Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:728857b3c80e63abbfacca10d1f25711a2e4fe2c73c47eb51aafe5d590b57ccc
+oid sha256:4e8042e8a66f779111574edb23e8d5c38834f4cacdb9af33887881eabf06c385
 size 498625128

run-2/checkpoint-564/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-2/checkpoint-564/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e8042e8a66f779111574edb23e8d5c38834f4cacdb9af33887881eabf06c385
+size 498625128

run-2/checkpoint-564/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:833abf2e23baab43469bf7282f52f6e13902a574e8528f912d771b88defd198c
+size 997370106

run-2/checkpoint-564/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b99d4651e5b9b77475812868d3a6b49436d527964ed98dfb1718b7fe878ae78
+size 14244

run-2/checkpoint-564/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24e4d5dbef331533ce0b6d9eae278e064359e90705ddd2a51dc79103f3942777
+size 1064

run-2/checkpoint-564/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-2/checkpoint-564/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-2/checkpoint-564/trainer_state.json

@@ -0,0 +1,63 @@
+{
+  "best_metric": 0.597013961740708,
+  "best_model_checkpoint": "students_scores_model/run-2/checkpoint-564",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 564,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.5280922046056804,
+      "eval_loss": 1.0346653461456299,
+      "eval_runtime": 37.6542,
+      "eval_samples_per_second": 59.754,
+      "eval_steps_per_second": 7.489,
+      "step": 282
+    },
+    {
+      "epoch": 1.773049645390071,
+      "grad_norm": 15.857311248779297,
+      "learning_rate": 4.500003283675112e-06,
+      "loss": 1.0255,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.597013961740708,
+      "eval_loss": 0.9119309782981873,
+      "eval_runtime": 37.6531,
+      "eval_samples_per_second": 59.756,
+      "eval_steps_per_second": 7.489,
+      "step": 564
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 846,
+  "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": 4203350064691200.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.1002898202280765e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 32,
+    "weight_decay": 0.008293142825111385
+  }
+}

run-2/checkpoint-564/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92eed261d071d88405c0cc7cdc0b8eceb2628d134f07932409e8529a92610828
+size 5368

runs/Dec08_21-54-18_6ff5f1d99a72/events.out.tfevents.1733697267.6ff5f1d99a72.23.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b4da3604c035e0fcb7a604e4fe47408defad95dc293db84af1e5f4fa9d32fcb
-size 5671
+oid sha256:8652c102ac90b4e7dea4324a91e066e47960d14c67685864f781c9ec2ee6315b
+size 6199