Training in progress, step 237

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca30b503cbcdf7bebde29febe999d9a873526151ed24edc11be81a583e87a476
+oid sha256:21467a9de9236441169d1f3d8f496f4b5960ab2f6126931d110f356d90b3457d
 size 265470032

run-0/checkpoint-1565/config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForQuestionAnswering"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.1",
+  "vocab_size": 30522
+}

run-0/checkpoint-1565/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7ee7c03f1c8ba840df30c963d8d698bff69f3c6882c5158340a80e887d4d257
+size 265470032

run-0/checkpoint-1565/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e7f80b85a3dbd56de058832dca3d9b0970bdf95aa6bd1af3ad42d36c18fb28a
+size 531000890

run-0/checkpoint-1565/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c63a85546c2f2fc295ad5e4e85da8ee1a4eee0f497e56f83bd4bfe4140d099cc
+size 14308

run-0/checkpoint-1565/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00bd87d790f5b691d1876bcfe3bf2aaf788dde82ba984eec451498062a71c669
+size 1064

run-0/checkpoint-1565/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-0/checkpoint-1565/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-0/checkpoint-1565/trainer_state.json

@@ -0,0 +1,272 @@
+{
+  "best_metric": 3.1414525508880615,
+  "best_model_checkpoint": "qa_finetuning/run-0/checkpoint-1500",
+  "epoch": 5.0,
+  "eval_steps": 100,
+  "global_step": 1565,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3194888178913738,
+      "grad_norm": 4.872162818908691,
+      "learning_rate": 2.2236495574546495e-06,
+      "loss": 5.793,
+      "step": 100
+    },
+    {
+      "epoch": 0.3194888178913738,
+      "eval_loss": 5.499853610992432,
+      "eval_runtime": 3.4844,
+      "eval_samples_per_second": 143.499,
+      "eval_steps_per_second": 4.592,
+      "step": 100
+    },
+    {
+      "epoch": 0.6389776357827476,
+      "grad_norm": 5.640169620513916,
+      "learning_rate": 2.0718646047273696e-06,
+      "loss": 5.1611,
+      "step": 200
+    },
+    {
+      "epoch": 0.6389776357827476,
+      "eval_loss": 4.561793327331543,
+      "eval_runtime": 3.7947,
+      "eval_samples_per_second": 131.764,
+      "eval_steps_per_second": 4.216,
+      "step": 200
+    },
+    {
+      "epoch": 0.9584664536741214,
+      "grad_norm": 6.388542175292969,
+      "learning_rate": 1.9200796520000897e-06,
+      "loss": 4.4606,
+      "step": 300
+    },
+    {
+      "epoch": 0.9584664536741214,
+      "eval_loss": 4.023355960845947,
+      "eval_runtime": 3.583,
+      "eval_samples_per_second": 139.546,
+      "eval_steps_per_second": 4.465,
+      "step": 300
+    },
+    {
+      "epoch": 1.2779552715654952,
+      "grad_norm": 7.301818370819092,
+      "learning_rate": 1.76829469927281e-06,
+      "loss": 4.0751,
+      "step": 400
+    },
+    {
+      "epoch": 1.2779552715654952,
+      "eval_loss": 3.76656436920166,
+      "eval_runtime": 3.7005,
+      "eval_samples_per_second": 135.118,
+      "eval_steps_per_second": 4.324,
+      "step": 400
+    },
+    {
+      "epoch": 1.5974440894568689,
+      "grad_norm": 9.462298393249512,
+      "learning_rate": 1.61650974654553e-06,
+      "loss": 3.8854,
+      "step": 500
+    },
+    {
+      "epoch": 1.5974440894568689,
+      "eval_loss": 3.5879857540130615,
+      "eval_runtime": 3.6179,
+      "eval_samples_per_second": 138.201,
+      "eval_steps_per_second": 4.422,
+      "step": 500
+    },
+    {
+      "epoch": 1.9169329073482428,
+      "grad_norm": 10.335731506347656,
+      "learning_rate": 1.4647247938182503e-06,
+      "loss": 3.7085,
+      "step": 600
+    },
+    {
+      "epoch": 1.9169329073482428,
+      "eval_loss": 3.472351312637329,
+      "eval_runtime": 3.6946,
+      "eval_samples_per_second": 135.333,
+      "eval_steps_per_second": 4.331,
+      "step": 600
+    },
