Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebf1c8709e4c84480638b5de501a42eadc26eff6e9bc088eacc566ebf2294b3b
+oid sha256:3b8942857e211a95731077a8027b0affdc5035d609496dcefa7f8658d6a1300b
 size 498612824

run-7uvn2uod/checkpoint-5084/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "FacebookAI/roberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "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": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

run-7uvn2uod/checkpoint-5084/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b8942857e211a95731077a8027b0affdc5035d609496dcefa7f8658d6a1300b
+size 498612824

run-7uvn2uod/checkpoint-5084/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d208d3de7bb757b02fc3ae37e1fa0f72d9a1edb901c4fb7ac7000f80b37263ca
+size 997345530

run-7uvn2uod/checkpoint-5084/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d1e5a276585b90ace7c68f508c392ea3c08432e18220220eed0b213cc2092fd
+size 14180

run-7uvn2uod/checkpoint-5084/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5a44af5769bbf64a4d04adc535553b83f819e9478d8efd18e283bf7a0e5a0fa
+size 1064

run-7uvn2uod/checkpoint-5084/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

run-7uvn2uod/checkpoint-5084/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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",
+  "unk_token": "<unk>"
+}

run-7uvn2uod/checkpoint-5084/trainer_state.json

@@ -0,0 +1,122 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 5084,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "grad_norm": 7.054161071777344,
+      "learning_rate": 1.901652242328875e-05,
+      "loss": 0.3218,
+      "step": 500
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 7.846043109893799,
+      "learning_rate": 1.80330448465775e-05,
+      "loss": 0.2636,
+      "step": 1000
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 5.984105587005615,
+      "learning_rate": 1.704956726986625e-05,
+      "loss": 0.2468,
+      "step": 1500
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 7.812429428100586,
+      "learning_rate": 1.6066089693154998e-05,
+      "loss": 0.2288,
+      "step": 2000
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 9.041316986083984,
+      "learning_rate": 1.5082612116443747e-05,
+      "loss": 0.2095,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_Accuracy": 0.9143152226033713,
+      "eval_F1": 0.8864891277791351,
+      "eval_Precision": 0.8512575075075075,
+      "eval_Recall": 0.9247629727800999,
+      "eval_loss": 0.20487980544567108,
+      "eval_runtime": 101.5947,
+      "eval_samples_per_second": 266.855,
+      "eval_steps_per_second": 33.358,
+      "step": 2542
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 6.866842746734619,
+      "learning_rate": 1.4099134539732496e-05,
+      "loss": 0.1776,
+      "step": 3000
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 3.0877809524536133,
+      "learning_rate": 1.3115656963021243e-05,
+      "loss": 0.1573,
+      "step": 3500
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 11.298906326293945,
+      "learning_rate": 1.2132179386309992e-05,
+      "loss": 0.1545,
+      "step": 4000
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 8.85756778717041,
+      "learning_rate": 1.1148701809598743e-05,
+      "loss": 0.147,
+      "step": 4500
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 9.660445213317871,
+      "learning_rate": 1.0165224232887492e-05,
+      "loss": 0.1459,
+      "step": 5000
+    },
+    {
+      "epoch": 2.0,
+      "eval_Accuracy": 0.9448194459813359,
+      "eval_F1": 0.9239914642820852,
+      "eval_Precision": 0.9209966575508964,
+      "eval_Recall": 0.9270058109899072,
+      "eval_loss": 0.15434661507606506,
+      "eval_runtime": 104.2443,
+      "eval_samples_per_second": 260.072,
+      "eval_steps_per_second": 32.51,
+      "step": 5084
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10168,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 9115511290718880.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "_wandb": {},
+    "assignments": {},
+    "learning_rate": 2e-05,
+    "metric": "eval/loss",
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 32
+  }
+}

run-7uvn2uod/checkpoint-5084/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06f8a6df2707669f8bf7410296805436bef9ba0e56fe4a2df8ff7d0726d7f03e
+size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dde10c28a53365df9182bc3888d1f202abddeabc74f43518071c9ce1357949d
+oid sha256:06f8a6df2707669f8bf7410296805436bef9ba0e56fe4a2df8ff7d0726d7f03e
 size 4920