Upload 15 files

Browse files

Files changed (15) hide show

checkpoint-2475/config.json +74 -0
checkpoint-2475/generation_config.json +13 -0
checkpoint-2475/model.safetensors +3 -0
checkpoint-2475/optimizer.pt +3 -0
checkpoint-2475/rng_state.pth +3 -0
checkpoint-2475/scheduler.pt +3 -0
checkpoint-2475/trainer_state.json +117 -0
checkpoint-2475/training_args.bin +3 -0
config.json +74 -0
generation_config.json +13 -0
merges.txt +0 -0
model.safetensors +3 -0
special_tokens_map.json +51 -0
tokenizer_config.json +56 -0
vocab.json +0 -0

checkpoint-2475/config.json ADDED Viewed

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

+{
+  "_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": 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": "4.45.2",
+  "use_cache": true,
+  "vocab_size": 50265
+}

checkpoint-2475/generation_config.json ADDED Viewed

	@@ -0,0 +1,13 @@

+{
+  "_from_model_config": true,
+  "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": "4.45.2"
+}

checkpoint-2475/model.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:6f2c9d4187405dcb0d1c5f8faddcb4f805f153bfb4a9cc008dbc453f363d5da3
+size 557912620

checkpoint-2475/optimizer.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:bbc7a62cae42d3db2b6b4743d1931129fdb707f6d148a5443bcef46a1ff79922
+size 1115579898

checkpoint-2475/rng_state.pth ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a9272a95cdcdca91efbdd683cfc666d6e3e2ce149da3b91f24f48972a1f32843
+size 14244

checkpoint-2475/scheduler.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:ea198067337d7cb319b6f5782f07cdabf48061cd8782ddaac4205a4aa8cc3338
+size 1064

checkpoint-2475/trainer_state.json ADDED Viewed

	@@ -0,0 +1,117 @@

+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 25.0,
+  "eval_steps": 500,
+  "global_step": 2475,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.0202020202020203,
+      "grad_norm": 3.2150983810424805,
+      "learning_rate": 4.595959595959596e-05,
+      "loss": 1.8523,
+      "step": 200
+    },
+    {
+      "epoch": 4.040404040404041,
+      "grad_norm": 1.2652349472045898,
+      "learning_rate": 4.191919191919192e-05,
+      "loss": 0.4357,
+      "step": 400
+    },
+    {
+      "epoch": 6.0606060606060606,
+      "grad_norm": 1.2245885133743286,
+      "learning_rate": 3.787878787878788e-05,
+      "loss": 0.2712,
+      "step": 600
+    },
+    {
+      "epoch": 8.080808080808081,
+      "grad_norm": 1.4887850284576416,
+      "learning_rate": 3.3838383838383844e-05,
+      "loss": 0.1956,
+      "step": 800
+    },
+    {
+      "epoch": 10.1010101010101,
+      "grad_norm": 1.4152169227600098,
+      "learning_rate": 2.9797979797979796e-05,
+      "loss": 0.1566,
+      "step": 1000
+    },
+    {
+      "epoch": 12.121212121212121,
+      "grad_norm": 0.9230123162269592,
+      "learning_rate": 2.575757575757576e-05,
+      "loss": 0.1279,
+      "step": 1200
+    },
+    {
+      "epoch": 14.141414141414142,
+      "grad_norm": 0.9463744163513184,
+      "learning_rate": 2.171717171717172e-05,
+      "loss": 0.0987,
+      "step": 1400
+    },
+    {
+      "epoch": 16.161616161616163,
+      "grad_norm": 1.6643699407577515,
+      "learning_rate": 1.7676767676767676e-05,
+      "loss": 0.0871,
+      "step": 1600
+    },
+    {
+      "epoch": 18.181818181818183,
+      "grad_norm": 0.7526511549949646,
+      "learning_rate": 1.3636363636363637e-05,
+      "loss": 0.076,
+      "step": 1800
+    },
+    {
+      "epoch": 20.2020202020202,
+      "grad_norm": 0.8697160482406616,
+      "learning_rate": 9.595959595959595e-06,
+      "loss": 0.0647,
+      "step": 2000
+    },
+    {
+      "epoch": 22.22222222222222,
+      "grad_norm": 0.369678258895874,
+      "learning_rate": 5.555555555555556e-06,
+      "loss": 0.0618,
+      "step": 2200
+    },
+    {
+      "epoch": 24.242424242424242,
+      "grad_norm": 0.760077178478241,
+      "learning_rate": 1.5151515151515152e-06,
+      "loss": 0.0546,
+      "step": 2400
+    }
+  ],
+  "logging_steps": 200,
+  "max_steps": 2475,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 25,
+  "save_steps": 10000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2995330351104000.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2475/training_args.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:bc0056c6ea5b29a25f7369d2e5175f36f99b0e43be56c846b326b05a3d19c0be
+size 5112

config.json ADDED Viewed

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

+{
+  "_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": 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": "4.45.2",
+  "use_cache": true,
+  "vocab_size": 50265
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,13 @@

+{
+  "_from_model_config": true,
+  "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": "4.45.2"
+}

merges.txt ADDED Viewed

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

model.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:6f2c9d4187405dcb0d1c5f8faddcb4f805f153bfb4a9cc008dbc453f363d5da3
+size 557912620

special_tokens_map.json ADDED Viewed

	@@ -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
+  }
+}

tokenizer_config.json ADDED Viewed

	@@ -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": false,
+  "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>"
+}

vocab.json ADDED Viewed

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