Training in progress, step 1500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2881f18b343cdd427fc66fc2cce8cec9de1a369fe5d3daa6a1163851301aac6d
+oid sha256:a4e8216b4bd112f4ed16a59512dca9cd037abdd6604ad814b94db4b98d881fdf
 size 1340618660

run-0/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-0/checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4e8216b4bd112f4ed16a59512dca9cd037abdd6604ad814b94db4b98d881fdf
+size 1340618660

run-0/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d52e0a0e2f9de699b2edbbbfc6fdf2cec0e9e886a5275bbe603e13a03ea2a5da
+size 2681472237

run-0/checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02726484d0368608126b4b623e8a9dca0feeef64e1c28760438804747f801dfd
+size 14244

run-0/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ffe8c3042419912798e897252d0e20cac6cbffbbdf307bf8ee4796ded1cbb71
+size 1064

run-0/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-0/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-0/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": 0.7532685399055481,
+      "eval_loss": 0.4793490469455719,
+      "eval_runtime": 9.3602,
+      "eval_samples_per_second": 318.688,
+      "eval_steps_per_second": 19.978,
+      "step": 187
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7790814638137817,
+      "eval_loss": 0.4668562114238739,
+      "eval_runtime": 9.4916,
+      "eval_samples_per_second": 314.277,
+      "eval_steps_per_second": 19.702,
+      "step": 374
+    },
+    {
+      "epoch": 2.6737967914438503,
+      "grad_norm": 9.970394134521484,
+      "learning_rate": 1.0116255710136231e-05,
+      "loss": 0.4413,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7790814638137817,
+      "eval_loss": 0.5445067882537842,
+      "eval_runtime": 9.4939,
+      "eval_samples_per_second": 314.202,
+      "eval_steps_per_second": 19.697,
+      "step": 561
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7700302004814148,
+      "eval_loss": 0.6839850544929504,
+      "eval_runtime": 9.4969,
+      "eval_samples_per_second": 314.101,
+      "eval_steps_per_second": 19.691,
+      "step": 748
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7680187821388245,
+      "eval_loss": 0.7934393286705017,
+      "eval_runtime": 9.5009,
+      "eval_samples_per_second": 313.97,
+      "eval_steps_per_second": 19.682,
+      "step": 935
+    },
+    {
+      "epoch": 5.347593582887701,
+      "grad_norm": 6.287047863006592,
+      "learning_rate": 6.424191582349286e-06,
+      "loss": 0.1515,
+      "step": 1000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7730472683906555,
+      "eval_loss": 0.7747542262077332,
+      "eval_runtime": 9.4572,
+      "eval_samples_per_second": 315.421,
+      "eval_steps_per_second": 19.773,
+      "step": 1122
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7700302004814148,
+      "eval_loss": 0.8394743800163269,
+      "eval_runtime": 9.6279,
+      "eval_samples_per_second": 309.83,
+      "eval_steps_per_second": 19.423,
+      "step": 1309
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7717063426971436,
+      "eval_loss": 0.8363062143325806,
+      "eval_runtime": 9.6181,
+      "eval_samples_per_second": 310.145,
+      "eval_steps_per_second": 19.443,
+      "step": 1496
+    },
+    {
+      "epoch": 8.02139037433155,
+      "grad_norm": 7.763587474822998,
+      "learning_rate": 2.73212745456234e-06,
+      "loss": 0.0648,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1870,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.7577443886948468e+16,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.3808319837923177e-05,
+    "per_device_train_batch_size": 64
+  }
+}

run-0/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feac2daf058c7e56243ee3aa074f41715308b943716dfb58c6ab30c00c466ccf
+size 5048