+    {
+      "epoch": 2.236421725239617,
+      "grad_norm": 14.032896995544434,
+      "learning_rate": 1.3129398410909704e-06,
+      "loss": 3.5566,
+      "step": 700
+    },
+    {
+      "epoch": 2.236421725239617,
+      "eval_loss": 3.368136405944824,
+      "eval_runtime": 3.6489,
+      "eval_samples_per_second": 137.027,
+      "eval_steps_per_second": 4.385,
+      "step": 700
+    },
+    {
+      "epoch": 2.5559105431309903,
+      "grad_norm": 17.996917724609375,
+      "learning_rate": 1.1611548883636908e-06,
+      "loss": 3.4447,
+      "step": 800
+    },
+    {
+      "epoch": 2.5559105431309903,
+      "eval_loss": 3.3015410900115967,
+      "eval_runtime": 3.6668,
+      "eval_samples_per_second": 136.358,
+      "eval_steps_per_second": 4.363,
+      "step": 800
+    },
+    {
+      "epoch": 2.8753993610223643,
+      "grad_norm": 15.922423362731934,
+      "learning_rate": 1.009369935636411e-06,
+      "loss": 3.4227,
+      "step": 900
+    },
+    {
+      "epoch": 2.8753993610223643,
+      "eval_loss": 3.2642431259155273,
+      "eval_runtime": 3.6623,
+      "eval_samples_per_second": 136.525,
+      "eval_steps_per_second": 4.369,
+      "step": 900
+    },
+    {
+      "epoch": 3.194888178913738,
+      "grad_norm": 19.34994125366211,
+      "learning_rate": 8.57584982909131e-07,
+      "loss": 3.3452,
+      "step": 1000
+    },
+    {
+      "epoch": 3.194888178913738,
+      "eval_loss": 3.2255563735961914,
+      "eval_runtime": 3.6578,
+      "eval_samples_per_second": 136.694,
+      "eval_steps_per_second": 4.374,
+      "step": 1000
+    },
+    {
+      "epoch": 3.5143769968051117,
+      "grad_norm": 15.923648834228516,
+      "learning_rate": 7.058000301818512e-07,
+      "loss": 3.3458,
+      "step": 1100
+    },
+    {
+      "epoch": 3.5143769968051117,
+      "eval_loss": 3.200777292251587,
+      "eval_runtime": 3.6881,
+      "eval_samples_per_second": 135.57,
+      "eval_steps_per_second": 4.338,
+      "step": 1100
+    },
+    {
+      "epoch": 3.8338658146964857,
+      "grad_norm": 13.226187705993652,
+      "learning_rate": 5.540150774545714e-07,
+      "loss": 3.2179,
+      "step": 1200
+    },
+    {
+      "epoch": 3.8338658146964857,
+      "eval_loss": 3.169455051422119,
+      "eval_runtime": 3.9818,
+      "eval_samples_per_second": 125.572,
+      "eval_steps_per_second": 4.018,
+      "step": 1200
+    },
+    {
+      "epoch": 4.15335463258786,
+      "grad_norm": 23.58437728881836,
+      "learning_rate": 4.0223012472729155e-07,
+      "loss": 3.2633,
+      "step": 1300
+    },
+    {
+      "epoch": 4.15335463258786,
+      "eval_loss": 3.1567466259002686,
+      "eval_runtime": 3.668,
+      "eval_samples_per_second": 136.314,
+      "eval_steps_per_second": 4.362,
+      "step": 1300
+    },
+    {
+      "epoch": 4.472843450479234,
+      "grad_norm": 15.142173767089844,
+      "learning_rate": 2.5044517200001173e-07,
+      "loss": 3.2125,
+      "step": 1400
+    },
+    {
+      "epoch": 4.472843450479234,
+      "eval_loss": 3.151430130004883,
+      "eval_runtime": 3.6873,
+      "eval_samples_per_second": 135.599,
+      "eval_steps_per_second": 4.339,
+      "step": 1400
+    },
+    {
+      "epoch": 4.792332268370607,
+      "grad_norm": 22.637807846069336,
+      "learning_rate": 9.866021927273189e-08,
+      "loss": 3.1618,
+      "step": 1500
+    },
+    {
+      "epoch": 4.792332268370607,
+      "eval_loss": 3.1414525508880615,
+      "eval_runtime": 3.6675,
+      "eval_samples_per_second": 136.332,
+      "eval_steps_per_second": 4.363,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1565,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2348620126175232.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.3754345101819293e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 31
+  }
+}

