Training in progress, step 5500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f5af69e38f44b092096fb6b1a7a98ee2cee043e1e415e684c5d1a36cd5b9127
+oid sha256:668eee6625b04cdf77f88804a40d928490781b7eeb81ffb044a7d533d81674b0
 size 1340618660

run-2/checkpoint-5000/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-2/checkpoint-5000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b944caab838363af1312066598b227dc90524048438e0cb63652693f54a996b
+size 1340618660

run-2/checkpoint-5000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11b26788be8d883956ce52debad2c73d4ec87fee219d9f4eac4d31b9a8ec9b69
+size 2681472237

run-2/checkpoint-5000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee6e7b4445fde26e96fc3b984ba0d561dd1184ebbc74ec417e69ac27afee388f
+size 14244

run-2/checkpoint-5000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79c4dcd3479a4256b04d2430ceb430f9112e9dbe4023fb4739e8cca030cad5e3
+size 1064

run-2/checkpoint-5000/special_tokens_map.json

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

run-2/checkpoint-5000/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-2/checkpoint-5000/trainer_state.json

@@ -0,0 +1,148 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.702412868632708,
+  "eval_steps": 500,
+  "global_step": 5000,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6702412868632708,
+      "grad_norm": 9.020133018493652,
+      "learning_rate": 1.4299394279479472e-06,
+      "loss": 0.6244,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7267851233482361,
+      "eval_loss": 0.5142917633056641,
+      "eval_runtime": 9.4466,
+      "eval_samples_per_second": 315.773,
+      "eval_steps_per_second": 19.795,
+      "step": 746
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 10.139765739440918,
+      "learning_rate": 1.3272138943309972e-06,
+      "loss": 0.5438,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7405296564102173,
+      "eval_loss": 0.49428224563598633,
+      "eval_runtime": 9.4794,
+      "eval_samples_per_second": 314.682,
+      "eval_steps_per_second": 19.727,
+      "step": 1492
+    },
+    {
+      "epoch": 2.0107238605898123,
+      "grad_norm": 7.425673961639404,
+      "learning_rate": 1.2244883607140467e-06,
+      "loss": 0.5108,
+      "step": 1500
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 8.044295310974121,
+      "learning_rate": 1.1217628270970966e-06,
+      "loss": 0.4787,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7468990683555603,
+      "eval_loss": 0.5006520748138428,
+      "eval_runtime": 9.5789,
+      "eval_samples_per_second": 311.415,
+      "eval_steps_per_second": 19.522,
+      "step": 2238
+    },
+    {
+      "epoch": 3.351206434316354,
+      "grad_norm": 19.568927764892578,
+      "learning_rate": 1.0190372934801463e-06,
+      "loss": 0.458,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7522628307342529,
+      "eval_loss": 0.49020281434059143,
+      "eval_runtime": 9.4558,
+      "eval_samples_per_second": 315.467,
+      "eval_steps_per_second": 19.776,
+      "step": 2984
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 5.546102046966553,
+      "learning_rate": 9.16311759863196e-07,
+      "loss": 0.4303,
+      "step": 3000
+    },
+    {
+      "epoch": 4.6916890080428955,
+      "grad_norm": 15.734197616577148,
+      "learning_rate": 8.135862262462459e-07,
+      "loss": 0.4115,
+      "step": 3500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7536037564277649,
+      "eval_loss": 0.5176616907119751,
+      "eval_runtime": 9.5583,
+      "eval_samples_per_second": 312.084,
+      "eval_steps_per_second": 19.564,
+      "step": 3730
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 15.1699857711792,
+      "learning_rate": 7.108606926292956e-07,
+      "loss": 0.401,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.755950391292572,
+      "eval_loss": 0.5166484713554382,
+      "eval_runtime": 9.6024,
+      "eval_samples_per_second": 310.652,
+      "eval_steps_per_second": 19.474,
+      "step": 4476
+    },
+    {
+      "epoch": 6.032171581769437,
+      "grad_norm": 15.72288990020752,
+      "learning_rate": 6.081351590123454e-07,
+      "loss": 0.3829,
+      "step": 4500
+    },
+    {
+      "epoch": 6.702412868632708,
+      "grad_norm": 9.840254783630371,
+      "learning_rate": 5.054096253953951e-07,
+      "loss": 0.3686,
+      "step": 5000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.303141432855536e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.5326649615648975e-06,
+    "per_device_train_batch_size": 16
+  }
+}

run-2/checkpoint-5000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9148e9896109331da2b7e9883edd81351654fb75b2cc6dc424bd2ba274c6c831
+size 5048

