Training in progress, step 500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e4bc4e6782caf840d8d4ba5374b7eb867d39b10557e1dbc0b4dcb994788c7f3
+oid sha256:46c96230ac04c72b5de6f4625be6662aedf4e72b2820cac4fd205591d196a404
 size 1340618660

run-17/checkpoint-7000/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-large-uncased",
+  "architectures": [
+    "BertForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-17/checkpoint-7000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb98dba92c54d8deb8439a73fcb617af2d45d9554e9e0e23c27a5c8b725cfebe
+size 1340618660

run-17/checkpoint-7000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35d718d092d1d4c0800920192ca8e86a0023ddb4e30b13fe90407ef2fd8c00fe
+size 2681472237

run-17/checkpoint-7000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d9034b167dd57fcb13ab131f7a6b12c7467166bd3b6746d19284f0b0fe4a597
+size 14244

run-17/checkpoint-7000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c6026bf8ea3208dafc157a40e09ec34f9fecbcda4e16232befc033af24c03f6
+size 1064

run-17/checkpoint-7000/special_tokens_map.json

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

run-17/checkpoint-7000/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": true,
+  "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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-17/checkpoint-7000/trainer_state.json

@@ -0,0 +1,203 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.383378016085791,
+  "eval_steps": 500,
+  "global_step": 7000,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6702412868632708,
+      "grad_norm": 4.858139514923096,
+      "learning_rate": 1.2967014882299104e-05,
+      "loss": 0.5448,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7599731683731079,
+      "eval_loss": 0.47365400195121765,
+      "eval_runtime": 8.7869,
+      "eval_samples_per_second": 339.484,
+      "eval_steps_per_second": 21.282,
+      "step": 746
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 11.917668342590332,
+      "learning_rate": 1.2035476456846583e-05,
+      "loss": 0.4065,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7740529775619507,
+      "eval_loss": 0.5378448367118835,
+      "eval_runtime": 8.8702,
+      "eval_samples_per_second": 336.296,
+      "eval_steps_per_second": 21.082,
+      "step": 1492
+    },
+    {
+      "epoch": 2.0107238605898123,
+      "grad_norm": 4.923449516296387,
+      "learning_rate": 1.1103938031394061e-05,
+      "loss": 0.2909,
+      "step": 1500
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 19.094558715820312,
+      "learning_rate": 1.017239960594154e-05,
+      "loss": 0.1253,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7747234106063843,
+      "eval_loss": 0.8239175081253052,
+      "eval_runtime": 8.8415,
+      "eval_samples_per_second": 337.388,
+      "eval_steps_per_second": 21.15,
+      "step": 2238
+    },
+    {
+      "epoch": 3.351206434316354,
+      "grad_norm": 0.7371454238891602,
+      "learning_rate": 9.240861180489016e-06,
+      "loss": 0.0964,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7777405381202698,
+      "eval_loss": 0.9014805555343628,
+      "eval_runtime": 8.9037,
+      "eval_samples_per_second": 335.03,
+      "eval_steps_per_second": 21.003,
+      "step": 2984
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 7.040419578552246,
+      "learning_rate": 8.309322755036494e-06,
+      "loss": 0.0611,
+      "step": 3000
+    },
+    {
+      "epoch": 4.6916890080428955,
+      "grad_norm": 1.5264679193496704,
+      "learning_rate": 7.3777843295839734e-06,
+      "loss": 0.0316,
+      "step": 3500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7767348289489746,
+      "eval_loss": 1.0428067445755005,
+      "eval_runtime": 8.8373,
+      "eval_samples_per_second": 337.548,
+      "eval_steps_per_second": 21.16,
+      "step": 3730
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 2.159295082092285,
+      "learning_rate": 6.446245904131451e-06,
+      "loss": 0.0271,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7680187821388245,
+      "eval_loss": 0.9851073622703552,
+      "eval_runtime": 8.8821,
+      "eval_samples_per_second": 335.843,
+      "eval_steps_per_second": 21.053,
+      "step": 4476
+    },
+    {
+      "epoch": 6.032171581769437,
+      "grad_norm": 0.09014640748500824,
+      "learning_rate": 5.514707478678929e-06,
+      "loss": 0.0182,
+      "step": 4500
+    },
+    {
+      "epoch": 6.702412868632708,
+      "grad_norm": 0.0038544442504644394,
+      "learning_rate": 4.5831690532264075e-06,
+      "loss": 0.0095,
+      "step": 5000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7727120518684387,
+      "eval_loss": 1.1702251434326172,
+      "eval_runtime": 8.8067,
+      "eval_samples_per_second": 338.721,
+      "eval_steps_per_second": 21.234,
+      "step": 5222
+    },
+    {
+      "epoch": 7.372654155495979,
+      "grad_norm": 0.013897113502025604,
+      "learning_rate": 3.651630627773886e-06,
+      "loss": 0.0111,
+      "step": 5500
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7693597078323364,
+      "eval_loss": 1.145080804824829,
+      "eval_runtime": 8.8425,
+      "eval_samples_per_second": 337.347,
+      "eval_steps_per_second": 21.148,
+      "step": 5968
+    },
+    {
+      "epoch": 8.04289544235925,
+      "grad_norm": 0.015557339414954185,
+      "learning_rate": 2.7200922023213638e-06,
+      "loss": 0.0065,
+      "step": 6000
+    },
+    {
+      "epoch": 8.71313672922252,
+      "grad_norm": 2.5071191787719727,
+      "learning_rate": 1.788553776868842e-06,
+      "loss": 0.0071,
+      "step": 6500
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.7696949243545532,
+      "eval_loss": 1.2042195796966553,
+      "eval_runtime": 8.8395,
+      "eval_samples_per_second": 337.463,
+      "eval_steps_per_second": 21.155,
+      "step": 6714
+    },
+    {
+      "epoch": 9.383378016085791,
+      "grad_norm": 0.004412880167365074,
+      "learning_rate": 8.570153514163201e-07,
+      "loss": 0.0036,
+      "step": 7000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.9242668553904836e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.3898553307751626e-05,
+    "per_device_train_batch_size": 16
+  }
+}

