Riyagarg01 commited on Mar 15, 2022

Commit

9e1ba1b

1 Parent(s): 2fd939c

new_model

Browse files

Files changed (36) hide show

checkpoint-1000/config.json +74 -0
checkpoint-1000/merges.txt +0 -0
checkpoint-1000/optimizer.pt +3 -0
checkpoint-1000/pytorch_model.bin +3 -0
checkpoint-1000/rng_state.pth +3 -0
checkpoint-1000/scheduler.pt +3 -0
checkpoint-1000/special_tokens_map.json +1 -0
checkpoint-1000/tokenizer.json +0 -0
checkpoint-1000/tokenizer_config.json +1 -0
checkpoint-1000/trainer_state.json +136 -0
checkpoint-1000/training_args.bin +3 -0
checkpoint-1000/vocab.json +0 -0
checkpoint-1500/config.json +74 -0
checkpoint-1500/merges.txt +0 -0
checkpoint-1500/optimizer.pt +3 -0
checkpoint-1500/pytorch_model.bin +3 -0
checkpoint-1500/rng_state.pth +3 -0
checkpoint-1500/scheduler.pt +3 -0
checkpoint-1500/special_tokens_map.json +1 -0
checkpoint-1500/tokenizer.json +0 -0
checkpoint-1500/tokenizer_config.json +1 -0
checkpoint-1500/trainer_state.json +196 -0
checkpoint-1500/training_args.bin +3 -0
checkpoint-1500/vocab.json +0 -0
checkpoint-500/config.json +74 -0
checkpoint-500/merges.txt +0 -0
checkpoint-500/optimizer.pt +3 -0
checkpoint-500/pytorch_model.bin +3 -0
checkpoint-500/rng_state.pth +3 -0
checkpoint-500/scheduler.pt +3 -0
checkpoint-500/special_tokens_map.json +1 -0
checkpoint-500/tokenizer.json +0 -0
checkpoint-500/tokenizer_config.json +1 -0
checkpoint-500/trainer_state.json +76 -0
checkpoint-500/training_args.bin +3 -0
checkpoint-500/vocab.json +0 -0

checkpoint-1000/config.json ADDED Viewed

	@@ -0,0 +1,74 @@

+{
+  "_name_or_path": "mse30/bart-base-finetuned-pubmed",
+  "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_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": "4.17.0",
+  "use_cache": true,
+  "vocab_size": 50265
+}

checkpoint-1000/merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

checkpoint-1000/optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:0b8cfafa39ac38e112f0e47f6e10e5715f33a7d2e2321cdd648c557d1f2a0fe8
+size 1115513717

checkpoint-1000/pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:06606d8c1bcbc08c0559d4d3283c6dd0cc8322cc12af915710b05710b7a48e54
+size 557979897

checkpoint-1000/rng_state.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:2a2df309f482fd9b6718ea5f7a379f2572ca4146bc60917d0cb524901ad6340d
+size 14503

checkpoint-1000/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:68d410523f251cf725752066d62278717bc8809b054410a3cb0cdd9748ddec5a
+size 623

checkpoint-1000/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1 @@


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-1000/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

checkpoint-1000/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "mse30/bart-base-finetuned-pubmed", "tokenizer_class": "BartTokenizer"}

