Training in progress, step 2500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34ad7fcc18694ecc94bcc97c5caa8ada81245713e9944319b5f05ffbeb7d97c7
+oid sha256:b36dd1f2edf990852c245f5ffbc464ad0e4e378d7c46407d9bda2cf79bd4786f
 size 1421491284

run-3/checkpoint-2000/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "roberta-large",
+  "architectures": [
+    "RobertaForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

run-3/checkpoint-2000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23695592eb752a9574d88fbc1f6224123e7eefe5aa72165fcbb44fffcc4cbd86
+size 1421491284

run-3/checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fce68afbe6bf797d68dc3c23e23d5820062e6e82b0aabaf23f186a79a9b1daf6
+size 2843215085

run-3/checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbb381a449d36d9eafe0476c182c2075cfdd8fa3b10ccea6591a7dde531518da
+size 14244

run-3/checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e10c648001cfd1c643004f70d6a635a9f743da4b3a9bede0d3e0e902709592c
+size 1064

run-3/checkpoint-2000/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

run-3/checkpoint-2000/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

run-3/checkpoint-2000/trainer_state.json

@@ -0,0 +1,97 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.361930294906166,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6443178057670593,
+      "eval_loss": 0.6200888156890869,
+      "eval_runtime": 9.4558,
+      "eval_samples_per_second": 315.469,
+      "eval_steps_per_second": 19.776,
+      "step": 373
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 11.498894691467285,
+      "learning_rate": 1.0365748013479516e-05,
+      "loss": 0.6738,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7539389729499817,
+      "eval_loss": 0.47277966141700745,
+      "eval_runtime": 9.3806,
+      "eval_samples_per_second": 317.998,
+      "eval_steps_per_second": 19.935,
+      "step": 746
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 9.671843528747559,
+      "learning_rate": 8.761143057832532e-06,
+      "loss": 0.4763,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7717063426971436,
+      "eval_loss": 0.5170367360115051,
+      "eval_runtime": 9.2678,
+      "eval_samples_per_second": 321.867,
+      "eval_steps_per_second": 20.177,
+      "step": 1119
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7787462472915649,
+      "eval_loss": 0.5018635392189026,
+      "eval_runtime": 9.2787,
+      "eval_samples_per_second": 321.49,
+      "eval_steps_per_second": 20.154,
+      "step": 1492
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 22.328227996826172,
+      "learning_rate": 7.156538102185547e-06,
+      "loss": 0.2904,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7800871729850769,
+      "eval_loss": 0.6816526651382446,
+      "eval_runtime": 9.2909,
+      "eval_samples_per_second": 321.068,
+      "eval_steps_per_second": 20.127,
+      "step": 1865
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 8.851292610168457,
+      "learning_rate": 5.551933146538564e-06,
+      "loss": 0.1552,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3730,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.1222931181027428e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.1970352969126499e-05,
+    "per_device_train_batch_size": 32
+  }
+}

run-3/checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:727738f55918307e08ad76d17a0ae75bcbb428e0ca4edd47d017bd972c0f5a21
+size 5048

run-3/checkpoint-2500/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "roberta-large",
+  "architectures": [
+    "RobertaForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

run-3/checkpoint-2500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b36dd1f2edf990852c245f5ffbc464ad0e4e378d7c46407d9bda2cf79bd4786f
+size 1421491284

run-3/checkpoint-2500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef8aa9d09b8dd4dcd902b702b3789bb262792220ed0933c86b8bcec369f004e7
+size 2843215085

run-3/checkpoint-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b5a7ca7ed33ad4adea3ef03b53fcfdcc68615f1d5a661797fd26a1d64e5bb70
+size 14244

run-3/checkpoint-2500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:266617ea136130790300735b2e44db2e8b95bb0dcf402ee70d84b988ea1397f9
+size 1064

run-3/checkpoint-2500/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

run-3/checkpoint-2500/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

run-3/checkpoint-2500/trainer_state.json

@@ -0,0 +1,113 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.702412868632708,
+  "eval_steps": 500,
+  "global_step": 2500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6443178057670593,
+      "eval_loss": 0.6200888156890869,
+      "eval_runtime": 9.4558,
+      "eval_samples_per_second": 315.469,
+      "eval_steps_per_second": 19.776,
+      "step": 373
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 11.498894691467285,
+      "learning_rate": 1.0365748013479516e-05,
+      "loss": 0.6738,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7539389729499817,
+      "eval_loss": 0.47277966141700745,
+      "eval_runtime": 9.3806,
+      "eval_samples_per_second": 317.998,
+      "eval_steps_per_second": 19.935,
+      "step": 746
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 9.671843528747559,
+      "learning_rate": 8.761143057832532e-06,
+      "loss": 0.4763,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7717063426971436,
+      "eval_loss": 0.5170367360115051,
+      "eval_runtime": 9.2678,
+      "eval_samples_per_second": 321.867,
+      "eval_steps_per_second": 20.177,
+      "step": 1119
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7787462472915649,
+      "eval_loss": 0.5018635392189026,
+      "eval_runtime": 9.2787,
+      "eval_samples_per_second": 321.49,
+      "eval_steps_per_second": 20.154,
+      "step": 1492
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 22.328227996826172,
+      "learning_rate": 7.156538102185547e-06,
+      "loss": 0.2904,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7800871729850769,
+      "eval_loss": 0.6816526651382446,
+      "eval_runtime": 9.2909,
+      "eval_samples_per_second": 321.068,
+      "eval_steps_per_second": 20.127,
+      "step": 1865
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 8.851292610168457,
+      "learning_rate": 5.551933146538564e-06,
+      "loss": 0.1552,
+      "step": 2000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.782433807849884,
+      "eval_loss": 0.8527898192405701,
+      "eval_runtime": 9.405,
+      "eval_samples_per_second": 317.172,
+      "eval_steps_per_second": 19.883,
+      "step": 2238
+    },
+    {
+      "epoch": 6.702412868632708,
+      "grad_norm": 20.3522891998291,
+      "learning_rate": 3.94732819089158e-06,
+      "loss": 0.1004,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3730,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.4022192353692968e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.1970352969126499e-05,
+    "per_device_train_batch_size": 32
+  }
+}

run-3/checkpoint-2500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:727738f55918307e08ad76d17a0ae75bcbb428e0ca4edd47d017bd972c0f5a21
+size 5048