Training in progress, step 6000

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:498d2da2ab31920cf0cd8bacea0c0c200dbe8e0fe068e052a803669c1ebb82f3
+oid sha256:93cbc8679a2da09c271459a443699fa855f8ec2f2b165892c3fc43a04f8b9c76
 size 1340618660

run-3/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-3/checkpoint-5000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d72c4c3ebc49e1cda5b89aeb688b23f066d4e160c650375c0492be4a809671a
+size 1340618660

run-3/checkpoint-5000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e136f4b7dede7c80164328ee3dc3dd5105e80c6d4bba5d9ecd405ca1b9f7dd71
+size 2681472237

run-3/checkpoint-5000/rng_state.pth

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

run-3/checkpoint-5000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b2aaceb7228dd7f7442f92a0426bb2545540287f469bf38eb7042c8f35f4aea
+size 1064

run-3/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-3/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-3/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": 1.8121609687805176,
+      "learning_rate": 4.400558387583305e-05,
+      "loss": 0.6264,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5072075128555298,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.1548,
+      "eval_samples_per_second": 325.839,
+      "eval_steps_per_second": 20.426,
+      "step": 746
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 1.8386740684509277,
+      "learning_rate": 4.0844263195097915e-05,
+      "loss": 0.7039,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.49882668256759644,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.1028,
+      "eval_samples_per_second": 327.702,
+      "eval_steps_per_second": 20.543,
+      "step": 1492
+    },
+    {
+      "epoch": 2.0107238605898123,
+      "grad_norm": 1.775593876838684,
+      "learning_rate": 3.768294251436278e-05,
+      "loss": 0.7008,
+      "step": 1500
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 1.6979082822799683,
+      "learning_rate": 3.452162183362765e-05,
+      "loss": 0.7034,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5015085339546204,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.1903,
+      "eval_samples_per_second": 324.583,
+      "eval_steps_per_second": 20.348,
+      "step": 2238
+    },
+    {
+      "epoch": 3.351206434316354,
+      "grad_norm": 1.7350631952285767,
+      "learning_rate": 3.136030115289252e-05,
+      "loss": 0.7017,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5065370202064514,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.2185,
+      "eval_samples_per_second": 323.589,
+      "eval_steps_per_second": 20.285,
+      "step": 2984
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 1.841038465499878,
+      "learning_rate": 2.8198980472157382e-05,
+      "loss": 0.7019,
+      "step": 3000
+    },
+    {
+      "epoch": 4.6916890080428955,
+      "grad_norm": 1.6272307634353638,
+      "learning_rate": 2.5037659791422253e-05,
+      "loss": 0.6994,
+      "step": 3500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5095541477203369,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.0976,
+      "eval_samples_per_second": 327.89,
+      "eval_steps_per_second": 20.555,
+      "step": 3730
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 1.7355244159698486,
+      "learning_rate": 2.1876339110687117e-05,
+      "loss": 0.7006,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.49446865916252136,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.0977,
+      "eval_samples_per_second": 327.885,
+      "eval_steps_per_second": 20.555,
+      "step": 4476
+    },
+    {
+      "epoch": 6.032171581769437,
+      "grad_norm": 1.6792231798171997,
+      "learning_rate": 1.8715018429951985e-05,
+      "loss": 0.7005,
+      "step": 4500
+    },
+    {
+      "epoch": 6.702412868632708,
+      "grad_norm": 1.7535431385040283,
+      "learning_rate": 1.5553697749216852e-05,
+      "loss": 0.701,
+      "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": 4.716690455656818e-05,
+    "per_device_train_batch_size": 16
+  }
+}

run-3/checkpoint-5000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0537522960a235b809ea329ec1396888a29088f8f8ec27bb9dbf5e7701ff29d
+size 5048

run-3/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-3/checkpoint-5500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1d0e62ad2bd743646ba78edee60d4bd33f164bfb34e83abea12f79cb3199ce4
+size 1340618660

