Training in progress, step 7000

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:668eee6625b04cdf77f88804a40d928490781b7eeb81ffb044a7d533d81674b0
+oid sha256:7a5c2e89a48f0f69015800fa93a8c495afcf988fd76206b993fa4c857c4f987f
 size 1340618660

run-2/checkpoint-6000/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-6000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b12ef5d7ab7756388743e4dae959d2cff5cffe9b18a33ec504ebc4f60e335e9d
+size 1340618660

run-2/checkpoint-6000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d7359a794c39468e1de90e6beb8411ec1e9bc583847c6c9cf445a7076aabaa4
+size 2681472237

run-2/checkpoint-6000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cb6c601562c14fd8f3b9d6b06f08a1bb52309eabe2bb4d684114b4d7a5fe8dc
+size 14244

run-2/checkpoint-6000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0539b5c2792180c9b832932971215f9c8713754af77ce6588438a6f5948169ff
+size 1064

run-2/checkpoint-6000/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-6000/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-6000/trainer_state.json

@@ -0,0 +1,180 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.04289544235925,
+  "eval_steps": 500,
+  "global_step": 6000,
+  "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
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.755950391292572,
+      "eval_loss": 0.562088131904602,
+      "eval_runtime": 9.4712,
+      "eval_samples_per_second": 314.955,
+      "eval_steps_per_second": 19.744,
+      "step": 5968
+    },
+    {
+      "epoch": 8.04289544235925,
+      "grad_norm": 15.2745361328125,
+      "learning_rate": 2.9995855816149467e-07,
+      "loss": 0.3402,
+      "step": 6000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.563011071614504e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.5326649615648975e-06,
+    "per_device_train_batch_size": 16
+  }
+}

run-2/checkpoint-6000/training_args.bin

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

run-2/checkpoint-6500/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-6500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2874ee4152315923053fb81055d01a27403fce4ce79fc51e5e0e98819f492919
+size 1340618660

run-2/checkpoint-6500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f7197a2589ad925379edbe3cbce7103d36cbceae6972f3204d12655573997dd
+size 2681472237

run-2/checkpoint-6500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1f6d894359f3e2243c392a48bf280d75a9d7da29d55346796c8f588e0ed80ca
+size 14244

run-2/checkpoint-6500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d436deda552ce6cfcefa1784ce6914ef580579b13a345f1b062775b00eebe315
+size 1064

run-2/checkpoint-6500/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-6500/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-6500/trainer_state.json

@@ -0,0 +1,187 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.71313672922252,
+  "eval_steps": 500,
+  "global_step": 6500,
+  "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
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.755950391292572,
+      "eval_loss": 0.562088131904602,
+      "eval_runtime": 9.4712,
+      "eval_samples_per_second": 314.955,
+      "eval_steps_per_second": 19.744,
+      "step": 5968
+    },
+    {
+      "epoch": 8.04289544235925,
+      "grad_norm": 15.2745361328125,
+      "learning_rate": 2.9995855816149467e-07,
+      "loss": 0.3402,
+      "step": 6000
+    },
+    {
+      "epoch": 8.71313672922252,
+      "grad_norm": 24.888896942138672,
+      "learning_rate": 1.9723302454454444e-07,
+      "loss": 0.3335,
+      "step": 6500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.6928810928603216e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.5326649615648975e-06,
+    "per_device_train_batch_size": 16
+  }
+}

run-2/checkpoint-6500/training_args.bin

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

run-2/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-2/checkpoint-7000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a5c2e89a48f0f69015800fa93a8c495afcf988fd76206b993fa4c857c4f987f
+size 1340618660

run-2/checkpoint-7000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc1637b8a2b2f2f2c4a0f82d01525e7189f2809e40fa5f6d07d2463691168fad
+size 2681472237

run-2/checkpoint-7000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e8822b3ce842a84ff93b4e9e34c5d6cc8389740adb793137e0de79524460bc4
+size 14244

run-2/checkpoint-7000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51c763270c183fef2248f247f1dfad938bcb08a2fa14d3bcd93e6ef6850622ee
+size 1064

run-2/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-2/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-2/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": 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
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.755950391292572,
+      "eval_loss": 0.562088131904602,
+      "eval_runtime": 9.4712,
+      "eval_samples_per_second": 314.955,
+      "eval_steps_per_second": 19.744,
+      "step": 5968
+    },
+    {
+      "epoch": 8.04289544235925,
+      "grad_norm": 15.2745361328125,
+      "learning_rate": 2.9995855816149467e-07,
+      "loss": 0.3402,
+      "step": 6000
+    },
+    {
+      "epoch": 8.71313672922252,
+      "grad_norm": 24.888896942138672,
+      "learning_rate": 1.9723302454454444e-07,
+      "loss": 0.3335,
+      "step": 6500
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.758632242679596,
+      "eval_loss": 0.5581969618797302,
+      "eval_runtime": 9.4627,
+      "eval_samples_per_second": 315.239,
+      "eval_steps_per_second": 19.762,
+      "step": 6714
+    },
+    {
+      "epoch": 9.383378016085791,
+      "grad_norm": 15.95915699005127,
+      "learning_rate": 9.450749092759422e-08,
+      "loss": 0.3302,
+      "step": 7000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.8226917764893548e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.5326649615648975e-06,
+    "per_device_train_batch_size": 16
+  }
+}

run-2/checkpoint-7000/training_args.bin

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