Training in progress, step 1500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13f8304572d65ad904d417efac86cde44a523cc835d6e334af1a1f17d0db4ce5
+oid sha256:d362c8e9030b0bd1703a71d0f73d5c91c00d45359af0be2ae70e072e92c486a4
 size 1340618660

run-13/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-13/checkpoint-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b48c0e49560e97bbc86694d07d686eb01c4830441d0072fda3a734aea4b920b
+size 1340618660

run-13/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7951b27efd0ce3f21931143393f3779a7d1bc932e29d0935f284a9d6a5ba767b
+size 2681472237

run-13/checkpoint-1000/rng_state.pth

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

run-13/checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1974a5c510a29a237b482369d92cd489c73aac40d5476d4dcdb1bee33ea682a5
+size 1064

run-13/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-13/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-13/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": 0.7609788775444031,
+      "eval_loss": 0.4698134660720825,
+      "eval_runtime": 8.8022,
+      "eval_samples_per_second": 338.891,
+      "eval_steps_per_second": 21.245,
+      "step": 187
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7733824849128723,
+      "eval_loss": 0.48511236906051636,
+      "eval_runtime": 8.9509,
+      "eval_samples_per_second": 333.262,
+      "eval_steps_per_second": 20.892,
+      "step": 374
+    },
+    {
+      "epoch": 2.6737967914438503,
+      "grad_norm": 6.67143440246582,
+      "learning_rate": 2.7825161779464667e-05,
+      "loss": 0.3435,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7784109711647034,
+      "eval_loss": 0.6542572975158691,
+      "eval_runtime": 8.8885,
+      "eval_samples_per_second": 335.602,
+      "eval_steps_per_second": 21.038,
+      "step": 561
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7700302004814148,
+      "eval_loss": 0.8408565521240234,
+      "eval_runtime": 8.9209,
+      "eval_samples_per_second": 334.385,
+      "eval_steps_per_second": 20.962,
+      "step": 748
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7720415592193604,
+      "eval_loss": 0.9585769772529602,
+      "eval_runtime": 8.9734,
+      "eval_samples_per_second": 332.426,
+      "eval_steps_per_second": 20.839,
+      "step": 935
+    },
+    {
+      "epoch": 5.347593582887701,
+      "grad_norm": 1.616738200187683,
+      "learning_rate": 1.766999324681333e-05,
+      "loss": 0.0517,
+      "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": 3.7980330312116e-05,
+    "per_device_train_batch_size": 64
+  }
+}

run-13/checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbf5ea618d805c38685d9ddf1ae439d729ef9017ac860777b339e70658397b5b
+size 5048

run-13/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-13/checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d362c8e9030b0bd1703a71d0f73d5c91c00d45359af0be2ae70e072e92c486a4
+size 1340618660

run-13/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bb2a19dcdaa1f63bbb6015b54dc0df865f713345422f045bcfbcecc8516c520
+size 2681472237

run-13/checkpoint-1500/rng_state.pth

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

run-13/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deb6745333a9375ff5fd554df891ffebc8bf4762163d95140683ca34e50e8e4e
+size 1064

run-13/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-13/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-13/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": 0.7609788775444031,
+      "eval_loss": 0.4698134660720825,
+      "eval_runtime": 8.8022,
+      "eval_samples_per_second": 338.891,
+      "eval_steps_per_second": 21.245,
+      "step": 187
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7733824849128723,
+      "eval_loss": 0.48511236906051636,
+      "eval_runtime": 8.9509,
+      "eval_samples_per_second": 333.262,
+      "eval_steps_per_second": 20.892,
+      "step": 374
+    },
+    {
+      "epoch": 2.6737967914438503,
+      "grad_norm": 6.67143440246582,
+      "learning_rate": 2.7825161779464667e-05,
+      "loss": 0.3435,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7784109711647034,
+      "eval_loss": 0.6542572975158691,
+      "eval_runtime": 8.8885,
+      "eval_samples_per_second": 335.602,
+      "eval_steps_per_second": 21.038,
+      "step": 561
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7700302004814148,
+      "eval_loss": 0.8408565521240234,
+      "eval_runtime": 8.9209,
+      "eval_samples_per_second": 334.385,
+      "eval_steps_per_second": 20.962,
+      "step": 748
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7720415592193604,
+      "eval_loss": 0.9585769772529602,
+      "eval_runtime": 8.9734,
+      "eval_samples_per_second": 332.426,
+      "eval_steps_per_second": 20.839,
+      "step": 935
+    },
+    {
+      "epoch": 5.347593582887701,
+      "grad_norm": 1.616738200187683,
+      "learning_rate": 1.766999324681333e-05,
+      "loss": 0.0517,
+      "step": 1000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7747234106063843,
+      "eval_loss": 0.9962263107299805,
+      "eval_runtime": 8.9033,
+      "eval_samples_per_second": 335.044,
+      "eval_steps_per_second": 21.003,
+      "step": 1122
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7747234106063843,
+      "eval_loss": 1.022032618522644,
+      "eval_runtime": 8.9866,
+      "eval_samples_per_second": 331.94,
+      "eval_steps_per_second": 20.809,
+      "step": 1309
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7690244913101196,
+      "eval_loss": 1.061006784439087,
+      "eval_runtime": 8.9852,
+      "eval_samples_per_second": 331.99,
+      "eval_steps_per_second": 20.812,
+      "step": 1496
+    },
+    {
+      "epoch": 8.02139037433155,
+      "grad_norm": 0.20956842601299286,
+      "learning_rate": 7.51482471416199e-06,
+      "loss": 0.0115,
+      "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": 3.7980330312116e-05,
+    "per_device_train_batch_size": 64
+  }
+}

run-13/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbf5ea618d805c38685d9ddf1ae439d729ef9017ac860777b339e70658397b5b
+size 5048