checkpoint-1000/trainer_state.json ADDED Viewed

	@@ -0,0 +1,136 @@

+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 55.55555555555556,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.78,
+      "learning_rate": 3e-06,
+      "loss": 8.2937,
+      "step": 50
+    },
+    {
+      "epoch": 5.56,
+      "learning_rate": 6e-06,
+      "loss": 4.7562,
+      "step": 100
+    },
+    {
+      "epoch": 8.33,
+      "learning_rate": 9e-06,
+      "loss": 3.0858,
+      "step": 150
+    },
+    {
+      "epoch": 11.11,
+      "learning_rate": 1.2e-05,
+      "loss": 2.4515,
+      "step": 200
+    },
+    {
+      "epoch": 13.89,
+      "learning_rate": 1.5e-05,
+      "loss": 2.1723,
+      "step": 250
+    },
+    {
+      "epoch": 16.67,
+      "learning_rate": 1.8e-05,
+      "loss": 1.981,
+      "step": 300
+    },
+    {
+      "epoch": 19.44,
+      "learning_rate": 2.1e-05,
+      "loss": 1.8522,
+      "step": 350
+    },
+    {
+      "epoch": 22.22,
+      "learning_rate": 2.4e-05,
+      "loss": 1.7612,
+      "step": 400
+    },
+    {
+      "epoch": 25.0,
+      "learning_rate": 2.7000000000000002e-05,
+      "loss": 1.7039,
+      "step": 450
+    },
+    {
+      "epoch": 27.78,
+      "learning_rate": 3e-05,
+      "loss": 1.6461,
+      "step": 500
+    },
+    {
+      "epoch": 30.56,
+      "learning_rate": 2.884615384615385e-05,
+      "loss": 1.6101,
+      "step": 550
+    },
+    {
+      "epoch": 33.33,
+      "learning_rate": 2.7692307692307694e-05,
+      "loss": 1.5799,
+      "step": 600
+    },
+    {
+      "epoch": 36.11,
+      "learning_rate": 2.6538461538461538e-05,
+      "loss": 1.56,
+      "step": 650
+    },
+    {
+      "epoch": 38.89,
+      "learning_rate": 2.5384615384615386e-05,
+      "loss": 1.5541,
+      "step": 700
+    },
+    {
+      "epoch": 41.67,
+      "learning_rate": 2.423076923076923e-05,
+      "loss": 1.5313,
+      "step": 750
+    },
+    {
+      "epoch": 44.44,
+      "learning_rate": 2.307692307692308e-05,
+      "loss": 1.5195,
+      "step": 800
+    },
+    {
+      "epoch": 47.22,
+      "learning_rate": 2.1923076923076924e-05,
+      "loss": 1.5154,
+      "step": 850
+    },
+    {
+      "epoch": 50.0,
+      "learning_rate": 2.076923076923077e-05,
+      "loss": 1.5126,
+      "step": 900
+    },
+    {
+      "epoch": 52.78,
+      "learning_rate": 1.9615384615384617e-05,
+      "loss": 1.5006,
+      "step": 950
+    },
+    {
+      "epoch": 55.56,
+      "learning_rate": 1.8461538461538465e-05,
+      "loss": 1.495,
+      "step": 1000
+    }
+  ],
+  "max_steps": 1800,
+  "num_train_epochs": 100,
+  "total_flos": 2438945832960000.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:79be1103501cc9c7c2bd1cb54516e648bec56b102558206f93a993dec74ff629
+size 3119

checkpoint-1000/vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff

checkpoint-1500/config.json ADDED Viewed

	@@ -0,0 +1,74 @@

+{
+  "_name_or_path": "mse30/bart-base-finetuned-pubmed",
+  "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_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": "4.17.0",
+  "use_cache": true,
+  "vocab_size": 50265
+}

checkpoint-1500/merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

checkpoint-1500/optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f70e17f579160d38f624bb64990acaf678f4ea10a714e3c134ca9828f572cfd1
+size 1115513717

checkpoint-1500/pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:bc04e068fbf64b5eed44305accdc655e472422de349b360c73c414654123ca5d
+size 557979897

checkpoint-1500/rng_state.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:35362d235f07727b526048e593b2be5c1c69da0b9e2b0ba70b7cee63ba1629cb
+size 14503

checkpoint-1500/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:71526034486315201e2f78db026a658970e090dee17689d5d3c5cd4410424f57
+size 623

checkpoint-1500/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1 @@


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-1500/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

checkpoint-1500/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "mse30/bart-base-finetuned-pubmed", "tokenizer_class": "BartTokenizer"}

