Upload trained RoBERTa model

Browse files

Files changed (6) hide show

checkpoint-1230/trainer_state.json +223 -0
checkpoint-369/trainer_state.json +90 -0
config.json +35 -0
model.safetensors +3 -0
tokenizer.json +0 -0
tokenizer_config.json +58 -0

checkpoint-1230/trainer_state.json ADDED Viewed

	@@ -0,0 +1,223 @@

+{
+  "best_metric": 0.7411347517730497,
+  "best_model_checkpoint": "roberta-Empathy-goodareas-eval_FeedbackESConv5pp_CARE10pp-sweeps-current/checkpoint-1230",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 1230,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 18.67070770263672,
+      "learning_rate": 2.4215053849812563e-05,
+      "loss": 0.6796,
+      "step": 123
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7329910141206675,
+      "eval_f1": 0.6510067114093959,
+      "eval_loss": 0.5134924650192261,
+      "eval_precision": 0.5527065527065527,
+      "eval_recall": 0.7918367346938775,
+      "eval_runtime": 5.5494,
+      "eval_samples_per_second": 140.375,
+      "eval_steps_per_second": 8.83,
+      "step": 123
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 14.706717491149902,
+      "learning_rate": 2.15244923109445e-05,
+      "loss": 0.5601,
+      "step": 246
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7869062901155327,
+      "eval_f1": 0.6992753623188406,
+      "eval_loss": 0.3676498532295227,
+      "eval_precision": 0.6286644951140065,
+      "eval_recall": 0.7877551020408163,
+      "eval_runtime": 5.6561,
+      "eval_samples_per_second": 137.727,
+      "eval_steps_per_second": 8.663,
+      "step": 246
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 9.49075984954834,
+      "learning_rate": 1.883393077207644e-05,
+      "loss": 0.4963,
+      "step": 369
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8215661103979461,
+      "eval_f1": 0.7352380952380952,
+      "eval_loss": 0.39641448855400085,
+      "eval_precision": 0.6892857142857143,
+      "eval_recall": 0.7877551020408163,
+      "eval_runtime": 5.7301,
+      "eval_samples_per_second": 135.948,
+      "eval_steps_per_second": 8.551,
+      "step": 369
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 11.884066581726074,
+      "learning_rate": 1.6143369233208374e-05,
+      "loss": 0.4666,
+      "step": 492
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7432605905006419,
+      "eval_f1": 0.6951219512195121,
+      "eval_loss": 0.5450116395950317,
+      "eval_precision": 0.5547445255474452,
+      "eval_recall": 0.9306122448979591,
+      "eval_runtime": 6.1436,
+      "eval_samples_per_second": 126.8,
+      "eval_steps_per_second": 7.976,
+      "step": 492
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 10.478497505187988,
+      "learning_rate": 1.3452807694340314e-05,
+      "loss": 0.44,
+      "step": 615
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8215661103979461,
+      "eval_f1": 0.7169042769857433,
+      "eval_loss": 0.2740727365016937,
+      "eval_precision": 0.7154471544715447,
+      "eval_recall": 0.7183673469387755,
+      "eval_runtime": 5.5644,
+      "eval_samples_per_second": 139.996,
+      "eval_steps_per_second": 8.806,
+      "step": 615
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 20.127138137817383,
+      "learning_rate": 1.076224615547225e-05,
+      "loss": 0.3848,
+      "step": 738
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8177150192554558,
+      "eval_f1": 0.7290076335877863,
+      "eval_loss": 0.321363627910614,
+      "eval_precision": 0.6845878136200717,
+      "eval_recall": 0.7795918367346939,
+      "eval_runtime": 5.691,
+      "eval_samples_per_second": 136.884,
+      "eval_steps_per_second": 8.61,
+      "step": 738
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 9.211082458496094,
+      "learning_rate": 8.071684616604187e-06,
+      "loss": 0.3553,
+      "step": 861
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8138639281129654,
+      "eval_f1": 0.720616570327553,
+      "eval_loss": 0.31627482175827026,
+      "eval_precision": 0.6824817518248175,
+      "eval_recall": 0.763265306122449,
+      "eval_runtime": 5.6854,
+      "eval_samples_per_second": 137.018,
+      "eval_steps_per_second": 8.619,
+      "step": 861
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 10.294879913330078,
+      "learning_rate": 5.381123077736125e-06,
+      "loss": 0.3197,
+      "step": 984
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7881899871630296,
+      "eval_f1": 0.7236180904522613,
+      "eval_loss": 0.4855680763721466,
+      "eval_precision": 0.6136363636363636,
+      "eval_recall": 0.8816326530612245,
+      "eval_runtime": 5.5376,
+      "eval_samples_per_second": 140.675,
+      "eval_steps_per_second": 8.849,
+      "step": 984
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 6.516270637512207,
+      "learning_rate": 2.6905615388680624e-06,
+      "loss": 0.2825,
+      "step": 1107
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.7958921694480102,
+      "eval_f1": 0.7234782608695652,
+      "eval_loss": 0.4514783024787903,
+      "eval_precision": 0.6303030303030303,
+      "eval_recall": 0.8489795918367347,
+      "eval_runtime": 5.604,
+      "eval_samples_per_second": 139.009,
+      "eval_steps_per_second": 8.744,
+      "step": 1107
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 50.148292541503906,
+      "learning_rate": 0.0,
+      "loss": 0.2423,
+      "step": 1230
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8125802310654685,
+      "eval_f1": 0.7411347517730497,
+      "eval_loss": 0.45171597599983215,
+      "eval_precision": 0.6551724137931034,
+      "eval_recall": 0.8530612244897959,
+      "eval_runtime": 5.5959,
+      "eval_samples_per_second": 139.21,
+      "eval_steps_per_second": 8.756,
+      "step": 1230
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1230,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.688470544354739e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-369/trainer_state.json ADDED Viewed

