Push from colab

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "cardiffnlp/twitter-roberta-base",
+  "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,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:895d0b4e7c9692088ab659494df43601c24459804e33ba612b9d8606049a22e3
+size 997293853

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19ede9b09209dd5644fa9a7f453082eee896464a9a50eb50a44dea406b098059
+size 498675053

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f774346f5effc87fcc856da9ee90ba0dfe7ed861e04acc9095bca1f19dbf66a3
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f59298a08cd157d1ecc05e8d4af34705a5651d34f0742e06d5e37fa3d64298a
+size 623

trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.615384615384615,
+  "global_step": 4500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.07,
+      "learning_rate": 4.465811965811966e-05,
+      "loss": 0.386,
+      "step": 500
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 3.931623931623932e-05,
+      "loss": 0.2035,
+      "step": 1000
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 3.397435897435898e-05,
+      "loss": 0.1108,
+      "step": 1500
+    },
+    {
+      "epoch": 4.27,
+      "learning_rate": 2.863247863247863e-05,
+      "loss": 0.065,
+      "step": 2000
+    },
+    {
+      "epoch": 5.34,
+      "learning_rate": 2.3290598290598293e-05,
+      "loss": 0.0495,
+      "step": 2500
+    },
+    {
+      "epoch": 6.41,
+      "learning_rate": 1.794871794871795e-05,
+      "loss": 0.0278,
+      "step": 3000
+    },
+    {
+      "epoch": 7.48,
+      "learning_rate": 1.2606837606837608e-05,
+      "loss": 0.02,
+      "step": 3500
+    },
+    {
+      "epoch": 8.55,
+      "learning_rate": 7.264957264957266e-06,
+      "loss": 0.0161,
+      "step": 4000
+    },
+    {
+      "epoch": 9.62,
+      "learning_rate": 1.9230769230769234e-06,
+      "loss": 0.0107,
+      "step": 4500
+    }
+  ],
+  "max_steps": 4680,
+  "num_train_epochs": 10,
+  "total_flos": 9458973995719680.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa25cc6bd0e760da2d27cd74041067b0cdabb6c5e42e39d5c26272c29b7b96bb
+size 2991