Training in progress, step 1500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c3f66bcd3e45ab532104798704c694b95d2a47205095fe155f6a071ec89622
+oid sha256:60d78dd9e01f3278e43a8323935d1e3d02573b45655c7695375b6817458b47b0
 size 498609724

run-3/checkpoint-1500/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-3/checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60d78dd9e01f3278e43a8323935d1e3d02573b45655c7695375b6817458b47b0
+size 498609724

run-3/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54971f527913025f28e1667a29d535bdc54b32736e95d0fe727e39f576542185
+size 997339386

run-3/checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ff8784e5a5405efe69b28433ad99b57dc88013840ff7412944d366b1d65cf64
+size 14244

run-3/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b25de1832e06ee1cbff6db4dc9ab9deb1a0555c75a4b66f34da6f529b5b5e48b
+size 1064

run-3/checkpoint-1500/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-3/checkpoint-1500/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-3/checkpoint-1500/trainer_state.json

@@ -0,0 +1,129 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.02139037433155,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5695608258247375,
+      "eval_loss": 0.6931408643722534,
+      "eval_runtime": 14.7678,
+      "eval_samples_per_second": 201.994,
+      "eval_steps_per_second": 12.663,
+      "step": 187
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5115655660629272,
+      "eval_loss": 0.6931466460227966,
+      "eval_runtime": 14.1666,
+      "eval_samples_per_second": 210.566,
+      "eval_steps_per_second": 13.2,
+      "step": 374
+    },
+    {
+      "epoch": 2.6737967914438503,
+      "grad_norm": 0.5249342918395996,
+      "learning_rate": 6.592302596343259e-05,
+      "loss": 0.6952,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5340261459350586,
+      "eval_loss": 0.6931462287902832,
+      "eval_runtime": 18.3671,
+      "eval_samples_per_second": 162.41,
+      "eval_steps_per_second": 10.181,
+      "step": 561
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.451894074678421,
+      "eval_loss": 0.6931475400924683,
+      "eval_runtime": 17.1911,
+      "eval_samples_per_second": 173.52,
+      "eval_steps_per_second": 10.878,
+      "step": 748
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5494468808174133,
+      "eval_loss": 0.6931442022323608,
+      "eval_runtime": 16.5408,
+      "eval_samples_per_second": 180.341,
+      "eval_steps_per_second": 11.305,
+      "step": 935
+    },
+    {
+      "epoch": 5.347593582887701,
+      "grad_norm": 0.5341861844062805,
+      "learning_rate": 4.1863527436632376e-05,
+      "loss": 0.6948,
+      "step": 1000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.45390546321868896,
+      "eval_loss": 0.6931485533714294,
+      "eval_runtime": 17.1349,
+      "eval_samples_per_second": 174.09,
+      "eval_steps_per_second": 10.913,
+      "step": 1122
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5544753670692444,
+      "eval_loss": 0.6931463479995728,
+      "eval_runtime": 16.6506,
+      "eval_samples_per_second": 179.152,
+      "eval_steps_per_second": 11.231,
+      "step": 1309
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.5517935156822205,
+      "eval_loss": 0.6931464076042175,
+      "eval_runtime": 13.4695,
+      "eval_samples_per_second": 221.463,
+      "eval_steps_per_second": 13.883,
+      "step": 1496
+    },
+    {
+      "epoch": 8.02139037433155,
+      "grad_norm": 0.34662115573883057,
+      "learning_rate": 1.780402890983216e-05,
+      "loss": 0.6945,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1870,
+  "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": 4644506675442972.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 8.99825244902328e-05,
+    "per_device_train_batch_size": 64
+  }
+}

run-3/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4d466828f8a000e6daa05d4a59747aebe187056a210844bb8310b3913f02778
+size 5176

runs/Jun06_00-29-21_Donghao-Win/events.out.tfevents.1717617680.Donghao-Win.17160.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22af0e04c015c923ddd79c9f4a046dce3486223907e3069671af30dd06e8248b
-size 7227
+oid sha256:31469bf2b0b25a338179ea83bf206db3ca21453f6038b254b8648299dd3708ea
+size 8407