Upload folder using huggingface_hub

xlmr_phq9_bucket_mock_v3/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": "4.57.6",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

xlmr_phq9_bucket_mock_v3/checkpoint-250/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66b0ee00294ec00758339956bdf77e0fdcf683469d0c287bb26c4125901bf959
+size 1112211160

xlmr_phq9_bucket_mock_v3/checkpoint-250/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1abace70e733234e43194212e8fc6271c833f29472b4a5bacf3c905c597e666f
+size 2224545163

xlmr_phq9_bucket_mock_v3/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_v3/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_v3/checkpoint-250/trainer_state.json

@@ -0,0 +1,134 @@
+{
+  "best_global_step": 225,
+  "best_metric": 0.6893233578016187,
+  "best_model_checkpoint": "/content/malviz_models1/xlmr_phq9_bucket_mock/checkpoint-225",
+  "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": 0.24,
+      "eval_loss": 1.389382004737854,
+      "eval_macro_f1": 0.09836065573770492,
+      "eval_runtime": 0.1704,
+      "eval_samples_per_second": 293.42,
+      "eval_steps_per_second": 23.474,
+      "step": 25
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.24,
+      "eval_loss": 1.3839259147644043,
+      "eval_macro_f1": 0.09836065573770492,
+      "eval_runtime": 0.165,
+      "eval_samples_per_second": 303.04,
+      "eval_steps_per_second": 24.243,
+      "step": 50
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.36,
+      "eval_loss": 1.360230565071106,
+      "eval_macro_f1": 0.2590909090909091,
+      "eval_runtime": 0.1658,
+      "eval_samples_per_second": 301.578,
+      "eval_steps_per_second": 24.126,
+      "step": 75
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.48,
+      "eval_loss": 1.2586359977722168,
+      "eval_macro_f1": 0.4423007246376811,
+      "eval_runtime": 0.1669,
+      "eval_samples_per_second": 299.567,
+      "eval_steps_per_second": 23.965,
+      "step": 100
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.68,
+      "eval_loss": 1.111634373664856,
+      "eval_macro_f1": 0.6227776799859179,
+      "eval_runtime": 0.166,
+      "eval_samples_per_second": 301.156,
+      "eval_steps_per_second": 24.092,
+      "step": 125
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.64,
+      "eval_loss": 0.9557175636291504,
+      "eval_macro_f1": 0.6201812770562771,
+      "eval_runtime": 0.1674,
+      "eval_samples_per_second": 298.773,
+      "eval_steps_per_second": 23.902,
+      "step": 150
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.64,
+      "eval_loss": 0.7907700538635254,
+      "eval_macro_f1": 0.6058197102604996,
+      "eval_runtime": 0.1672,
+      "eval_samples_per_second": 299.105,
+      "eval_steps_per_second": 23.928,
+      "step": 175
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.66,
+      "eval_loss": 0.7282854318618774,
+      "eval_macro_f1": 0.6468585762064023,
+      "eval_runtime": 0.167,
+      "eval_samples_per_second": 299.428,
+      "eval_steps_per_second": 23.954,
+      "step": 200
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.7,
+      "eval_loss": 0.7091819047927856,
+      "eval_macro_f1": 0.6893233578016187,
+      "eval_runtime": 0.1669,
+      "eval_samples_per_second": 299.53,
+      "eval_steps_per_second": 23.962,
+      "step": 225
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.7,
+      "eval_loss": 0.70115065574646,
+      "eval_macro_f1": 0.6893233578016187,
+      "eval_runtime": 0.1688,
+      "eval_samples_per_second": 296.2,
+      "eval_steps_per_second": 23.696,
+      "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_v3/checkpoint-250/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eef2e40f5fe6704a86d7ad6b844dcfe487e83325d5d3b65ec7f1e3a828df5633
+size 5905