run-3/checkpoint-5500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d42939335f7fe49d9409d3fc1d8b8d2ee2aa16d63c4f72a092140aed2c7a9c5
+size 2681472237

run-3/checkpoint-5500/rng_state.pth

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

run-3/checkpoint-5500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:874004cf5dcac57efb6829d0b47cc530c105993080dc83c1d534d285b51ad35c
+size 1064

run-3/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-3/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-3/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": 1.8121609687805176,
+      "learning_rate": 4.400558387583305e-05,
+      "loss": 0.6264,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5072075128555298,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.1548,
+      "eval_samples_per_second": 325.839,
+      "eval_steps_per_second": 20.426,
+      "step": 746
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 1.8386740684509277,
+      "learning_rate": 4.0844263195097915e-05,
+      "loss": 0.7039,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.49882668256759644,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.1028,
+      "eval_samples_per_second": 327.702,
+      "eval_steps_per_second": 20.543,
+      "step": 1492
+    },
+    {
+      "epoch": 2.0107238605898123,
+      "grad_norm": 1.775593876838684,
+      "learning_rate": 3.768294251436278e-05,
+      "loss": 0.7008,
+      "step": 1500
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 1.6979082822799683,
+      "learning_rate": 3.452162183362765e-05,
+      "loss": 0.7034,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5015085339546204,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.1903,
+      "eval_samples_per_second": 324.583,
+      "eval_steps_per_second": 20.348,
+      "step": 2238
+    },
+    {
+      "epoch": 3.351206434316354,
+      "grad_norm": 1.7350631952285767,
+      "learning_rate": 3.136030115289252e-05,
+      "loss": 0.7017,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5065370202064514,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.2185,
+      "eval_samples_per_second": 323.589,
+      "eval_steps_per_second": 20.285,
+      "step": 2984
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 1.841038465499878,
+      "learning_rate": 2.8198980472157382e-05,
+      "loss": 0.7019,
+      "step": 3000
+    },
+    {
+      "epoch": 4.6916890080428955,
+      "grad_norm": 1.6272307634353638,
+      "learning_rate": 2.5037659791422253e-05,
+      "loss": 0.6994,
+      "step": 3500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5095541477203369,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.0976,
+      "eval_samples_per_second": 327.89,
+      "eval_steps_per_second": 20.555,
+      "step": 3730
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 1.7355244159698486,
+      "learning_rate": 2.1876339110687117e-05,
+      "loss": 0.7006,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.49446865916252136,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.0977,
+      "eval_samples_per_second": 327.885,
+      "eval_steps_per_second": 20.555,
+      "step": 4476
+    },
+    {
+      "epoch": 6.032171581769437,
+      "grad_norm": 1.6792231798171997,
+      "learning_rate": 1.8715018429951985e-05,
+      "loss": 0.7005,
+      "step": 4500
+    },
+    {
+      "epoch": 6.702412868632708,
+      "grad_norm": 1.7535431385040283,
+      "learning_rate": 1.5553697749216852e-05,
+      "loss": 0.701,
+      "step": 5000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.4941334128379822,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.0431,
+      "eval_samples_per_second": 329.865,
+      "eval_steps_per_second": 20.679,
+      "step": 5222
+    },
+    {
+      "epoch": 7.372654155495979,
+      "grad_norm": 1.7443852424621582,
+      "learning_rate": 1.239237706848172e-05,
+      "loss": 0.7015,
+      "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": 4.716690455656818e-05,
+    "per_device_train_batch_size": 16
+  }
+}

run-3/checkpoint-5500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0537522960a235b809ea329ec1396888a29088f8f8ec27bb9dbf5e7701ff29d
+size 5048

run-3/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-3/checkpoint-6000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93cbc8679a2da09c271459a443699fa855f8ec2f2b165892c3fc43a04f8b9c76
+size 1340618660

run-3/checkpoint-6000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09d25c3a015f7433fc03d34f46f636d543fc37e05c7a200548e108107be9d3a7
+size 2681472237

