update

Browse files

Files changed (10) hide show

config.json +29 -0
eval_results.json +11 -0
merges.txt +0 -0
pytorch_model.bin +3 -0
special_tokens_map.json +1 -0
tokenizer.json +0 -0
tokenizer_config.json +1 -0
trainer_state.json +241 -0
training_args.bin +3 -0
vocab.json +0 -0

config.json ADDED Viewed

	@@ -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": "4.18.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.json ADDED Viewed

	@@ -0,0 +1,11 @@

+{
+    "epoch": 3.0,
+    "eval_hate_f1": 0.7096774193548387,
+    "eval_hate_precision": 0.55,
+    "eval_hate_recall": 1.0,
+    "eval_loss": 0.6891850829124451,
+    "eval_macro_f1": 0.3548387096774194,
+    "eval_runtime": 29.6082,
+    "eval_samples_per_second": 16.887,
+    "eval_steps_per_second": 2.128
+}

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:dc700d2327a29be31ed85d6756e10b6a526252b74ce862c66ae212aa61cc5ec9
+size 498657517

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.json ADDED Viewed

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

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1 @@

+ {"errors": "replace", "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"}, "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"}, "unk_token": {"content": "<unk>", "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"}, "add_prefix_space": false, "trim_offsets": true, "special_tokens_map_file": null, "name_or_path": "cardiffnlp/twitter-roberta-base", "tokenizer_class": "RobertaTokenizer"}

trainer_state.json ADDED Viewed

	@@ -0,0 +1,241 @@

+{
+  "best_metric": 0.3548387096774194,
+  "best_model_checkpoint": "/home/myigezu/Mesay/Low_resourced/english-base-models/xlmt_eng_full/checkpoint-5000",
+  "epoch": 3.0,
+  "global_step": 15000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.8333333333333334e-05,
+      "loss": 0.7027,
+      "step": 500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.7051,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.5e-05,
+      "loss": 0.6994,
+      "step": 1500
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 0.7014,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 0.6982,
+      "step": 2500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4e-05,
+      "loss": 0.6966,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.8333333333333334e-05,
+      "loss": 0.7035,
+      "step": 3500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.7002,
+      "step": 4000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 3.5e-05,
+      "loss": 0.7002,
+      "step": 4500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.6929,
+      "step": 5000
+    },
+    {
+      "epoch": 1.0,
+      "eval_hate_f1": 0.7096774193548387,
+      "eval_hate_precision": 0.55,
+      "eval_hate_recall": 1.0,
+      "eval_loss": 0.6891850829124451,
+      "eval_macro_f1": 0.3548387096774194,
+      "eval_runtime": 29.7652,
+      "eval_samples_per_second": 16.798,
+      "eval_steps_per_second": 2.117,
+      "step": 5000
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 3.1666666666666666e-05,
+      "loss": 0.7073,
+      "step": 5500
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 3e-05,
+      "loss": 0.7046,
+      "step": 6000
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 2.8333333333333335e-05,
+      "loss": 0.7073,
+      "step": 6500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.7001,
+      "step": 7000
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 2.5e-05,
+      "loss": 0.7,
+      "step": 7500
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 0.6976,
+      "step": 8000
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 2.1666666666666667e-05,
+      "loss": 0.6983,
+      "step": 8500
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 2e-05,
+      "loss": 0.6944,
+      "step": 9000
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.8333333333333333e-05,
+      "loss": 0.6968,
+      "step": 9500
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.6955,
+      "step": 10000
+    },
+    {
+      "epoch": 2.0,
+      "eval_hate_f1": 0.7096774193548387,
+      "eval_hate_precision": 0.55,
+      "eval_hate_recall": 1.0,
+      "eval_loss": 0.6883429884910583,
+      "eval_macro_f1": 0.3548387096774194,
+      "eval_runtime": 29.7995,
+      "eval_samples_per_second": 16.779,
+      "eval_steps_per_second": 2.114,
+      "step": 10000
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 1.5e-05,
+      "loss": 0.7024,
+      "step": 10500
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.6953,
+      "step": 11000
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 1.1666666666666668e-05,
+      "loss": 0.6983,
+      "step": 11500
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 1e-05,
+      "loss": 0.6947,
+      "step": 12000
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.696,
+      "step": 12500
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.6947,
+      "step": 13000
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 5e-06,
+      "loss": 0.6923,
+      "step": 13500
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.6947,
+      "step": 14000
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.6907,
+      "step": 14500
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.6875,
+      "step": 15000
+    },
+    {
+      "epoch": 3.0,
+      "eval_hate_f1": 0.7096774193548387,
+      "eval_hate_precision": 0.55,
+      "eval_hate_recall": 1.0,
+      "eval_loss": 0.6882578730583191,
+      "eval_macro_f1": 0.3548387096774194,
+      "eval_runtime": 29.5782,
+      "eval_samples_per_second": 16.904,
+      "eval_steps_per_second": 2.13,
+      "step": 15000
+    },
+    {
+      "epoch": 3.0,
+      "step": 15000,
+      "total_flos": 1957320140815200.0,
+      "train_loss": 0.6982911661783854,
+      "train_runtime": 13954.391,
+      "train_samples_per_second": 4.3,
+      "train_steps_per_second": 1.075
+    }
+  ],
+  "max_steps": 15000,
+  "num_train_epochs": 3,
+  "total_flos": 1957320140815200.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5f7863dbf95d9becefbfa8d6d8d9b167359d7b6069e8aaa920058520e4151f65
+size 3119

vocab.json ADDED Viewed

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