Upload folder using huggingface_hub

xlmr_phq9_bucket_mock_v2/checkpoint-250/config.json

@@ -0,0 +1,40 @@
+{
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "PHQ9_0",
+    "1": "PHQ9_1",
+    "2": "PHQ9_2",
+    "3": "PHQ9_3"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "PHQ9_0": 0,
+    "PHQ9_1": 1,
+    "PHQ9_2": 2,
+    "PHQ9_3": 3
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.57.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

xlmr_phq9_bucket_mock_v2/checkpoint-250/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75fa28f1402dc0da4a98bfc86f02cfc462b8f7c5a7684e7e11bdbaf54c939eef
+size 1112211160

xlmr_phq9_bucket_mock_v2/checkpoint-250/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dd2490b7b714a9a2c7a208aabc3c7bdc6525ca83497bf0d87293c8b2f2d4eeb
+size 2224545163

xlmr_phq9_bucket_mock_v2/checkpoint-250/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7e44548d239bfeb4c5e6f685763e90e986f8f9ebfd6602a3febb031d2e28069
+size 14645

xlmr_phq9_bucket_mock_v2/checkpoint-250/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b04611bea80597dee677a377375d057cf3fa3437fb4ed8809d4662285b8811b
+size 1465

xlmr_phq9_bucket_mock_v2/checkpoint-250/trainer_state.json

@@ -0,0 +1,134 @@
+{
+  "best_global_step": 150,
+  "best_metric": 0.7067466266866567,
+  "best_model_checkpoint": "/content/malviz_models1/xlmr_phq9_bucket_mock/checkpoint-150",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.26,
+      "eval_loss": 1.384892225265503,
+      "eval_macro_f1": 0.10317460317460317,
+      "eval_runtime": 0.1672,
+      "eval_samples_per_second": 299.041,
+      "eval_steps_per_second": 23.923,
+      "step": 25
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.26,
+      "eval_loss": 1.3814570903778076,
+      "eval_macro_f1": 0.10317460317460317,
+      "eval_runtime": 0.1688,
+      "eval_samples_per_second": 296.197,
+      "eval_steps_per_second": 23.696,
+      "step": 50
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.56,
+      "eval_loss": 1.3717080354690552,
+      "eval_macro_f1": 0.4993865783339467,
+      "eval_runtime": 0.1667,
+      "eval_samples_per_second": 299.888,
+      "eval_steps_per_second": 23.991,
+      "step": 75
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.58,
+      "eval_loss": 1.1022435426712036,
+      "eval_macro_f1": 0.5910441880101324,
+      "eval_runtime": 0.1693,
+      "eval_samples_per_second": 295.311,
+      "eval_steps_per_second": 23.625,
+      "step": 100
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.68,
+      "eval_loss": 0.826448917388916,
+      "eval_macro_f1": 0.5928991596638655,
+      "eval_runtime": 0.1735,
+      "eval_samples_per_second": 288.228,
+      "eval_steps_per_second": 23.058,
+      "step": 125
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.72,
+      "eval_loss": 0.7121301889419556,
+      "eval_macro_f1": 0.7067466266866567,
+      "eval_runtime": 0.1688,
+      "eval_samples_per_second": 296.229,
+      "eval_steps_per_second": 23.698,
+      "step": 150
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.68,
+      "eval_loss": 0.6965749263763428,
+      "eval_macro_f1": 0.5961134453781513,
+      "eval_runtime": 0.1682,
+      "eval_samples_per_second": 297.34,
+      "eval_steps_per_second": 23.787,
+      "step": 175
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7,
+      "eval_loss": 0.6177582740783691,
+      "eval_macro_f1": 0.6836076280041797,
+      "eval_runtime": 0.1667,
+      "eval_samples_per_second": 299.923,
+      "eval_steps_per_second": 23.994,
+      "step": 200
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.7,
+      "eval_loss": 0.6033841371536255,
+      "eval_macro_f1": 0.6836076280041797,
+      "eval_runtime": 0.1689,
+      "eval_samples_per_second": 296.017,
+      "eval_steps_per_second": 23.681,
+      "step": 225
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.68,
+      "eval_loss": 0.5988900661468506,
+      "eval_macro_f1": 0.659376026272578,
+      "eval_runtime": 0.1689,
+      "eval_samples_per_second": 295.957,
+      "eval_steps_per_second": 23.677,
+      "step": 250
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 250,
+  "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": 263115780096000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

xlmr_phq9_bucket_mock_v2/checkpoint-250/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae377a491453a46c2c0a2f59e71f38ce623a80d04788b8891adf4aa9e04586a5
+size 5905