Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7c8ef2b86376232500ff9940c361d0544acac23c33e5419a7f6a7e3956528b7
+oid sha256:89a707838234df27816026cd36bf731d3d30b127c0fb559639a06f337e089a8b
 size 498612824

run-y29l1u2z/checkpoint-10168/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-y29l1u2z/checkpoint-10168/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89a707838234df27816026cd36bf731d3d30b127c0fb559639a06f337e089a8b
+size 498612824

run-y29l1u2z/checkpoint-10168/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab4e7ca2b34d2607cba7ca4374f65661e85f19f6e9f28229e24e74657335a59a
+size 997345530

run-y29l1u2z/checkpoint-10168/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2aa970ebd6a3406ad3025be295f048dba477be80f059fbeb69b964105d26234
+size 14244

run-y29l1u2z/checkpoint-10168/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17381c622b20031ad66cafdb50182137eb2b6c81d3169346c2e386103c7f7fbf
+size 1064

run-y29l1u2z/checkpoint-10168/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-y29l1u2z/checkpoint-10168/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-y29l1u2z/checkpoint-10168/trainer_state.json

@@ -0,0 +1,192 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 10168,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "grad_norm": 10.249451637268066,
+      "learning_rate": 4.877065302911094e-05,
+      "loss": 0.4019,
+      "step": 500
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 8.789582252502441,
+      "learning_rate": 4.7541306058221875e-05,
+      "loss": 0.3315,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 4.354233741760254,
+      "learning_rate": 4.631195908733281e-05,
+      "loss": 0.3172,
+      "step": 1500
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 1.9432165622711182,
+      "learning_rate": 4.508261211644375e-05,
+      "loss": 0.3254,
+      "step": 2000
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 4.077924728393555,
+      "learning_rate": 4.3853265145554684e-05,
+      "loss": 0.4011,
+      "step": 2500
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 11.647229194641113,
+      "learning_rate": 4.262391817466562e-05,
+      "loss": 0.3489,
+      "step": 3000
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.7888924479484558,
+      "learning_rate": 4.1394571203776556e-05,
+      "loss": 0.3667,
+      "step": 3500
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 1.787675380706787,
+      "learning_rate": 4.016522423288749e-05,
+      "loss": 0.3543,
+      "step": 4000
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 9.598677635192871,
+      "learning_rate": 3.893587726199843e-05,
+      "loss": 0.3334,
+      "step": 4500
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 7.287684917449951,
+      "learning_rate": 3.7706530291109365e-05,
+      "loss": 0.3123,
+      "step": 5000
+    },
+    {
+      "epoch": 1.0,
+      "eval_Accuracy": 0.8917044741986647,
+      "eval_F1": 0.8404347826086956,
+      "eval_Precision": 0.9000116400884647,
+      "eval_Recall": 0.788255683555918,
+      "eval_loss": 0.3318740427494049,
+      "eval_runtime": 101.766,
+      "eval_samples_per_second": 266.405,
+      "eval_steps_per_second": 33.302,
+      "step": 5084
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 11.22262191772461,
+      "learning_rate": 3.64771833202203e-05,
+      "loss": 0.302,
+      "step": 5500
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 1.5249664783477783,
+      "learning_rate": 3.524783634933124e-05,
+      "loss": 0.3012,
+      "step": 6000
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 4.435938835144043,
+      "learning_rate": 3.4018489378442174e-05,
+      "loss": 0.2731,
+      "step": 6500
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 7.305878639221191,
+      "learning_rate": 3.278914240755311e-05,
+      "loss": 0.2666,
+      "step": 7000
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 2.5083842277526855,
+      "learning_rate": 3.1559795436664046e-05,
+      "loss": 0.2762,
+      "step": 7500
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 4.361833572387695,
+      "learning_rate": 3.033044846577498e-05,
+      "loss": 0.2661,
+      "step": 8000
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 2.4096310138702393,
+      "learning_rate": 2.910110149488592e-05,
+      "loss": 0.2741,
+      "step": 8500
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 0.772872269153595,
+      "learning_rate": 2.7871754523996855e-05,
+      "loss": 0.2506,
+      "step": 9000
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 3.299116373062134,
+      "learning_rate": 2.664240755310779e-05,
+      "loss": 0.2578,
+      "step": 9500
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 2.9145114421844482,
+      "learning_rate": 2.5413060582218728e-05,
+      "loss": 0.2795,
+      "step": 10000
+    },
+    {
+      "epoch": 2.0,
+      "eval_Accuracy": 0.9143152226033713,
+      "eval_F1": 0.8835997394397956,
+      "eval_Precision": 0.8688411509657076,
+      "eval_Recall": 0.8988683861759609,
+      "eval_loss": 0.26267826557159424,
+      "eval_runtime": 101.6652,
+      "eval_samples_per_second": 266.669,
+      "eval_steps_per_second": 33.335,
+      "step": 10168
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 20336,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 8055335612583780.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "_wandb": {},
+    "assignments": {},
+    "learning_rate": 5e-05,
+    "metric": "eval/loss",
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16
+  }
+}

run-y29l1u2z/checkpoint-10168/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:317009daba171581d5c14eab94fd34e72c050d1467c32c0c702a54a9399f264a
+size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f4836b23635ad9d0685501b421061fc0d597436df0b9dcbc686b37fce08600d
+oid sha256:317009daba171581d5c14eab94fd34e72c050d1467c32c0c702a54a9399f264a
 size 4920