checkpoint-1500/trainer_state.json ADDED Viewed

	@@ -0,0 +1,196 @@

+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 83.33333333333333,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.78,
+      "learning_rate": 3e-06,
+      "loss": 8.2937,
+      "step": 50
+    },
+    {
+      "epoch": 5.56,
+      "learning_rate": 6e-06,
+      "loss": 4.7562,
+      "step": 100
+    },
+    {
+      "epoch": 8.33,
+      "learning_rate": 9e-06,
+      "loss": 3.0858,
+      "step": 150
+    },
+    {
+      "epoch": 11.11,
+      "learning_rate": 1.2e-05,
+      "loss": 2.4515,
+      "step": 200
+    },
+    {
+      "epoch": 13.89,
+      "learning_rate": 1.5e-05,
+      "loss": 2.1723,
+      "step": 250
+    },
+    {
+      "epoch": 16.67,
+      "learning_rate": 1.8e-05,
+      "loss": 1.981,
+      "step": 300
+    },
+    {
+      "epoch": 19.44,
+      "learning_rate": 2.1e-05,
+      "loss": 1.8522,
+      "step": 350
+    },
+    {
+      "epoch": 22.22,
+      "learning_rate": 2.4e-05,
+      "loss": 1.7612,
+      "step": 400
+    },
+    {
+      "epoch": 25.0,
+      "learning_rate": 2.7000000000000002e-05,
+      "loss": 1.7039,
+      "step": 450
+    },
+    {
+      "epoch": 27.78,
+      "learning_rate": 3e-05,
+      "loss": 1.6461,
+      "step": 500
+    },
+    {
+      "epoch": 30.56,
+      "learning_rate": 2.884615384615385e-05,
+      "loss": 1.6101,
+      "step": 550
+    },
+    {
+      "epoch": 33.33,
+      "learning_rate": 2.7692307692307694e-05,
+      "loss": 1.5799,
+      "step": 600
+    },
+    {
+      "epoch": 36.11,
+      "learning_rate": 2.6538461538461538e-05,
+      "loss": 1.56,
+      "step": 650
+    },
+    {
+      "epoch": 38.89,
+      "learning_rate": 2.5384615384615386e-05,
+      "loss": 1.5541,
+      "step": 700
+    },
+    {
+      "epoch": 41.67,
+      "learning_rate": 2.423076923076923e-05,
+      "loss": 1.5313,
+      "step": 750
+    },
+    {
+      "epoch": 44.44,
+      "learning_rate": 2.307692307692308e-05,
+      "loss": 1.5195,
+      "step": 800
+    },
+    {
+      "epoch": 47.22,
+      "learning_rate": 2.1923076923076924e-05,
+      "loss": 1.5154,
+      "step": 850
+    },
+    {
+      "epoch": 50.0,
+      "learning_rate": 2.076923076923077e-05,
+      "loss": 1.5126,
+      "step": 900
+    },
+    {
+      "epoch": 52.78,
+      "learning_rate": 1.9615384615384617e-05,
+      "loss": 1.5006,
+      "step": 950
+    },
+    {
+      "epoch": 55.56,
+      "learning_rate": 1.8461538461538465e-05,
+      "loss": 1.495,
+      "step": 1000
+    },
+    {
+      "epoch": 58.33,
+      "learning_rate": 1.7307692307692306e-05,
+      "loss": 1.49,
+      "step": 1050
+    },
+    {
+      "epoch": 61.11,
+      "learning_rate": 1.6153846153846154e-05,
+      "loss": 1.4854,
+      "step": 1100
+    },
+    {
+      "epoch": 63.89,
+      "learning_rate": 1.5e-05,
+      "loss": 1.4836,
+      "step": 1150
+    },
+    {
+      "epoch": 66.67,
+      "learning_rate": 1.3846153846153847e-05,
+      "loss": 1.4796,
+      "step": 1200
+    },
+    {
+      "epoch": 69.44,
+      "learning_rate": 1.2692307692307693e-05,
+      "loss": 1.4768,
+      "step": 1250
+    },
+    {
+      "epoch": 72.22,
+      "learning_rate": 1.153846153846154e-05,
+      "loss": 1.477,
+      "step": 1300
+    },
+    {
+      "epoch": 75.0,
+      "learning_rate": 1.0384615384615384e-05,
+      "loss": 1.4762,
+      "step": 1350
+    },
+    {
+      "epoch": 77.78,
+      "learning_rate": 9.230769230769232e-06,
+      "loss": 1.469,
+      "step": 1400
+    },
+    {
+      "epoch": 80.56,
+      "learning_rate": 8.076923076923077e-06,
+      "loss": 1.4677,
+      "step": 1450
+    },
+    {
+      "epoch": 83.33,
+      "learning_rate": 6.923076923076923e-06,
+      "loss": 1.4692,
+      "step": 1500
+    }
+  ],
+  "max_steps": 1800,
+  "num_train_epochs": 100,
+  "total_flos": 3658418749440000.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1500/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:79be1103501cc9c7c2bd1cb54516e648bec56b102558206f93a993dec74ff629
+size 3119

