theraphy_model_empathy

Browse files

Files changed (15) hide show

checkpoint-880/config.json +50 -0
checkpoint-880/model.safetensors +3 -0
checkpoint-880/optimizer.pt +3 -0
checkpoint-880/rng_state.pth +3 -0
checkpoint-880/scheduler.pt +3 -0
checkpoint-880/trainer_state.json +193 -0
checkpoint-880/training_args.bin +3 -0
config.json +50 -0
label_map.json +13 -0
model.safetensors +3 -0
special_tokens_map.json +7 -0
tokenizer.json +0 -0
tokenizer_config.json +56 -0
training_data.json +0 -0
vocab.txt +0 -0

checkpoint-880/config.json ADDED Viewed

	@@ -0,0 +1,50 @@

+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.57.3",
+  "vocab_size": 30522
+}

checkpoint-880/model.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:178976a03cb0b4cbd4708206436f36f258f6dc5969333cd3cad933d363406ec4
+size 267860252

checkpoint-880/optimizer.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:e8f6931ced400f6aa9df9a811dc7fe7fb5383e55efcd2916861057f9fa86f5ee
+size 535780171

checkpoint-880/rng_state.pth ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:bdf20b536b841ae00302a87a5554a163da7c3a74cb0f30f8e412080b027440fe
+size 14455

checkpoint-880/scheduler.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:0b6305b66c3dba715b1debc5f22becac5db8f36abba019141c6d03f654e2d14e
+size 1465

checkpoint-880/trainer_state.json ADDED Viewed

	@@ -0,0 +1,193 @@

+{
+  "best_global_step": 880,
+  "best_metric": 0.03167559579014778,
+  "best_model_checkpoint": "therapy_model_v2/checkpoint-880",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 880,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2840909090909091,
+      "grad_norm": 3.655754804611206,
+      "learning_rate": 2.94e-05,
+      "loss": 2.1685,
+      "step": 50
+    },
+    {
+      "epoch": 0.5681818181818182,
+      "grad_norm": 7.086261749267578,
+      "learning_rate": 2.8538767395626242e-05,
+      "loss": 1.6208,
+      "step": 100
+    },
+    {
+      "epoch": 0.8522727272727273,
+      "grad_norm": 3.383866310119629,
+      "learning_rate": 2.704771371769384e-05,
+      "loss": 1.0512,
+      "step": 150
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6480007767677307,
+      "eval_runtime": 117.4999,
+      "eval_samples_per_second": 5.974,
+      "eval_steps_per_second": 0.374,
+      "step": 176
+    },
+    {
+      "epoch": 1.1363636363636362,
+      "grad_norm": 2.4574246406555176,
+      "learning_rate": 2.5556660039761434e-05,
+      "loss": 0.6298,
+      "step": 200
+    },
+    {
+      "epoch": 1.4204545454545454,
+      "grad_norm": 6.754581928253174,
+      "learning_rate": 2.4065606361829024e-05,
+      "loss": 0.3986,
+      "step": 250
+    },
+    {
+      "epoch": 1.7045454545454546,
+      "grad_norm": 2.3031885623931885,
+      "learning_rate": 2.2574552683896622e-05,
+      "loss": 0.3178,
+      "step": 300
+    },
+    {
+      "epoch": 1.9886363636363638,
+      "grad_norm": 7.972731113433838,
+      "learning_rate": 2.1083499005964216e-05,
+      "loss": 0.2452,
+      "step": 350
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.18218687176704407,
+      "eval_runtime": 117.6397,
+      "eval_samples_per_second": 5.967,
+      "eval_steps_per_second": 0.374,
+      "step": 352
+    },
+    {
+      "epoch": 2.2727272727272725,
+      "grad_norm": 1.7412598133087158,
+      "learning_rate": 1.9592445328031807e-05,
+      "loss": 0.1585,
+      "step": 400
+    },
+    {
+      "epoch": 2.5568181818181817,
+      "grad_norm": 6.392980098724365,
+      "learning_rate": 1.8101391650099404e-05,
+      "loss": 0.1024,
+      "step": 450
+    },
+    {
+      "epoch": 2.840909090909091,
+      "grad_norm": 0.96819669008255,
+      "learning_rate": 1.6610337972167e-05,
+      "loss": 0.0486,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.07200995832681656,
+      "eval_runtime": 117.2831,
+      "eval_samples_per_second": 5.986,
+      "eval_steps_per_second": 0.375,
+      "step": 528
+    },
+    {
+      "epoch": 3.125,
+      "grad_norm": 0.18693216145038605,
+      "learning_rate": 1.5119284294234594e-05,
+      "loss": 0.0462,
+      "step": 550
+    },
+    {
+      "epoch": 3.409090909090909,
+      "grad_norm": 0.16053710877895355,
+      "learning_rate": 1.3628230616302189e-05,
+      "loss": 0.039,
+      "step": 600
+    },
+    {
+      "epoch": 3.6931818181818183,
+      "grad_norm": 2.7669754028320312,
+      "learning_rate": 1.2137176938369781e-05,
+      "loss": 0.0297,
+      "step": 650
+    },
+    {
+      "epoch": 3.9772727272727275,
+      "grad_norm": 0.07028041779994965,
+      "learning_rate": 1.0646123260437375e-05,
+      "loss": 0.0254,
+      "step": 700
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.04889064282178879,
+      "eval_runtime": 117.1195,
+      "eval_samples_per_second": 5.994,
+      "eval_steps_per_second": 0.376,
+      "step": 704
+    },
+    {
+      "epoch": 4.261363636363637,
+      "grad_norm": 0.05612948164343834,
+      "learning_rate": 9.155069582504971e-06,
+      "loss": 0.021,
+      "step": 750
+    },
+    {
+      "epoch": 4.545454545454545,
+      "grad_norm": 0.3926457464694977,
+      "learning_rate": 7.664015904572564e-06,
+      "loss": 0.0114,
+      "step": 800
+    },
+    {
+      "epoch": 4.829545454545455,
+      "grad_norm": 5.097391128540039,
+      "learning_rate": 6.172962226640159e-06,
+      "loss": 0.0146,
+      "step": 850
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.03167559579014778,
+      "eval_runtime": 117.8556,
+      "eval_samples_per_second": 5.956,
+      "eval_steps_per_second": 0.373,
+      "step": 880
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1056,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "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": 464703974837760.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-880/training_args.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:8268ebe96b7e7766c6c4c4a35e9afc12ad5c8915a17b02e6ae7af1c736e75297
+size 5777

config.json ADDED Viewed

	@@ -0,0 +1,50 @@

+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.57.3",
+  "vocab_size": 30522
+}

label_map.json ADDED Viewed

	@@ -0,0 +1,13 @@

+{
+  "anger": 0,
+  "anxiety": 1,
+  "depression": 2,
+  "family": 3,
+  "general_support": 4,
+  "grief": 5,
+  "relationship": 6,
+  "self_esteem": 7,
+  "sleep_issues": 8,
+  "suicide": 9,
+  "trauma": 10
+}

model.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:178976a03cb0b4cbd4708206436f36f258f6dc5969333cd3cad933d363406ec4
+size 267860252

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer.json ADDED Viewed

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

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,56 @@

+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_data.json ADDED Viewed

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

vocab.txt ADDED Viewed

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