Training in progress, epoch 1

checkpoint-211/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "cardiffnlp/twitter-roberta-base-2021-124m",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

checkpoint-211/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcbaea9cfef034a1b613174d5bc5eb798ccf302df464be53d22fde2c798c3808
+size 997299037

checkpoint-211/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46a7c04c421d3a323a6c4b34231a1eb59a5b4ede1835684d7add813f9b8100b3
+size 498678125

checkpoint-211/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5059ac010c6f78eee32f8badc34cb93245c967316ed927862ac93af122b1ac21
+size 14503

checkpoint-211/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0225db2165b1e7895063a491111c1a4012f29b3a906de12eca90687d009d2a52
+size 559

checkpoint-211/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5752209138a8b0f834d596eb59449fe1e7d2834ccaa97fd8f79df3bdc31d616b
+size 623

checkpoint-211/special_tokens_map.json

@@ -0,0 +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-211/tokenizer_config.json

@@ -0,0 +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": 512, "special_tokens_map_file": null, "name_or_path": "cardiffnlp/twitter-roberta-base-2021-124m", "normalization": true, "tokenizer_class": "RobertaTokenizer"}

checkpoint-211/trainer_state.json

@@ -0,0 +1,32 @@
+{
+  "best_metric": 0.6998718119161117,
+  "best_model_checkpoint": "outputs/time_lm_nli/checkpoint-211",
+  "epoch": 1.0,
+  "global_step": 211,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.666666666666666e-07,
+      "loss": 0.5392,
+      "step": 211
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7,
+      "eval_f1": 0.6998718119161117,
+      "eval_loss": 0.4048246741294861,
+      "eval_runtime": 5.0256,
+      "eval_samples_per_second": 596.939,
+      "eval_steps_per_second": 74.617,
+      "step": 211
+    }
+  ],
+  "max_steps": 6330,
+  "num_train_epochs": 30,
+  "total_flos": 1430448984655488.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-211/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3966be765a13463da707bf5cd58cd4c0452776ca8eaf9c649e2dbde2a9daa7b1
+size 3119

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "cardiffnlp/twitter-roberta-base-2021-124m",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46a7c04c421d3a323a6c4b34231a1eb59a5b4ede1835684d7add813f9b8100b3
+size 498678125

special_tokens_map.json

@@ -0,0 +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}}

tokenizer_config.json

@@ -0,0 +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": 512, "special_tokens_map_file": null, "name_or_path": "cardiffnlp/twitter-roberta-base-2021-124m", "normalization": true, "tokenizer_class": "RobertaTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3966be765a13463da707bf5cd58cd4c0452776ca8eaf9c649e2dbde2a9daa7b1
+size 3119