Training in progress, step 1500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7f964c35bac9a5c234b0c6ac0756d1ea9936e34693f24a28718d70837f7ce34
+oid sha256:182372e908a835721b427839e2da1e9e210839bb5ee2f88f3a19dfe6ec75ee0c
 size 498609724

run-11/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-11/checkpoint-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:436b3634a15551f51ee6dcdc92bbdb255e5d35a86aed7fea84c4a726853957eb
+size 498609724

run-11/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d5c884f90561003d0e2d062680d8f0041274d948f13d2bad3181280aaa18948
+size 997339386

run-11/checkpoint-1000/rng_state.pth

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

run-11/checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66315aaff9f149f44e536ebaa1c9e144088aaf5ad1c79d946898e466a297f3bb
+size 1064

run-11/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-11/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-11/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": 0.6557157039642334,
+      "eval_loss": 0.5895818471908569,
+      "eval_runtime": 14.1651,
+      "eval_samples_per_second": 210.588,
+      "eval_steps_per_second": 13.201,
+      "step": 187
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6775058507919312,
+      "eval_loss": 0.560325026512146,
+      "eval_runtime": 13.2773,
+      "eval_samples_per_second": 224.67,
+      "eval_steps_per_second": 14.084,
+      "step": 374
+    },
+    {
+      "epoch": 2.6737967914438503,
+      "grad_norm": 7.770582675933838,
+      "learning_rate": 1.736336286304512e-05,
+      "loss": 0.566,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6842105388641357,
+      "eval_loss": 0.5659032464027405,
+      "eval_runtime": 16.7775,
+      "eval_samples_per_second": 177.797,
+      "eval_steps_per_second": 11.146,
+      "step": 561
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6932618021965027,
+      "eval_loss": 0.6125087141990662,
+      "eval_runtime": 16.7549,
+      "eval_samples_per_second": 178.038,
+      "eval_steps_per_second": 11.161,
+      "step": 748
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6982902884483337,
+      "eval_loss": 0.649093747138977,
+      "eval_runtime": 18.0748,
+      "eval_samples_per_second": 165.036,
+      "eval_steps_per_second": 10.346,
+      "step": 935
+    },
+    {
+      "epoch": 5.347593582887701,
+      "grad_norm": 15.092613220214844,
+      "learning_rate": 1.1026369117408215e-05,
+      "loss": 0.3717,
+      "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": 2.3700356608682024e-05,
+    "per_device_train_batch_size": 64
+  }
+}

run-11/checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7526746dcc3a30a7991bf296c74915c6df7cab992b3c5fd519172b14cd33a2d0
+size 5176

run-11/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-11/checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:182372e908a835721b427839e2da1e9e210839bb5ee2f88f3a19dfe6ec75ee0c
+size 498609724

run-11/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e32e37e60d6ebc5679827a731fd28a42fcfea4aad1a0eeb22352c81090d3129e
+size 997339386

run-11/checkpoint-1500/rng_state.pth

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

run-11/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0e6fa2adb134e11fd612f2c5467c2e1194191ddac87dd6d3efec2bdb5ec1bcb
+size 1064

run-11/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-11/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-11/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": 0.6557157039642334,
+      "eval_loss": 0.5895818471908569,
+      "eval_runtime": 14.1651,
+      "eval_samples_per_second": 210.588,
+      "eval_steps_per_second": 13.201,
+      "step": 187
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6775058507919312,
+      "eval_loss": 0.560325026512146,
+      "eval_runtime": 13.2773,
+      "eval_samples_per_second": 224.67,
+      "eval_steps_per_second": 14.084,
+      "step": 374
+    },
+    {
+      "epoch": 2.6737967914438503,
+      "grad_norm": 7.770582675933838,
+      "learning_rate": 1.736336286304512e-05,
+      "loss": 0.566,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6842105388641357,
+      "eval_loss": 0.5659032464027405,
+      "eval_runtime": 16.7775,
+      "eval_samples_per_second": 177.797,
+      "eval_steps_per_second": 11.146,
+      "step": 561
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6932618021965027,
+      "eval_loss": 0.6125087141990662,
+      "eval_runtime": 16.7549,
+      "eval_samples_per_second": 178.038,
+      "eval_steps_per_second": 11.161,
+      "step": 748
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6982902884483337,
+      "eval_loss": 0.649093747138977,
+      "eval_runtime": 18.0748,
+      "eval_samples_per_second": 165.036,
+      "eval_steps_per_second": 10.346,
+      "step": 935
+    },
+    {
+      "epoch": 5.347593582887701,
+      "grad_norm": 15.092613220214844,
+      "learning_rate": 1.1026369117408215e-05,
+      "loss": 0.3717,
+      "step": 1000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6969493627548218,
+      "eval_loss": 0.7359085083007812,
+      "eval_runtime": 17.6648,
+      "eval_samples_per_second": 168.867,
+      "eval_steps_per_second": 10.586,
+      "step": 1122
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6996312141418457,
+      "eval_loss": 0.8457220196723938,
+      "eval_runtime": 13.657,
+      "eval_samples_per_second": 218.422,
+      "eval_steps_per_second": 13.693,
+      "step": 1309
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6969493627548218,
+      "eval_loss": 0.9168502688407898,
+      "eval_runtime": 13.351,
+      "eval_samples_per_second": 223.428,
+      "eval_steps_per_second": 14.006,
+      "step": 1496
+    },
+    {
+      "epoch": 8.02139037433155,
+      "grad_norm": 8.993176460266113,
+      "learning_rate": 4.68937537177131e-06,
+      "loss": 0.2124,
+      "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": 2.3700356608682024e-05,
+    "per_device_train_batch_size": 64
+  }
+}

run-11/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7526746dcc3a30a7991bf296c74915c6df7cab992b3c5fd519172b14cd33a2d0
+size 5176

runs/Jun06_00-29-21_Donghao-Win/events.out.tfevents.1717633576.Donghao-Win.17160.11

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:874b7167a1a3906ca7f01d3effbff7d02ae8cb336a7ec3d79c5515d8de6e3a1b
-size 6906
+oid sha256:ce7bc6f39d821118307fe530f3b099296e0c9163d181e89a7359c6dee07727bd
+size 9086