epoch": 12.0,
+      "eval_gen_len": 39.23,
+      "eval_loss": 0.8847034573554993,
+      "eval_rouge1": 0.1727,
+      "eval_rouge2": 0.0524,
+      "eval_rougeL": 0.1349,
+      "eval_rougeLsum": 0.1347,
+      "eval_runtime": 23.6964,
+      "eval_samples_per_second": 4.22,
+      "eval_steps_per_second": 1.055,
+      "step": 3612
+    },
+    {
+      "epoch": 13.0,
+      "eval_gen_len": 41.93,
+      "eval_loss": 0.8969386219978333,
+      "eval_rouge1": 0.156,
+      "eval_rouge2": 0.0349,
+      "eval_rougeL": 0.1209,
+      "eval_rougeLsum": 0.1204,
+      "eval_runtime": 24.7305,
+      "eval_samples_per_second": 4.044,
+      "eval_steps_per_second": 1.011,
+      "step": 3913
+    },
+    {
+      "epoch": 13.29,
+      "learning_rate": 3.728313030638612e-05,
+      "loss": 0.1897,
+      "step": 4000
+    },
+    {
+      "epoch": 14.0,
+      "eval_gen_len": 38.77,
+      "eval_loss": 0.9095367193222046,
+      "eval_rouge1": 0.1606,
+      "eval_rouge2": 0.0457,
+      "eval_rougeL": 0.1237,
+      "eval_rougeLsum": 0.1237,
+      "eval_runtime": 22.2241,
+      "eval_samples_per_second": 4.5,
+      "eval_steps_per_second": 1.125,
+      "step": 4214
+    },
+    {
+      "epoch": 14.95,
+      "learning_rate": 2.8054632705795497e-05,
+      "loss": 0.1431,
+      "step": 4500
+    },
+    {
+      "epoch": 15.0,
+      "eval_gen_len": 31.47,
+      "eval_loss": 0.9321858882904053,
+      "eval_rouge1": 0.1326,
+      "eval_rouge2": 0.0355,
+      "eval_rougeL": 0.0999,
+      "eval_rougeLsum": 0.0999,
+      "eval_runtime": 18.5828,
+      "eval_samples_per_second": 5.381,
+      "eval_steps_per_second": 1.345,
+      "step": 4515
+    },
+    {
+      "epoch": 16.0,
+      "eval_gen_len": 38.33,
+      "eval_loss": 0.9329277276992798,
+      "eval_rouge1": 0.1574,
+      "eval_rouge2": 0.0436,
+      "eval_rougeL": 0.1197,
+      "eval_rougeLsum": 0.1196,
+      "eval_runtime": 23.3814,
+      "eval_samples_per_second": 4.277,
+      "eval_steps_per_second": 1.069,
+      "step": 4816
+    },
+    {
+      "epoch": 16.61,
+      "learning_rate": 1.882613510520487e-05,
+      "loss": 0.0998,
+      "step": 5000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6020,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "total_flos": 1.782050070528e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

tmp-checkpoint-5000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f72711b887cbed0cffe0244e68691c5b1fa4c683b86522656866bfd1bc7d5d60
+size 4463

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f72711b887cbed0cffe0244e68691c5b1fa4c683b86522656866bfd1bc7d5d60
+oid sha256:47e72807479ad7a934ee17b52d43f1c0c409dfed1616f888d3a719f361abefbf
 size 4463