Training in progress, step 3500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2d3933289269a726f0b123167e1da1abf13bad2f687110964009440ff903590
+oid sha256:7e5abed5ff2656d9b8baf98f1e50bee83a34ed01ba6d99609bdef693eeb173f9
 size 1421491284

run-2/checkpoint-3000/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-2/checkpoint-3000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:041daced02bfdd73654d1fd952f35db6d7c3ccc388f35c3f3742b75a09112424
+size 1421491284

run-2/checkpoint-3000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3006fd0237e4842cd5d632b161fb6d587d6be1c5d6a313b561054b26ef4b13e
+size 2843215085

run-2/checkpoint-3000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39d877b28a8cd06c07aabb601fbd8f6ea1d4177967208aba352cb58683f5b319
+size 14244

run-2/checkpoint-3000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:127ebd4d681e1351553c093601197a1767e204925087d5320ad67efd4406e976
+size 1064

run-2/checkpoint-3000/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-2/checkpoint-3000/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-2/checkpoint-3000/trainer_state.json

@@ -0,0 +1,138 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.04289544235925,
+  "eval_steps": 500,
+  "global_step": 3000,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7680187821388245,
+      "eval_loss": 0.4622006416320801,
+      "eval_runtime": 9.5056,
+      "eval_samples_per_second": 313.816,
+      "eval_steps_per_second": 19.673,
+      "step": 373
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 21.834245681762695,
+      "learning_rate": 3.516708684536568e-06,
+      "loss": 0.5575,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7968488335609436,
+      "eval_loss": 0.4220982789993286,
+      "eval_runtime": 9.4241,
+      "eval_samples_per_second": 316.529,
+      "eval_steps_per_second": 19.843,
+      "step": 746
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 18.592424392700195,
+      "learning_rate": 2.972326535227502e-06,
+      "loss": 0.4016,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8162923455238342,
+      "eval_loss": 0.4073546528816223,
+      "eval_runtime": 9.4187,
+      "eval_samples_per_second": 316.71,
+      "eval_steps_per_second": 19.854,
+      "step": 1119
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8213208317756653,
+      "eval_loss": 0.4337773323059082,
+      "eval_runtime": 9.4694,
+      "eval_samples_per_second": 315.016,
+      "eval_steps_per_second": 19.748,
+      "step": 1492
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 26.7930850982666,
+      "learning_rate": 2.4279443859184353e-06,
+      "loss": 0.2956,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8246731758117676,
+      "eval_loss": 0.4652492105960846,
+      "eval_runtime": 9.4433,
+      "eval_samples_per_second": 315.885,
+      "eval_steps_per_second": 19.802,
+      "step": 1865
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 20.48050880432129,
+      "learning_rate": 1.8835622366093693e-06,
+      "loss": 0.2101,
+      "step": 2000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8236674666404724,
+      "eval_loss": 0.4927256107330322,
+      "eval_runtime": 9.3134,
+      "eval_samples_per_second": 320.292,
+      "eval_steps_per_second": 20.079,
+      "step": 2238
+    },
+    {
+      "epoch": 6.702412868632708,
+      "grad_norm": 23.84658432006836,
+      "learning_rate": 1.3391800873003031e-06,
+      "loss": 0.1735,
+      "step": 2500
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8250083923339844,
+      "eval_loss": 0.5141119360923767,
+      "eval_runtime": 9.2734,
+      "eval_samples_per_second": 321.672,
+      "eval_steps_per_second": 20.165,
+      "step": 2611
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.822996973991394,
+      "eval_loss": 0.5317586660385132,
+      "eval_runtime": 9.4667,
+      "eval_samples_per_second": 315.104,
+      "eval_steps_per_second": 19.753,
+      "step": 2984
+    },
+    {
+      "epoch": 8.04289544235925,
+      "grad_norm": 16.326515197753906,
+      "learning_rate": 7.947979379912367e-07,
+      "loss": 0.1395,
+      "step": 3000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3730,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.6826244219836316e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.0610908338456346e-06,
+    "per_device_train_batch_size": 32
+  }
+}

run-2/checkpoint-3000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cae059bfd0e893f604e76ac7260a76bc59dfcceeaa6b67fd62cc5af12c7e0649
+size 5048

