Training in progress, step 1000

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fdd942e6407bd8e4d66630bd2665213892db3f8b8e096b626b54fba0dfb1419
+oid sha256:27f4bd6c713384ef6c330e4d9f3d6ed70e5bb9e915ae01b0c536ad0e30d5900e
 size 498609724

run-2/checkpoint-1000/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-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27f4bd6c713384ef6c330e4d9f3d6ed70e5bb9e915ae01b0c536ad0e30d5900e
+size 498609724

run-2/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72aff5d4f00de16e51ab37d1d38d313839283f0859a882d1b4fedb43a70232d5
+size 997339386

run-2/checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bf7fa3e4e47c1a94527580ecc5e7d9d5c4bf2d1f82605f00e3683c2aab1daf8
+size 14244

run-2/checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ef823b151c0f9bae9e60bd520f140c821f5bfd8e4d39b05c90098459d3a9b89
+size 1064

run-2/checkpoint-1000/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-1000/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-1000/trainer_state.json

@@ -0,0 +1,95 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.347593582887701,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "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
+    }
+  ],
+  "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": 3102926121226212.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.21786122536252e-06,
+    "per_device_train_batch_size": 64
+  }
+}

run-2/checkpoint-1000/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 sha256:02f5a646895a54aab9b49fe98d02b1186f2dcd8ccf053302b37664226c965072
-size 6047
+oid sha256:fea6efd746929dfde34d8de836234eeae42921ce85cf8f8e0dc38462290d51a3
+size 7227