Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3da82207b392e8f05a0dbdc7c2d34132095b3a67a17fa5c60c1e45bda6db4174
+oid sha256:2f8d72cdb20e20ec81ad6b4dbce29327e4016adc4cba69888b1eae6bcb8dcaba
 size 498625128

run-4/checkpoint-1689/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-4/checkpoint-1689/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f8d72cdb20e20ec81ad6b4dbce29327e4016adc4cba69888b1eae6bcb8dcaba
+size 498625128

run-4/checkpoint-1689/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:156fcd99a3517015a4749b7026217ddfcd3ccc2b97673323f6c51b290274f188
+size 997370106

run-4/checkpoint-1689/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:071c5e9be8c89f7e7601ef6e67c044701f3e899071b5431a452dcbeb2c3af0a4
+size 14244

run-4/checkpoint-1689/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c04129761359fe928c486f7b91c7c3a0b9f60d1cb89350c84707fee66fd2e95a
+size 1064

run-4/checkpoint-1689/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-4/checkpoint-1689/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-4/checkpoint-1689/trainer_state.json

@@ -0,0 +1,86 @@
+{
+  "best_metric": 0.6268681418752026,
+  "best_model_checkpoint": "students_scores_model/run-4/checkpoint-1126",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1689,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8880994671403197,
+      "grad_norm": 12.275317192077637,
+      "learning_rate": 1.4598246141554418e-05,
+      "loss": 1.0768,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.5337342004113407,
+      "eval_loss": 1.0920056104660034,
+      "eval_runtime": 37.5701,
+      "eval_samples_per_second": 59.888,
+      "eval_steps_per_second": 7.506,
+      "step": 563
+    },
+    {
+      "epoch": 1.7761989342806395,
+      "grad_norm": 22.032495498657227,
+      "learning_rate": 1.1445277212492988e-05,
+      "loss": 0.881,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.6268681418752026,
+      "eval_loss": 0.8564010858535767,
+      "eval_runtime": 37.4689,
+      "eval_samples_per_second": 60.05,
+      "eval_steps_per_second": 7.526,
+      "step": 1126
+    },
+    {
+      "epoch": 2.664298401420959,
+      "grad_norm": 14.71834945678711,
+      "learning_rate": 8.29230828343156e-06,
+      "loss": 0.775,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.5967192597885715,
+      "eval_loss": 0.9332024455070496,
+      "eval_runtime": 37.6856,
+      "eval_samples_per_second": 59.705,
+      "eval_steps_per_second": 7.483,
+      "step": 1689
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2815,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 6310155946881024.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.7751215070615847e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "weight_decay": 0.0002884204184667258
+  }
+}

run-4/checkpoint-1689/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a62e1f6a90ed4f39459c087d00d082ce1ebfa6be7f9d0f437b408dd861a50103
+size 5368

runs/Dec08_21-54-18_6ff5f1d99a72/events.out.tfevents.1733700639.6ff5f1d99a72.23.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5192a84440dff153d418b06619596ab55ee5617aff4b77c9627dd39885a2a261
-size 6411
+oid sha256:7878b6850f58c498407fb5673dc5e4ffbf61e2dfc7b5c7dc20925b79624783e0
+size 6939