checkpoint-1500/vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff

checkpoint-500/config.json ADDED Viewed

	@@ -0,0 +1,74 @@

+{
+  "_name_or_path": "mse30/bart-base-finetuned-pubmed",
+  "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_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": "4.17.0",
+  "use_cache": true,
+  "vocab_size": 50265
+}

checkpoint-500/merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

checkpoint-500/optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:842ab02739549c1dee88b258d716d29973e585e3fe0af1a7e6af6023566d0e40
+size 1115513717

checkpoint-500/pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:090a531fe944f0477c7b6963e36f2257e7491dc75349b2ddda2e97f2cccdfa61
+size 557979897

checkpoint-500/rng_state.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:64d748507b4faa7f7dddfdf33fd950d644123c2830c09d9458e5ef7b291ad537
+size 14503

checkpoint-500/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:305adfba547ade1451728c1637f0e6c6617e8774c24c7cc62fcb46ac48bb99b6
+size 623

checkpoint-500/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1 @@


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-500/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

checkpoint-500/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "mse30/bart-base-finetuned-pubmed", "tokenizer_class": "BartTokenizer"}

checkpoint-500/trainer_state.json ADDED Viewed

	@@ -0,0 +1,76 @@

+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 27.77777777777778,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.78,
+      "learning_rate": 3e-06,
+      "loss": 8.2937,
+      "step": 50
+    },
+    {
+      "epoch": 5.56,
+      "learning_rate": 6e-06,
+      "loss": 4.7562,
+      "step": 100
+    },
+    {
+      "epoch": 8.33,
+      "learning_rate": 9e-06,
+      "loss": 3.0858,
+      "step": 150
+    },
+    {
+      "epoch": 11.11,
+      "learning_rate": 1.2e-05,
+      "loss": 2.4515,
+      "step": 200
+    },
+    {
+      "epoch": 13.89,
+      "learning_rate": 1.5e-05,
+      "loss": 2.1723,
+      "step": 250
+    },
+    {
+      "epoch": 16.67,
+      "learning_rate": 1.8e-05,
+      "loss": 1.981,
+      "step": 300
+    },
+    {
+      "epoch": 19.44,
+      "learning_rate": 2.1e-05,
+      "loss": 1.8522,
+      "step": 350
+    },
+    {
+      "epoch": 22.22,
+      "learning_rate": 2.4e-05,
+      "loss": 1.7612,
+      "step": 400
+    },
+    {
+      "epoch": 25.0,
+      "learning_rate": 2.7000000000000002e-05,
+      "loss": 1.7039,
+      "step": 450
+    },
+    {
+      "epoch": 27.78,
+      "learning_rate": 3e-05,
+      "loss": 1.6461,
+      "step": 500
+    }
+  ],
+  "max_steps": 1800,
+  "num_train_epochs": 100,
+  "total_flos": 1219472916480000.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:79be1103501cc9c7c2bd1cb54516e648bec56b102558206f93a993dec74ff629
+size 3119

checkpoint-500/vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff