Training in progress, step 1500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32fbf9f24ae8e394ca797afae5157f62eb6cef86f71f6c1d52abc69cbb83d922
+oid sha256:485f35495cbf8ab5a39af89c3afb73f46620fbd55f4f6194a188efb0904cfa66
 size 498609724

run-12/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-12/checkpoint-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87bc1d861ef8f27e19f383d44af68861dcecdd5c6cf25a4068e273cb3ff49689
+size 498609724

run-12/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dd882a29b6322f884426b91be99b0c3f8077e72d310b3382f78e320aa91da47
+size 997339386

run-12/checkpoint-1000/rng_state.pth

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

run-12/checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49a0ac095ca6d0db7efdf2a9ddbfd8b30a6d2e32256d6fbe58a8a7173f27e9a6
+size 1064

run-12/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-12/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-12/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": 0.66376131772995,
+      "eval_loss": 0.5811143517494202,
+      "eval_runtime": 13.6891,
+      "eval_samples_per_second": 217.911,
+      "eval_steps_per_second": 13.661,
+      "step": 187
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.687562882900238,
+      "eval_loss": 0.5562570095062256,
+      "eval_runtime": 13.6754,
+      "eval_samples_per_second": 218.129,
+      "eval_steps_per_second": 13.674,
+      "step": 374
+    },
+    {
+      "epoch": 2.6737967914438503,
+      "grad_norm": 6.280329704284668,
+      "learning_rate": 1.9434783770908435e-05,
+      "loss": 0.56,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.683875322341919,
+      "eval_loss": 0.5756075382232666,
+      "eval_runtime": 17.9603,
+      "eval_samples_per_second": 166.089,
+      "eval_steps_per_second": 10.412,
+      "step": 561
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6956084370613098,
+      "eval_loss": 0.625312089920044,
+      "eval_runtime": 17.3889,
+      "eval_samples_per_second": 171.547,
+      "eval_steps_per_second": 10.754,
+      "step": 748
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.702983558177948,
+      "eval_loss": 0.6639668941497803,
+      "eval_runtime": 16.6459,
+      "eval_samples_per_second": 179.203,
+      "eval_steps_per_second": 11.234,
+      "step": 935
+    },
+    {
+      "epoch": 5.347593582887701,
+      "grad_norm": 12.349366188049316,
+      "learning_rate": 1.2341796993204627e-05,
+      "loss": 0.3526,
+      "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": 2.6527770548612244e-05,
+    "per_device_train_batch_size": 64
+  }
+}

run-12/checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:652c372a6998524698fb60b277c46157fb475b3da83745a748403e9bf636ebf0
+size 5176

run-12/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-12/checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:485f35495cbf8ab5a39af89c3afb73f46620fbd55f4f6194a188efb0904cfa66
+size 498609724

run-12/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86a8149965884168e1992fb10d79845f9f8d41d904a9733749c699bc11e3a23e
+size 997339386

run-12/checkpoint-1500/rng_state.pth

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

run-12/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59baf716efd055d2393d5e184ce48f708478480af2c36feec9023917bb0b4d82
+size 1064

run-12/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-12/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-12/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": 0.66376131772995,
+      "eval_loss": 0.5811143517494202,
+      "eval_runtime": 13.6891,
+      "eval_samples_per_second": 217.911,
+      "eval_steps_per_second": 13.661,
+      "step": 187
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.687562882900238,
+      "eval_loss": 0.5562570095062256,
+      "eval_runtime": 13.6754,
+      "eval_samples_per_second": 218.129,
+      "eval_steps_per_second": 13.674,
+      "step": 374
+    },
+    {
+      "epoch": 2.6737967914438503,
+      "grad_norm": 6.280329704284668,
+      "learning_rate": 1.9434783770908435e-05,
+      "loss": 0.56,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.683875322341919,
+      "eval_loss": 0.5756075382232666,
+      "eval_runtime": 17.9603,
+      "eval_samples_per_second": 166.089,
+      "eval_steps_per_second": 10.412,
+      "step": 561
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6956084370613098,
+      "eval_loss": 0.625312089920044,
+      "eval_runtime": 17.3889,
+      "eval_samples_per_second": 171.547,
+      "eval_steps_per_second": 10.754,
+      "step": 748
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.702983558177948,
+      "eval_loss": 0.6639668941497803,
+      "eval_runtime": 16.6459,
+      "eval_samples_per_second": 179.203,
+      "eval_steps_per_second": 11.234,
+      "step": 935
+    },
+    {
+      "epoch": 5.347593582887701,
+      "grad_norm": 12.349366188049316,
+      "learning_rate": 1.2341796993204627e-05,
+      "loss": 0.3526,
+      "step": 1000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7033188343048096,
+      "eval_loss": 0.778536319732666,
+      "eval_runtime": 18.169,
+      "eval_samples_per_second": 164.18,
+      "eval_steps_per_second": 10.292,
+      "step": 1122
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6999664902687073,
+      "eval_loss": 0.8368160128593445,
+      "eval_runtime": 21.9874,
+      "eval_samples_per_second": 135.668,
+      "eval_steps_per_second": 8.505,
+      "step": 1309
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.701642632484436,
+      "eval_loss": 0.9104980826377869,
+      "eval_runtime": 13.652,
+      "eval_samples_per_second": 218.503,
+      "eval_steps_per_second": 13.698,
+      "step": 1496
+    },
+    {
+      "epoch": 8.02139037433155,
+      "grad_norm": 14.8399658203125,
+      "learning_rate": 5.248810215500818e-06,
+      "loss": 0.1973,
+      "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": 2.6527770548612244e-05,
+    "per_device_train_batch_size": 64
+  }
+}

run-12/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:652c372a6998524698fb60b277c46157fb475b3da83745a748403e9bf636ebf0
+size 5176

runs/Jun06_00-29-21_Donghao-Win/events.out.tfevents.1717635227.Donghao-Win.17160.12

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b75ccfda953302c8520e42b3b6a23faed7fa71ad61703dc72264c8c5259eadd
-size 6906
+oid sha256:49d7538e595e369ca699cc516e6fe3d9a80e75283e8cc549e65cbb5c0399ad83
+size 9086