Training in progress, step 3000

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:995422e6b6f5cc92646ff702d1bfb16b759990290840e42942825b4ea0ca6efa
+oid sha256:fbc240f900b9dff13a08b0eb768f38ae5c151d5263ab02995c270ff946f97de5
 size 498609724

run-0/checkpoint-3000/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForMultipleChoice"
+  ],
+  "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,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

run-0/checkpoint-3000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbc240f900b9dff13a08b0eb768f38ae5c151d5263ab02995c270ff946f97de5
+size 498609724

run-0/checkpoint-3000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba18f6242551509fbc4158d2e375970d3bb23c4002bca3cf2dca7b148608c23e
+size 997339386

run-0/checkpoint-3000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2ef33be091b06b5b8c8f25173291bcd6e72d40e434a961d79e103faa1af3852
+size 14244

run-0/checkpoint-3000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11fc58d976a0e29f32453a6f2c41231b0902e1fb84be334d44df82a5b2bd7e23
+size 1064

run-0/checkpoint-3000/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-0/checkpoint-3000/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

run-0/checkpoint-3000/trainer_state.json

@@ -0,0 +1,150 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.04289544235925,
+  "eval_steps": 500,
+  "global_step": 3000,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6429768800735474,
+      "eval_loss": 0.5945129990577698,
+      "eval_runtime": 45.8254,
+      "eval_samples_per_second": 65.095,
+      "eval_steps_per_second": 4.081,
+      "step": 373
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 10.595976829528809,
+      "learning_rate": 8.574439800439004e-06,
+      "loss": 0.6212,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6778411269187927,
+      "eval_loss": 0.5707619786262512,
+      "eval_runtime": 45.8803,
+      "eval_samples_per_second": 65.017,
+      "eval_steps_per_second": 4.076,
+      "step": 746
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 11.34949779510498,
+      "learning_rate": 7.247127137832347e-06,
+      "loss": 0.5391,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6744887828826904,
+      "eval_loss": 0.5923792123794556,
+      "eval_runtime": 51.3582,
+      "eval_samples_per_second": 58.082,
+      "eval_steps_per_second": 3.641,
+      "step": 1119
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6761649250984192,
+      "eval_loss": 0.58919757604599,
+      "eval_runtime": 49.5338,
+      "eval_samples_per_second": 60.221,
+      "eval_steps_per_second": 3.775,
+      "step": 1492
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 10.796440124511719,
+      "learning_rate": 5.919814475225689e-06,
+      "loss": 0.4812,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.683875322341919,
+      "eval_loss": 0.6181617975234985,
+      "eval_runtime": 49.5046,
+      "eval_samples_per_second": 60.257,
+      "eval_steps_per_second": 3.777,
+      "step": 1865
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 20.43950653076172,
+      "learning_rate": 4.592501812619033e-06,
+      "loss": 0.4094,
+      "step": 2000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.690244734287262,
+      "eval_loss": 0.6364904642105103,
+      "eval_runtime": 49.2434,
+      "eval_samples_per_second": 60.577,
+      "eval_steps_per_second": 3.797,
+      "step": 2238
+    },
+    {
+      "epoch": 6.702412868632708,
+      "grad_norm": 15.7015962600708,
+      "learning_rate": 3.265189150012376e-06,
+      "loss": 0.3557,
+      "step": 2500
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.690244734287262,
+      "eval_loss": 0.6809911131858826,
+      "eval_runtime": 53.7724,
+      "eval_samples_per_second": 55.475,
+      "eval_steps_per_second": 3.478,
+      "step": 2611
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.687562882900238,
+      "eval_loss": 0.7227169871330261,
+      "eval_runtime": 48.2616,
+      "eval_samples_per_second": 61.809,
+      "eval_steps_per_second": 3.875,
+      "step": 2984
+    },
+    {
+      "epoch": 8.04289544235925,
+      "grad_norm": 21.409116744995117,
+      "learning_rate": 1.937876487405719e-06,
+      "loss": 0.3167,
+      "step": 3000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3730,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4358935077786780.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 9.90175246304566e-06,
+    "per_device_train_batch_size": 32
+  }
+}

run-0/checkpoint-3000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1c707689e4d63e47693f0038153b73ae05c4398571232f06530682e53de0a7e
+size 5176

runs/Jun06_00-29-21_Donghao-Win/events.out.tfevents.1717604983.Donghao-Win.17160.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf3b591229d2fc21b75791c56b5b5fd4be4317f7f5d0448178e30bfcdab0d45b
-size 7870
+oid sha256:6cef48301d3097263724d9cd6a8cb3f891a7fd030673c63daaf4945c510bb117
+size 8727