run-0/checkpoint-1565/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3ef1379406259e48f9c8943dd50b0a6da2c00398967a46798f218c876807a1f
+size 5176

run-1/checkpoint-237/config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForQuestionAnswering"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.1",
+  "vocab_size": 30522
+}

run-1/checkpoint-237/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21467a9de9236441169d1f3d8f496f4b5960ab2f6126931d110f356d90b3457d
+size 265470032

run-1/checkpoint-237/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:936880be91649f72461129c514360856e95c4e42e4dd310cbe768169bef4a1c8
+size 531000890

run-1/checkpoint-237/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82cd41eab9b7ca6d55195b647f839b7bd9327fbde21745a8ade66b325e401ade
+size 14244

run-1/checkpoint-237/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43c63f956bb78722837ae940ab6765dc5bd18b2c75d9f91fcf2d734177c08a4e
+size 1064

run-1/checkpoint-237/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-1/checkpoint-237/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-1/checkpoint-237/trainer_state.json

@@ -0,0 +1,77 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 100,
+  "global_step": 237,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.2658227848101267,
+      "grad_norm": 6.242897987365723,
+      "learning_rate": 8.287016016392707e-06,
+      "loss": 4.3828,
+      "step": 100
+    },
+    {
+      "epoch": 1.2658227848101267,
+      "eval_loss": 3.1804521083831787,
+      "eval_runtime": 3.6528,
+      "eval_samples_per_second": 136.88,
+      "eval_steps_per_second": 4.38,
+      "step": 100
+    },
+    {
+      "epoch": 2.5316455696202533,
+      "grad_norm": 11.491621017456055,
+      "learning_rate": 2.2380992161060595e-06,
+      "loss": 3.082,
+      "step": 200
+    },
+    {
+      "epoch": 2.5316455696202533,
+      "eval_loss": 2.6495375633239746,
+      "eval_runtime": 3.6891,
+      "eval_samples_per_second": 135.533,
+      "eval_steps_per_second": 4.337,
+      "step": 200
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 237,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1243294899904512.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.4335932816679354e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 32,
+    "seed": 9
+  }
+}

run-1/checkpoint-237/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adf95a1b40d7940f8a3f7af89bc534a9cafc9dabe2afeba003b8c21fddf5340e
+size 5176

runs/Nov18_10-11-09_aa151f0a91fc/events.out.tfevents.1731924671.aa151f0a91fc.1516.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f6146753d4f0fa6aebc3dc0cdda719d76aa12e11638ebd4f7b9e5bdb5a028a6
-size 12092
+oid sha256:72b07c1317461dea374ad73ec0cd403b12f36d1551449418b78acca63ed84b9c
+size 12446

runs/Nov18_10-11-09_aa151f0a91fc/events.out.tfevents.1731925305.aa151f0a91fc.1516.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd0c61414fc0cda5ad06b1aa4ed7dc16e97a306d2152475b9ab2b0eb5cc72cff
+size 6141

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3ef1379406259e48f9c8943dd50b0a6da2c00398967a46798f218c876807a1f
+oid sha256:adf95a1b40d7940f8a3f7af89bc534a9cafc9dabe2afeba003b8c21fddf5340e
 size 5176