run-2/checkpoint-5500/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-2/checkpoint-5500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:668eee6625b04cdf77f88804a40d928490781b7eeb81ffb044a7d533d81674b0
+size 1340618660

run-2/checkpoint-5500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3a8b4e52ced45c2484ea918552fe25c14476f2669f0fd0e6463b472b276688f
+size 2681472237

run-2/checkpoint-5500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd4bd4443156419aea67e93c5b42b9fa93aaa633686043f4ecd36cb3df827a6e
+size 14244

run-2/checkpoint-5500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f6a67a398e7a064cc6e590fe7748e4fcb0e68fb8963ee510aa4e962efc563e0
+size 1064

run-2/checkpoint-5500/special_tokens_map.json

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

run-2/checkpoint-5500/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-2/checkpoint-5500/trainer_state.json

@@ -0,0 +1,164 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.372654155495979,
+  "eval_steps": 500,
+  "global_step": 5500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6702412868632708,
+      "grad_norm": 9.020133018493652,
+      "learning_rate": 1.4299394279479472e-06,
+      "loss": 0.6244,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7267851233482361,
+      "eval_loss": 0.5142917633056641,
+      "eval_runtime": 9.4466,
+      "eval_samples_per_second": 315.773,
+      "eval_steps_per_second": 19.795,
+      "step": 746
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 10.139765739440918,
+      "learning_rate": 1.3272138943309972e-06,
+      "loss": 0.5438,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7405296564102173,
+      "eval_loss": 0.49428224563598633,
+      "eval_runtime": 9.4794,
+      "eval_samples_per_second": 314.682,
+      "eval_steps_per_second": 19.727,
+      "step": 1492
+    },
+    {
+      "epoch": 2.0107238605898123,
+      "grad_norm": 7.425673961639404,
+      "learning_rate": 1.2244883607140467e-06,
+      "loss": 0.5108,
+      "step": 1500
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 8.044295310974121,
+      "learning_rate": 1.1217628270970966e-06,
+      "loss": 0.4787,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7468990683555603,
+      "eval_loss": 0.5006520748138428,
+      "eval_runtime": 9.5789,
+      "eval_samples_per_second": 311.415,
+      "eval_steps_per_second": 19.522,
+      "step": 2238
+    },
+    {
+      "epoch": 3.351206434316354,
+      "grad_norm": 19.568927764892578,
+      "learning_rate": 1.0190372934801463e-06,
+      "loss": 0.458,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7522628307342529,
+      "eval_loss": 0.49020281434059143,
+      "eval_runtime": 9.4558,
+      "eval_samples_per_second": 315.467,
+      "eval_steps_per_second": 19.776,
+      "step": 2984
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 5.546102046966553,
+      "learning_rate": 9.16311759863196e-07,
+      "loss": 0.4303,
+      "step": 3000
+    },
+    {
+      "epoch": 4.6916890080428955,
+      "grad_norm": 15.734197616577148,
+      "learning_rate": 8.135862262462459e-07,
+      "loss": 0.4115,
+      "step": 3500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7536037564277649,
+      "eval_loss": 0.5176616907119751,
+      "eval_runtime": 9.5583,
+      "eval_samples_per_second": 312.084,
+      "eval_steps_per_second": 19.564,
+      "step": 3730
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 15.1699857711792,
+      "learning_rate": 7.108606926292956e-07,
+      "loss": 0.401,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.755950391292572,
+      "eval_loss": 0.5166484713554382,
+      "eval_runtime": 9.6024,
+      "eval_samples_per_second": 310.652,
+      "eval_steps_per_second": 19.474,
+      "step": 4476
+    },
+    {
+      "epoch": 6.032171581769437,
+      "grad_norm": 15.72288990020752,
+      "learning_rate": 6.081351590123454e-07,
+      "loss": 0.3829,
+      "step": 4500
+    },
+    {
+      "epoch": 6.702412868632708,
+      "grad_norm": 9.840254783630371,
+      "learning_rate": 5.054096253953951e-07,
+      "loss": 0.3686,
+      "step": 5000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7596379518508911,
+      "eval_loss": 0.5389177799224854,
+      "eval_runtime": 9.5625,
+      "eval_samples_per_second": 311.946,
+      "eval_steps_per_second": 19.555,
+      "step": 5222
+    },
+    {
+      "epoch": 7.372654155495979,
+      "grad_norm": 13.200855255126953,
+      "learning_rate": 4.0268409177844495e-07,
+      "loss": 0.358,
+      "step": 5500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.4332422519482328e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.5326649615648975e-06,
+    "per_device_train_batch_size": 16
+  }
+}

run-2/checkpoint-5500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9148e9896109331da2b7e9883edd81351654fb75b2cc6dc424bd2ba274c6c831
+size 5048