run-2/checkpoint-3500/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-2/checkpoint-3500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e5abed5ff2656d9b8baf98f1e50bee83a34ed01ba6d99609bdef693eeb173f9
+size 1421491284

run-2/checkpoint-3500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d72f888a197c9a4c41f6f34d9d0ecdfefb4868f63c56db61e979ad816cfef18
+size 2843215085

run-2/checkpoint-3500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89fcfe9c1b5080b260fd4f680dbc672465e21ae3377576806ff2322f72cb0630
+size 14244

run-2/checkpoint-3500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ad50919a060bff2f99b4afa505b12cc6426b4d8af96388d996def99b45120cc
+size 1064

run-2/checkpoint-3500/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-2/checkpoint-3500/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-2/checkpoint-3500/trainer_state.json

@@ -0,0 +1,154 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.383378016085791,
+  "eval_steps": 500,
+  "global_step": 3500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7680187821388245,
+      "eval_loss": 0.4622006416320801,
+      "eval_runtime": 9.5056,
+      "eval_samples_per_second": 313.816,
+      "eval_steps_per_second": 19.673,
+      "step": 373
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 21.834245681762695,
+      "learning_rate": 3.516708684536568e-06,
+      "loss": 0.5575,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7968488335609436,
+      "eval_loss": 0.4220982789993286,
+      "eval_runtime": 9.4241,
+      "eval_samples_per_second": 316.529,
+      "eval_steps_per_second": 19.843,
+      "step": 746
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 18.592424392700195,
+      "learning_rate": 2.972326535227502e-06,
+      "loss": 0.4016,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8162923455238342,
+      "eval_loss": 0.4073546528816223,
+      "eval_runtime": 9.4187,
+      "eval_samples_per_second": 316.71,
+      "eval_steps_per_second": 19.854,
+      "step": 1119
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8213208317756653,
+      "eval_loss": 0.4337773323059082,
+      "eval_runtime": 9.4694,
+      "eval_samples_per_second": 315.016,
+      "eval_steps_per_second": 19.748,
+      "step": 1492
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 26.7930850982666,
+      "learning_rate": 2.4279443859184353e-06,
+      "loss": 0.2956,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8246731758117676,
+      "eval_loss": 0.4652492105960846,
+      "eval_runtime": 9.4433,
+      "eval_samples_per_second": 315.885,
+      "eval_steps_per_second": 19.802,
+      "step": 1865
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 20.48050880432129,
+      "learning_rate": 1.8835622366093693e-06,
+      "loss": 0.2101,
+      "step": 2000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8236674666404724,
+      "eval_loss": 0.4927256107330322,
+      "eval_runtime": 9.3134,
+      "eval_samples_per_second": 320.292,
+      "eval_steps_per_second": 20.079,
+      "step": 2238
+    },
+    {
+      "epoch": 6.702412868632708,
+      "grad_norm": 23.84658432006836,
+      "learning_rate": 1.3391800873003031e-06,
+      "loss": 0.1735,
+      "step": 2500
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8250083923339844,
+      "eval_loss": 0.5141119360923767,
+      "eval_runtime": 9.2734,
+      "eval_samples_per_second": 321.672,
+      "eval_steps_per_second": 20.165,
+      "step": 2611
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.822996973991394,
+      "eval_loss": 0.5317586660385132,
+      "eval_runtime": 9.4667,
+      "eval_samples_per_second": 315.104,
+      "eval_steps_per_second": 19.753,
+      "step": 2984
+    },
+    {
+      "epoch": 8.04289544235925,
+      "grad_norm": 16.326515197753906,
+      "learning_rate": 7.947979379912367e-07,
+      "loss": 0.1395,
+      "step": 3000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.825678825378418,
+      "eval_loss": 0.5802580714225769,
+      "eval_runtime": 9.4585,
+      "eval_samples_per_second": 315.378,
+      "eval_steps_per_second": 19.771,
+      "step": 3357
+    },
+    {
+      "epoch": 9.383378016085791,
+      "grad_norm": 32.17158126831055,
+      "learning_rate": 2.504157886821705e-07,
+      "loss": 0.1158,
+      "step": 3500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3730,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.9626746750006364e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.0610908338456346e-06,
+    "per_device_train_batch_size": 32
+  }
+}

run-2/checkpoint-3500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cae059bfd0e893f604e76ac7260a76bc59dfcceeaa6b67fd62cc5af12c7e0649
+size 5048