Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d3503959fba8a735c03966179e6a011b9eb835c3954b48452cb21262aee35ed
+oid sha256:2999c5c45ace354242376f2be90db4238a31117d3a08d6a1feb43fe0596f3f9e
 size 498625128

run-0/checkpoint-2252/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4be1a45cd710a79a95de01680d78de842ea44199bf1ccdb9b8dfb49f0908c77d
+oid sha256:9c12ed69c86e794797a0b1de6c0630e157810b87167e91afae46f31f0a4ae43d
 size 14244

run-1/checkpoint-563/config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "roberta-base",
+  "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": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
+  },
+  "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": "4.47.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

run-1/checkpoint-563/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2999c5c45ace354242376f2be90db4238a31117d3a08d6a1feb43fe0596f3f9e
+size 498625128

run-1/checkpoint-563/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dca027a35397ca14b602cf38277bd2d0cf8431351e372bf1ed202e14cdb5cad9
+size 997370106

run-1/checkpoint-563/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49348fa43bd53147898b45d0b95d766e80d34cb0478edbfadb78cb95f3ed5edb
+size 14244

run-1/checkpoint-563/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ed49c5af3789e22fc643ddfa776a4e4d1dac2c8b6d694f36fa76f1a6d6a6b58
+size 1064

run-1/checkpoint-563/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

run-1/checkpoint-563/tokenizer_config.json

@@ -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>"
+}

run-1/checkpoint-563/trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_metric": 0.5438473456606133,
+  "best_model_checkpoint": "students_scores_model/run-1/checkpoint-563",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 563,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8880994671403197,
+      "grad_norm": 16.69457244873047,
+      "learning_rate": 1.3821787207411013e-05,
+      "loss": 1.0782,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.5438473456606133,
+      "eval_loss": 1.0308393239974976,
+      "eval_runtime": 37.8021,
+      "eval_samples_per_second": 59.52,
+      "eval_steps_per_second": 7.46,
+      "step": 563
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1689,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 2104964038656000.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.9634145158382844e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "weight_decay": 0.000263763325616835
+  }
+}

run-1/checkpoint-563/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b1b930fb8e91788c965e2716a6235c673c8a487c662e9f94e1672503a85155c
+size 5368

runs/Dec08_12-21-15_6761a2862959/events.out.tfevents.1733660487.6761a2862959.23.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00c2318e753315a1905f9bb2becbea7ea931b00fc7136db0ab1c264a10451e49
-size 12961
+oid sha256:8f198186c0e0063b3b09937abca30965644f597513ea842031160dc05b2d0eb1
+size 13632

runs/Dec08_12-21-15_6761a2862959/events.out.tfevents.1733663495.6761a2862959.23.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a915c9485b999db47d9aa9ea6c9b18f77bc85bc4601516c3e673f7c6f91f0d9c
+size 5882

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:525778a4bf55e74b3e05d86fa160c25920ec80c82219483d314284448f6893fa
+oid sha256:4b1b930fb8e91788c965e2716a6235c673c8a487c662e9f94e1672503a85155c
 size 5368