Training in progress, epoch 8

checkpoint-1688/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-1688/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef4802ad38eb73fe5dfaa7cf016af984d8ab875ba7a3b70983c1ec626caa9e25
+size 997299037

checkpoint-1688/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:138d40b8d593a1a676495429fef65fdc09b45ac861796495d741df47139d0f11
+size 498678125

checkpoint-1688/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77715b01271ff5b5173f23a7e1fe3241d91894f79cb6bdb25cb96d9255d269a7
+size 14503

checkpoint-1688/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f38ba29d4e8440ae570539dcf8d8594992b1faabc701274645aec28ed9db9823
+size 559

checkpoint-1688/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9bf8408d38ae065a394d43f0a65aec036841bb6806e8db92542b71758aff3e4
+size 623

checkpoint-1688/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-1688/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-1688/trainer_state.json

@@ -0,0 +1,144 @@
+{
+  "best_metric": 0.7782108653517272,
+  "best_model_checkpoint": "outputs/time_lm_nli/checkpoint-1266",
+  "epoch": 8.0,
+  "global_step": 1688,
+  "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
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 9.333333333333333e-07,
+      "loss": 0.3725,
+      "step": 422
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.759,
+      "eval_f1": 0.7583549419422403,
+      "eval_loss": 0.3489450216293335,
+      "eval_runtime": 5.103,
+      "eval_samples_per_second": 587.885,
+      "eval_steps_per_second": 73.486,
+      "step": 422
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 9e-07,
+      "loss": 0.3158,
+      "step": 633
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7613333333333333,
+      "eval_f1": 0.7569694772671423,
+      "eval_loss": 0.3286795914173126,
+      "eval_runtime": 5.4646,
+      "eval_samples_per_second": 548.991,
+      "eval_steps_per_second": 68.624,
+      "step": 633
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 8.666666666666667e-07,
+      "loss": 0.289,
+      "step": 844
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.769,
+      "eval_f1": 0.7684440341259363,
+      "eval_loss": 0.33065709471702576,
+      "eval_runtime": 5.2159,
+      "eval_samples_per_second": 575.162,
+      "eval_steps_per_second": 71.895,
+      "step": 844
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 8.333333333333333e-07,
+      "loss": 0.2716,
+      "step": 1055
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7766666666666666,
+      "eval_f1": 0.775028474008066,
+      "eval_loss": 0.3240624666213989,
+      "eval_runtime": 5.2721,
+      "eval_samples_per_second": 569.029,
+      "eval_steps_per_second": 71.129,
+      "step": 1055
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 8e-07,
+      "loss": 0.2575,
+      "step": 1266
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7786666666666666,
+      "eval_f1": 0.7782108653517272,
+      "eval_loss": 0.32720017433166504,
+      "eval_runtime": 5.4144,
+      "eval_samples_per_second": 554.075,
+      "eval_steps_per_second": 69.259,
+      "step": 1266
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 7.666666666666667e-07,
+      "loss": 0.2441,
+      "step": 1477
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7783333333333333,
+      "eval_f1": 0.7775937336504917,
+      "eval_loss": 0.3257558345794678,
+      "eval_runtime": 5.0695,
+      "eval_samples_per_second": 591.777,
+      "eval_steps_per_second": 73.972,
+      "step": 1477
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 7.333333333333332e-07,
+      "loss": 0.2363,
+      "step": 1688
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7776666666666666,
+      "eval_f1": 0.777267505288088,
+      "eval_loss": 0.331592321395874,
+      "eval_runtime": 5.1518,
+      "eval_samples_per_second": 582.323,
+      "eval_steps_per_second": 72.79,
+      "step": 1688
+    }
+  ],
+  "max_steps": 6330,
+  "num_train_epochs": 30,
+  "total_flos": 1.1471153007750912e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1688/training_args.bin

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

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a986c17ae415bf0a8b1d675d593ed72a2a3f1afb845d75e1ddfd1eeec5747783
+oid sha256:138d40b8d593a1a676495429fef65fdc09b45ac861796495d741df47139d0f11
 size 498678125