Training in progress, step 1500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27f4bd6c713384ef6c330e4d9f3d6ed70e5bb9e915ae01b0c536ad0e30d5900e
+oid sha256:1f00fab18e290620f4880e5fb3829cee3cd6d2b4dc548457319b9675937f5265
 size 498609724

run-2/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-2/checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f00fab18e290620f4880e5fb3829cee3cd6d2b4dc548457319b9675937f5265
+size 498609724

run-2/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f58d83edb1cb9afaa769878386b9d26ece244e6f2fb6105d0e3d99a41b9ef4bf
+size 997339386

run-2/checkpoint-1500/rng_state.pth

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

run-2/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcf9e1fd59ca807862a4ff3874d86268bf35ca8e1f70391f7e52338da54ccaae
+size 1064

run-2/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-2/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-2/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": 0.6087831258773804,
+      "eval_loss": 0.6791656017303467,
+      "eval_runtime": 14.2003,
+      "eval_samples_per_second": 210.065,
+      "eval_steps_per_second": 13.169,
+      "step": 187
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6238685846328735,
+      "eval_loss": 0.628938615322113,
+      "eval_runtime": 13.6649,
+      "eval_samples_per_second": 218.297,
+      "eval_steps_per_second": 13.685,
+      "step": 374
+    },
+    {
+      "epoch": 2.6737967914438503,
+      "grad_norm": 6.880990028381348,
+      "learning_rate": 1.624850202538317e-06,
+      "loss": 0.6611,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6315789222717285,
+      "eval_loss": 0.6185832619667053,
+      "eval_runtime": 16.7698,
+      "eval_samples_per_second": 177.88,
+      "eval_steps_per_second": 11.151,
+      "step": 561
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6366074681282043,
+      "eval_loss": 0.6134097576141357,
+      "eval_runtime": 18.0683,
+      "eval_samples_per_second": 165.096,
+      "eval_steps_per_second": 10.35,
+      "step": 748
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6406302452087402,
+      "eval_loss": 0.6063551306724548,
+      "eval_runtime": 13.3999,
+      "eval_samples_per_second": 222.614,
+      "eval_steps_per_second": 13.955,
+      "step": 935
+    },
+    {
+      "epoch": 5.347593582887701,
+      "grad_norm": 5.784094333648682,
+      "learning_rate": 1.0318391797141137e-06,
+      "loss": 0.611,
+      "step": 1000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6382836103439331,
+      "eval_loss": 0.604193389415741,
+      "eval_runtime": 17.7921,
+      "eval_samples_per_second": 167.658,
+      "eval_steps_per_second": 10.51,
+      "step": 1122
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.643647313117981,
+      "eval_loss": 0.6020446419715881,
+      "eval_runtime": 17.4668,
+      "eval_samples_per_second": 170.781,
+      "eval_steps_per_second": 10.706,
+      "step": 1309
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6429768800735474,
+      "eval_loss": 0.5997877717018127,
+      "eval_runtime": 13.9999,
+      "eval_samples_per_second": 213.073,
+      "eval_steps_per_second": 13.357,
+      "step": 1496
+    },
+    {
+      "epoch": 8.02139037433155,
+      "grad_norm": 5.9522199630737305,
+      "learning_rate": 4.3882815688991044e-07,
+      "loss": 0.5896,
+      "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": 2.21786122536252e-06,
+    "per_device_train_batch_size": 64
+  }
+}

run-2/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:688a4f0673592b957d4b22db69cc7a2dac63d0ed160802be872a1803d3816f89
+size 5176

runs/Jun06_00-29-21_Donghao-Win/events.out.tfevents.1717616366.Donghao-Win.17160.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fea6efd746929dfde34d8de836234eeae42921ce85cf8f8e0dc38462290d51a3
-size 7227
+oid sha256:af2f17004f62d03a4ee2f0a77dfaf07148de73ad058cb0fd5b147c1de87c535e
+size 8407