initial roberta model commit

Browse files

Files changed (9) hide show

added_tokens.json +1 -0
config.json +34 -0
merges.txt +0 -0
pytorch_model.bin +3 -0
special_tokens_map.json +1 -0
tokenizer_config.json +1 -0
trainer_state.json +107 -0
training_args.bin +3 -0
vocab.json +0 -0

added_tokens.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"<Ul>": 50281, "</Tr>": 50276, "<Li>": 50279, "<Ol>": 50277, "</Table>": 50265, "<Table>": 50266, "</Li>": 50280, "</Td>": 50272, "</Th>": 50274, "<P>": 50268, "<Tr>": 50275, "</Ul>": 50282, "<Head>": 50267, "<Th>": 50273, "</Head>": 50270, "</P>": 50269, "<Td>": 50271, "</Ol>": 50278}

config.json ADDED Viewed

	@@ -0,0 +1,34 @@

+{
+  "_name_or_path": "deepset/roberta-base-squad2",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "language": "english",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "name": "Roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.2.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50283
+}

merges.txt ADDED Viewed

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

pytorch_model.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:8ac8a28cb0df64813384c290430a9f14202dd7db9820f84f5dd23bce25e693f4
+size 498729623

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1 @@

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

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1 @@

+ {"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "do_lower_case": false, "model_max_length": 512, "full_tokenizer_file": null, "special_tokens_map_file": "/root/.cache/huggingface/transformers/c9d2c178fac8d40234baa1833a3b1903d393729bf93ea34da247c07db24900d0.cb2244924ab24d706b02fd7fcedaea4531566537687a539ebb94db511fd122a0", "name_or_path": "deepset/roberta-base-squad2"}

trainer_state.json ADDED Viewed

	@@ -0,0 +1,107 @@

+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9954493742889647,
+  "global_step": 7000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.7653286978508224e-05,
+      "loss": 0.3321,
+      "step": 1000
+    },
+    {
+      "epoch": 0.14,
+      "eval_loss": 8.593664169311523,
+      "eval_runtime": 118.099,
+      "eval_samples_per_second": 211.695,
+      "step": 1000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 3.975189633375474e-05,
+      "loss": 0.2726,
+      "step": 2000
+    },
+    {
+      "epoch": 0.28,
+      "eval_loss": 9.972230911254883,
+      "eval_runtime": 118.1942,
+      "eval_samples_per_second": 211.525,
+      "step": 2000
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 3.185050568900126e-05,
+      "loss": 0.2505,
+      "step": 3000
+    },
+    {
+      "epoch": 0.43,
+      "eval_loss": 11.511611938476562,
+      "eval_runtime": 118.1309,
+      "eval_samples_per_second": 211.638,
+      "step": 3000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.394911504424779e-05,
+      "loss": 0.2275,
+      "step": 4000
+    },
+    {
+      "epoch": 0.57,
+      "eval_loss": 10.211225509643555,
+      "eval_runtime": 118.2397,
+      "eval_samples_per_second": 211.443,
+      "step": 4000
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.6047724399494312e-05,
+      "loss": 0.2173,
+      "step": 5000
+    },
+    {
+      "epoch": 0.71,
+      "eval_loss": 13.594472885131836,
+      "eval_runtime": 118.3052,
+      "eval_samples_per_second": 211.326,
+      "step": 5000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 8.146333754740834e-06,
+      "loss": 0.2038,
+      "step": 6000
+    },
+    {
+      "epoch": 0.85,
+      "eval_loss": 17.407012939453125,
+      "eval_runtime": 117.4057,
+      "eval_samples_per_second": 212.945,
+      "step": 6000
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.449431099873578e-07,
+      "loss": 0.1963,
+      "step": 7000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 18.987485885620117,
+      "eval_runtime": 117.6706,
+      "eval_samples_per_second": 212.466,
+      "step": 7000
+    }
+  ],
+  "max_steps": 7032,
+  "num_train_epochs": 1,
+  "total_flos": 75170067805473600,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5601974d823b5d120c9e871d50a352c0dfaf539fc3ebafe4bf8f3f2f044bc32b
+size 2031

vocab.json ADDED Viewed

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