Upload 9 files

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "/app/data_patent/train_roberta/model_result",
+  "architectures": [
+    "RobertaForCL"
+  ],
+  "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,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 514,
+  "model_type": "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": 52000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ec2761edd5166d89d35a2049202efcb3d1b93545d235bc52ef77719be325d1a
+size 501634165

special_tokens_map.json

@@ -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

@@ -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"}, "special_tokens_map_file": null, "name_or_path": "/app/data_patent/tokenizing/tokenized_result"}

train_results.txt

@@ -0,0 +1,3 @@
+epoch = 2.0
+train_runtime = 1295.503
+train_samples_per_second = 17.38

trainer_state.json

@@ -0,0 +1,292 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "global_step": 22516,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.9333807070527625e-05,
+      "loss": 0.5737,
+      "step": 500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.8667614141055253e-05,
+      "loss": 0.4695,
+      "step": 1000
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 2.8001421211582874e-05,
+      "loss": 0.439,
+      "step": 1500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 2.73352282821105e-05,
+      "loss": 0.3985,
+      "step": 2000
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 2.6669035352638126e-05,
+      "loss": 0.3858,
+      "step": 2500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.600284242316575e-05,
+      "loss": 0.3637,
+      "step": 3000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2.5336649493693375e-05,
+      "loss": 0.3589,
+      "step": 3500
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2.4670456564221e-05,
+      "loss": 0.3473,
+      "step": 4000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 2.4004263634748624e-05,
+      "loss": 0.3185,
+      "step": 4500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 2.3338070705276248e-05,
+      "loss": 0.3282,
+      "step": 5000
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.2671877775803876e-05,
+      "loss": 0.3195,
+      "step": 5500
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.20056848463315e-05,
+      "loss": 0.3099,
+      "step": 6000
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 2.133949191685912e-05,
+      "loss": 0.2884,
+      "step": 6500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 2.0673298987386746e-05,
+      "loss": 0.2962,
+      "step": 7000
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 2.0007106057914373e-05,
+      "loss": 0.2811,
+      "step": 7500
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.9340913128441998e-05,
+      "loss": 0.2757,
+      "step": 8000
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.8674720198969622e-05,
+      "loss": 0.2615,
+      "step": 8500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.8008527269497247e-05,
+      "loss": 0.2716,
+      "step": 9000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.734233434002487e-05,
+      "loss": 0.2503,
+      "step": 9500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.6676141410552495e-05,
+      "loss": 0.248,
+      "step": 10000
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.6009948481080123e-05,
+      "loss": 0.2374,
+      "step": 10500
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.5343755551607744e-05,
+      "loss": 0.247,
+      "step": 11000
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.4677562622135372e-05,
+      "loss": 0.1944,
+      "step": 11500
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.4011369692662995e-05,
+      "loss": 0.1465,
+      "step": 12000
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.334517676319062e-05,
+      "loss": 0.1489,
+      "step": 12500
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.2678983833718245e-05,
+      "loss": 0.1389,
+      "step": 13000
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.201279090424587e-05,
+      "loss": 0.1495,
+      "step": 13500
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.1346597974773496e-05,
+      "loss": 0.1483,
+      "step": 14000
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.068040504530112e-05,
+      "loss": 0.1432,
+      "step": 14500
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.0014212115828744e-05,
+      "loss": 0.1288,
+      "step": 15000
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 9.348019186356369e-06,
+      "loss": 0.1403,
+      "step": 15500
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 8.681826256883993e-06,
+      "loss": 0.14,
+      "step": 16000
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 8.015633327411618e-06,
+      "loss": 0.1369,
+      "step": 16500
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 7.349440397939243e-06,
+      "loss": 0.1241,
+      "step": 17000
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 6.683247468466868e-06,
+      "loss": 0.129,
+      "step": 17500
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 6.017054538994493e-06,
+      "loss": 0.1224,
+      "step": 18000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 5.350861609522118e-06,
+      "loss": 0.127,
+      "step": 18500
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 4.684668680049743e-06,
+      "loss": 0.1258,
+      "step": 19000
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 4.018475750577367e-06,
+      "loss": 0.1186,
+      "step": 19500
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 3.3522828211049918e-06,
+      "loss": 0.1107,
+      "step": 20000
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 2.686089891632617e-06,
+      "loss": 0.1202,
+      "step": 20500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 2.0198969621602414e-06,
+      "loss": 0.1182,
+      "step": 21000
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.3537040326878664e-06,
+      "loss": 0.1132,
+      "step": 21500
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 6.875111032154912e-07,
+      "loss": 0.112,
+      "step": 22000
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2.1318173743116005e-08,
+      "loss": 0.1181,
+      "step": 22500
+    },
+    {
+      "epoch": 2.0,
+      "step": 22516,
+      "train_runtime": 1295.503,
+      "train_samples_per_second": 17.38
+    }
+  ],
+  "max_steps": 22516,
+  "num_train_epochs": 2,
+  "total_flos": 34691312231055360,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d39439ac6c3a4c50ff0a057635bb777618d30eaf62c7ac11198bfb012d8e4737
+size 2031