	@@ -0,0 +1,90 @@

+{
+  "best_metric": 0.7352380952380952,
+  "best_model_checkpoint": "roberta-Empathy-goodareas-eval_FeedbackESConv5pp_CARE10pp-sweeps-current/checkpoint-369",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 369,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 18.67070770263672,
+      "learning_rate": 2.4215053849812563e-05,
+      "loss": 0.6796,
+      "step": 123
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7329910141206675,
+      "eval_f1": 0.6510067114093959,
+      "eval_loss": 0.5134924650192261,
+      "eval_precision": 0.5527065527065527,
+      "eval_recall": 0.7918367346938775,
+      "eval_runtime": 5.5494,
+      "eval_samples_per_second": 140.375,
+      "eval_steps_per_second": 8.83,
+      "step": 123
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 14.706717491149902,
+      "learning_rate": 2.15244923109445e-05,
+      "loss": 0.5601,
+      "step": 246
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7869062901155327,
+      "eval_f1": 0.6992753623188406,
+      "eval_loss": 0.3676498532295227,
+      "eval_precision": 0.6286644951140065,
+      "eval_recall": 0.7877551020408163,
+      "eval_runtime": 5.6561,
+      "eval_samples_per_second": 137.727,
+      "eval_steps_per_second": 8.663,
+      "step": 246
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 9.49075984954834,
+      "learning_rate": 1.883393077207644e-05,
+      "loss": 0.4963,
+      "step": 369
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8215661103979461,
+      "eval_f1": 0.7352380952380952,
+      "eval_loss": 0.39641448855400085,
+      "eval_precision": 0.6892857142857143,
+      "eval_recall": 0.7877551020408163,
+      "eval_runtime": 5.7301,
+      "eval_samples_per_second": 135.948,
+      "eval_steps_per_second": 8.551,
+      "step": 369
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1230,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8103725661239040.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

config.json ADDED Viewed

	@@ -0,0 +1,35 @@

+{
+  "_name_or_path": "FacebookAI/roberta-large",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "not selected",
+    "1": "selected"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "not selected": "0",
+    "selected": "1"
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:1b1811a574aafefd5aa8845394c0bcf71e873a16fd1076fb95fbdb03b682dea7
+size 1421495416

tokenizer.json ADDED Viewed

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

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,58 @@

+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}