Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bd941985c23059f97cfa7d2aebaaf25d395c3fd75769b25f876bea629e85568
+oid sha256:8857d743a2fe05d5efc3e4f437b70d6ee76601ecdd666aa1536bab8c9378538a
 size 498612824

run-i1xkwgrc/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-i1xkwgrc/checkpoint-10168/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8857d743a2fe05d5efc3e4f437b70d6ee76601ecdd666aa1536bab8c9378538a
+size 498612824

run-i1xkwgrc/checkpoint-10168/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:facf8bb76e13b4b643e32cc1c598c8db5a2458182467d38bd56a2d126c6fa989
+size 997345530

run-i1xkwgrc/checkpoint-10168/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:249c55aa8e98972ee4ffa5a1f5c6326bcfd928bb24eee55d6353e23e14d50c74
+size 14180

run-i1xkwgrc/checkpoint-10168/scheduler.pt

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

run-i1xkwgrc/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-i1xkwgrc/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-i1xkwgrc/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": 9.13818645477295,
+      "learning_rate": 4.877065302911094e-05,
+      "loss": 0.3942,
+      "step": 500
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.770092010498047,
+      "learning_rate": 4.7541306058221875e-05,
+      "loss": 0.3183,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 5.269647598266602,
+      "learning_rate": 4.631195908733281e-05,
+      "loss": 0.3337,
+      "step": 1500
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 4.7381978034973145,
+      "learning_rate": 4.508261211644375e-05,
+      "loss": 0.3283,
+      "step": 2000
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 4.226181983947754,
+      "learning_rate": 4.3853265145554684e-05,
+      "loss": 0.3197,
+      "step": 2500
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 1.0734018087387085,
+      "learning_rate": 4.262391817466562e-05,
+      "loss": 0.3629,
+      "step": 3000
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 112.0802993774414,
+      "learning_rate": 4.1394571203776556e-05,
+      "loss": 0.3589,
+      "step": 3500
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 2.571420669555664,
+      "learning_rate": 4.016522423288749e-05,
+      "loss": 0.3318,
+      "step": 4000
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 2.4702706336975098,
+      "learning_rate": 3.893587726199843e-05,
+      "loss": 0.3335,
+      "step": 4500
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.9089040756225586,
+      "learning_rate": 3.7706530291109365e-05,
+      "loss": 0.3519,
+      "step": 5000
+    },
+    {
+      "epoch": 1.0,
+      "eval_Accuracy": 0.8820773855630556,
+      "eval_F1": 0.8178243774574051,
+      "eval_Precision": 0.9271317829457364,
+      "eval_Recall": 0.7315730451626058,
+      "eval_loss": 0.3840866982936859,
+      "eval_runtime": 102.3237,
+      "eval_samples_per_second": 264.953,
+      "eval_steps_per_second": 33.12,
+      "step": 5084
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 1.7815802097320557,
+      "learning_rate": 3.64771833202203e-05,
+      "loss": 0.3011,
+      "step": 5500
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 29.481904983520508,
+      "learning_rate": 3.524783634933124e-05,
+      "loss": 0.3162,
+      "step": 6000
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 2.48317289352417,
+      "learning_rate": 3.4018489378442174e-05,
+      "loss": 0.2966,
+      "step": 6500
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 2.315831422805786,
+      "learning_rate": 3.278914240755311e-05,
+      "loss": 0.2925,
+      "step": 7000
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 1.042138695716858,
+      "learning_rate": 3.1559795436664046e-05,
+      "loss": 0.2962,
+      "step": 7500
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 1.6230789422988892,
+      "learning_rate": 3.033044846577498e-05,
+      "loss": 0.3448,
+      "step": 8000
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 7.854997158050537,
+      "learning_rate": 2.910110149488592e-05,
+      "loss": 0.3254,
+      "step": 8500
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 11.756633758544922,
+      "learning_rate": 2.7871754523996855e-05,
+      "loss": 0.2866,
+      "step": 9000
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 8.235610008239746,
+      "learning_rate": 2.664240755310779e-05,
+      "loss": 0.3131,
+      "step": 9500
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 0.9118052124977112,
+      "learning_rate": 2.5413060582218728e-05,
+      "loss": 0.3171,
+      "step": 10000
+    },
+    {
+      "epoch": 2.0,
+      "eval_Accuracy": 0.9031389472907676,
+      "eval_F1": 0.8641208734347511,
+      "eval_Precision": 0.8773773247872229,
+      "eval_Recall": 0.8512590478132327,
+      "eval_loss": 0.30002930760383606,
+      "eval_runtime": 102.0615,
+      "eval_samples_per_second": 265.634,
+      "eval_steps_per_second": 33.205,
+      "step": 10168
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 20336,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 8079980176806240.0,
+  "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-i1xkwgrc/checkpoint-10168/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:602c16475c0c1143f90b1079c90227c1ef914b9fd9650bc47e993d21dc77137f
+size 4920