run-17/checkpoint-7000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:503070edac2d16b2b33bbd599e65f370683d1669cf4a45aaa9b5d940a0fa779a
+size 5048

run-19/checkpoint-500/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-large-uncased",
+  "architectures": [
+    "BertForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-19/checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46c96230ac04c72b5de6f4625be6662aedf4e72b2820cac4fd205591d196a404
+size 1340618660

run-19/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc96a599084664add49541e71e49bc2b23b2fbf8b5a92c8d24b4f050d82ca40c
+size 2681472237

run-19/checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b39308b250b2dde21cca6217a709d5456bcdcab3c796c6926f25c06b9c730de1
+size 14244

run-19/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdb4a0a9cf6ac847c2247ca11f0dc82db21c047b0b0b75c2f25318228dbc547b
+size 1064

run-19/checkpoint-500/special_tokens_map.json

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

run-19/checkpoint-500/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": true,
+  "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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-19/checkpoint-500/trainer_state.json

@@ -0,0 +1,31 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6702412868632708,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6702412868632708,
+      "grad_norm": 4.357646942138672,
+      "learning_rate": 1.0524844447678954e-05,
+      "loss": 0.552,
+      "step": 500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 3210288839752032.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.1280939594782328e-05,
+    "per_device_train_batch_size": 16
+  }
+}

run-19/checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e8d635ff262d94e3653cb4692e65059af6f5ed4e3cfbd089131942e413b468c
+size 5048

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:503070edac2d16b2b33bbd599e65f370683d1669cf4a45aaa9b5d940a0fa779a
+oid sha256:3e8d635ff262d94e3653cb4692e65059af6f5ed4e3cfbd089131942e413b468c
 size 5048