Training in progress, step 1500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d91f8a42ae561d47c39b56b2bc7e1cd185bf0a92a15d925892dc36ce4e86723
+oid sha256:710c6ca415ba623d6243e0648033e3c96fa62b826fcff50001b8504f98f6b432
 size 1340618660

run-12/checkpoint-1000/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-12/checkpoint-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f2ee5459053adf74021d3c5a8b0f609dd8ed873e5821e4b66c292d5a80e2531
+size 1340618660

run-12/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62add1b82f0cf51f82b5e6c75562d9a4d0c22b687ab8af44f4f99e0201c4d781
+size 2681472237

run-12/checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2cdfcea7c19f545a5c3968413dcd70b32c860d464dd9abffbe95cff448fb946
+size 14244

run-12/checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c0ef164aa0097376053b925012e5a4e8e81ed279a9227efc71893a76b412a6e
+size 1064

run-12/checkpoint-1000/special_tokens_map.json

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

run-12/checkpoint-1000/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-12/checkpoint-1000/trainer_state.json

@@ -0,0 +1,83 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.347593582887701,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7512571215629578,
+      "eval_loss": 0.48031705617904663,
+      "eval_runtime": 8.8097,
+      "eval_samples_per_second": 338.604,
+      "eval_steps_per_second": 21.227,
+      "step": 187
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7616493701934814,
+      "eval_loss": 0.5087804198265076,
+      "eval_runtime": 8.9807,
+      "eval_samples_per_second": 332.158,
+      "eval_steps_per_second": 20.823,
+      "step": 374
+    },
+    {
+      "epoch": 2.6737967914438503,
+      "grad_norm": 8.481908798217773,
+      "learning_rate": 1.6199576132025075e-05,
+      "loss": 0.3779,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7686892151832581,
+      "eval_loss": 0.6262584328651428,
+      "eval_runtime": 8.8636,
+      "eval_samples_per_second": 336.547,
+      "eval_steps_per_second": 21.098,
+      "step": 561
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7653369307518005,
+      "eval_loss": 0.8179434537887573,
+      "eval_runtime": 8.9802,
+      "eval_samples_per_second": 332.177,
+      "eval_steps_per_second": 20.824,
+      "step": 748
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7693597078323364,
+      "eval_loss": 0.9568465948104858,
+      "eval_runtime": 8.9826,
+      "eval_samples_per_second": 332.086,
+      "eval_steps_per_second": 20.818,
+      "step": 935
+    },
+    {
+      "epoch": 5.347593582887701,
+      "grad_norm": 2.222888469696045,
+      "learning_rate": 1.0287322069242202e-05,
+      "loss": 0.0803,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1870,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.0895504027404356e+16,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.2111830194807948e-05,
+    "per_device_train_batch_size": 64
+  }
+}

run-12/checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94f8775f0fe4338594e1dacc56e91d8ca17472a641c2c429df8213c416ea5afa
+size 5048

run-12/checkpoint-1500/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-12/checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:710c6ca415ba623d6243e0648033e3c96fa62b826fcff50001b8504f98f6b432
+size 1340618660

run-12/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05ccac8907c745420e9cdf11fe38a32f33727ead780986c9f8dcfc471ae550b3
+size 2681472237

run-12/checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fff9554be5662c81dc5324c0ba82c1e4075d9a58be3ecf2692e8a0f7f508c509
+size 14244

run-12/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab9acf187ea97df66eab288cbc52a698e1dd688dbbf2a1491ce0c8f4d87e1044
+size 1064

run-12/checkpoint-1500/special_tokens_map.json

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

run-12/checkpoint-1500/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-12/checkpoint-1500/trainer_state.json

@@ -0,0 +1,117 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.02139037433155,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7512571215629578,
+      "eval_loss": 0.48031705617904663,
+      "eval_runtime": 8.8097,
+      "eval_samples_per_second": 338.604,
+      "eval_steps_per_second": 21.227,
+      "step": 187
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7616493701934814,
+      "eval_loss": 0.5087804198265076,
+      "eval_runtime": 8.9807,
+      "eval_samples_per_second": 332.158,
+      "eval_steps_per_second": 20.823,
+      "step": 374
+    },
+    {
+      "epoch": 2.6737967914438503,
+      "grad_norm": 8.481908798217773,
+      "learning_rate": 1.6199576132025075e-05,
+      "loss": 0.3779,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7686892151832581,
+      "eval_loss": 0.6262584328651428,
+      "eval_runtime": 8.8636,
+      "eval_samples_per_second": 336.547,
+      "eval_steps_per_second": 21.098,
+      "step": 561
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7653369307518005,
+      "eval_loss": 0.8179434537887573,
+      "eval_runtime": 8.9802,
+      "eval_samples_per_second": 332.177,
+      "eval_steps_per_second": 20.824,
+      "step": 748
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7693597078323364,
+      "eval_loss": 0.9568465948104858,
+      "eval_runtime": 8.9826,
+      "eval_samples_per_second": 332.086,
+      "eval_steps_per_second": 20.818,
+      "step": 935
+    },
+    {
+      "epoch": 5.347593582887701,
+      "grad_norm": 2.222888469696045,
+      "learning_rate": 1.0287322069242202e-05,
+      "loss": 0.0803,
+      "step": 1000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7670130729675293,
+      "eval_loss": 1.2737796306610107,
+      "eval_runtime": 8.967,
+      "eval_samples_per_second": 332.662,
+      "eval_steps_per_second": 20.854,
+      "step": 1122
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7727120518684387,
+      "eval_loss": 1.2703953981399536,
+      "eval_runtime": 8.9779,
+      "eval_samples_per_second": 332.261,
+      "eval_steps_per_second": 20.829,
+      "step": 1309
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7663425803184509,
+      "eval_loss": 1.2119802236557007,
+      "eval_runtime": 8.9795,
+      "eval_samples_per_second": 332.202,
+      "eval_steps_per_second": 20.825,
+      "step": 1496
+    },
+    {
+      "epoch": 8.02139037433155,
+      "grad_norm": 6.644580841064453,
+      "learning_rate": 4.3750680064593265e-06,
+      "loss": 0.023,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1870,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.6341528697599528e+16,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.2111830194807948e-05,
+    "per_device_train_batch_size": 64
+  }
+}

run-12/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94f8775f0fe4338594e1dacc56e91d8ca17472a641c2c429df8213c416ea5afa
+size 5048