run-3/checkpoint-6000/rng_state.pth

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

run-3/checkpoint-6000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:646dede8c2c66d6004063aa903371672a533a9e259d0095d047d1806dd636f01
+size 1064

run-3/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-3/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-3/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": 1.8121609687805176,
+      "learning_rate": 4.400558387583305e-05,
+      "loss": 0.6264,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5072075128555298,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.1548,
+      "eval_samples_per_second": 325.839,
+      "eval_steps_per_second": 20.426,
+      "step": 746
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 1.8386740684509277,
+      "learning_rate": 4.0844263195097915e-05,
+      "loss": 0.7039,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.49882668256759644,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.1028,
+      "eval_samples_per_second": 327.702,
+      "eval_steps_per_second": 20.543,
+      "step": 1492
+    },
+    {
+      "epoch": 2.0107238605898123,
+      "grad_norm": 1.775593876838684,
+      "learning_rate": 3.768294251436278e-05,
+      "loss": 0.7008,
+      "step": 1500
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 1.6979082822799683,
+      "learning_rate": 3.452162183362765e-05,
+      "loss": 0.7034,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5015085339546204,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.1903,
+      "eval_samples_per_second": 324.583,
+      "eval_steps_per_second": 20.348,
+      "step": 2238
+    },
+    {
+      "epoch": 3.351206434316354,
+      "grad_norm": 1.7350631952285767,
+      "learning_rate": 3.136030115289252e-05,
+      "loss": 0.7017,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5065370202064514,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.2185,
+      "eval_samples_per_second": 323.589,
+      "eval_steps_per_second": 20.285,
+      "step": 2984
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 1.841038465499878,
+      "learning_rate": 2.8198980472157382e-05,
+      "loss": 0.7019,
+      "step": 3000
+    },
+    {
+      "epoch": 4.6916890080428955,
+      "grad_norm": 1.6272307634353638,
+      "learning_rate": 2.5037659791422253e-05,
+      "loss": 0.6994,
+      "step": 3500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5095541477203369,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.0976,
+      "eval_samples_per_second": 327.89,
+      "eval_steps_per_second": 20.555,
+      "step": 3730
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 1.7355244159698486,
+      "learning_rate": 2.1876339110687117e-05,
+      "loss": 0.7006,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.49446865916252136,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.0977,
+      "eval_samples_per_second": 327.885,
+      "eval_steps_per_second": 20.555,
+      "step": 4476
+    },
+    {
+      "epoch": 6.032171581769437,
+      "grad_norm": 1.6792231798171997,
+      "learning_rate": 1.8715018429951985e-05,
+      "loss": 0.7005,
+      "step": 4500
+    },
+    {
+      "epoch": 6.702412868632708,
+      "grad_norm": 1.7535431385040283,
+      "learning_rate": 1.5553697749216852e-05,
+      "loss": 0.701,
+      "step": 5000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.4941334128379822,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.0431,
+      "eval_samples_per_second": 329.865,
+      "eval_steps_per_second": 20.679,
+      "step": 5222
+    },
+    {
+      "epoch": 7.372654155495979,
+      "grad_norm": 1.7443852424621582,
+      "learning_rate": 1.239237706848172e-05,
+      "loss": 0.7015,
+      "step": 5500
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.5122359991073608,
+      "eval_loss": 0.6931472420692444,
+      "eval_runtime": 9.0713,
+      "eval_samples_per_second": 328.839,
+      "eval_steps_per_second": 20.614,
+      "step": 5968
+    },
+    {
+      "epoch": 8.04289544235925,
+      "grad_norm": 1.6793931722640991,
+      "learning_rate": 9.231056387746587e-06,
+      "loss": 0.7003,
+      "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": 4.716690455656818e-05,
+    "per_device_train_batch_size": 16
+  }
+}

run-3/checkpoint-6000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0537522960a235b809ea329ec1396888a29088f8f8ec27bb9dbf5e7701ff29d
+size 5048