Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6e9c3380139fe12b22f9bfe81c2e97a8c4ae7311dd42a27160978d2a1ffb15d
+oid sha256:62c44c0a2bfb9495eef4f7449274c4c10590be12c94afd30ef2335ecf6d3258c
 size 498612824

run-aiqm0bwn/checkpoint-20336/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-aiqm0bwn/checkpoint-20336/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62c44c0a2bfb9495eef4f7449274c4c10590be12c94afd30ef2335ecf6d3258c
+size 498612824

run-aiqm0bwn/checkpoint-20336/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87c1c04120a54a268024109e32045bae0fc5ab85d770384a2712b363aef421aa
+size 997345530

run-aiqm0bwn/checkpoint-20336/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9951426c0ef577d78ddc6baefdb142d039af0d9fc9c6fe05a09eccee397c462
+size 14180

run-aiqm0bwn/checkpoint-20336/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:447c2593f07d910b54a250eb3f4ccc48238e5e0e0d51833eb5a4a48174cee1f8
+size 1064

run-aiqm0bwn/checkpoint-20336/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-aiqm0bwn/checkpoint-20336/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-aiqm0bwn/checkpoint-20336/trainer_state.json

@@ -0,0 +1,356 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 20336,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.639714002609253,
+      "learning_rate": 4.877065302911094e-05,
+      "loss": 0.4358,
+      "step": 500
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 5.436565399169922,
+      "learning_rate": 4.7541306058221875e-05,
+      "loss": 0.3804,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 4.662177085876465,
+      "learning_rate": 4.631195908733281e-05,
+      "loss": 0.3975,
+      "step": 1500
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 12.201448440551758,
+      "learning_rate": 4.508261211644375e-05,
+      "loss": 0.3733,
+      "step": 2000
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 2.0421175956726074,
+      "learning_rate": 4.3853265145554684e-05,
+      "loss": 0.3712,
+      "step": 2500
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 4.97001838684082,
+      "learning_rate": 4.262391817466562e-05,
+      "loss": 0.4752,
+      "step": 3000
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 2.7016830444335938,
+      "learning_rate": 4.1394571203776556e-05,
+      "loss": 0.4282,
+      "step": 3500
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 1.6109079122543335,
+      "learning_rate": 4.016522423288749e-05,
+      "loss": 0.4309,
+      "step": 4000
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 7.190454483032227,
+      "learning_rate": 3.893587726199843e-05,
+      "loss": 0.389,
+      "step": 4500
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.701509952545166,
+      "learning_rate": 3.7706530291109365e-05,
+      "loss": 0.4228,
+      "step": 5000
+    },
+    {
+      "epoch": 1.0,
+      "eval_Accuracy": 0.8657740400575412,
+      "eval_F1": 0.8202341550165488,
+      "eval_Precision": 0.7956680084339659,
+      "eval_Recall": 0.8463655826281986,
+      "eval_loss": 0.39325135946273804,
+      "eval_runtime": 89.4137,
+      "eval_samples_per_second": 303.209,
+      "eval_steps_per_second": 37.902,
+      "step": 5084
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 1.2046446800231934,
+      "learning_rate": 3.64771833202203e-05,
+      "loss": 0.3931,
+      "step": 5500
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 0.729346752166748,
+      "learning_rate": 3.524783634933124e-05,
+      "loss": 0.3827,
+      "step": 6000
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 3.0332932472229004,
+      "learning_rate": 3.4018489378442174e-05,
+      "loss": 0.385,
+      "step": 6500
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 290.25067138671875,
+      "learning_rate": 3.278914240755311e-05,
+      "loss": 0.3822,
+      "step": 7000
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 1.7939294576644897,
+      "learning_rate": 3.1559795436664046e-05,
+      "loss": 0.3673,
+      "step": 7500
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 1.399434208869934,
+      "learning_rate": 3.033044846577498e-05,
+      "loss": 0.3799,
+      "step": 8000
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 0.8836120367050171,
+      "learning_rate": 2.910110149488592e-05,
+      "loss": 0.3648,
+      "step": 8500
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 2.145643711090088,
+      "learning_rate": 2.7871754523996855e-05,
+      "loss": 0.3916,
+      "step": 9000
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 2.656245231628418,
+      "learning_rate": 2.664240755310779e-05,
+      "loss": 0.4065,
+      "step": 9500
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 2.332174301147461,
+      "learning_rate": 2.5413060582218728e-05,
+      "loss": 0.3884,
+      "step": 10000
+    },
+    {
+      "epoch": 2.0,
+      "eval_Accuracy": 0.8491387259783851,
+      "eval_F1": 0.8093417863136304,
+      "eval_Precision": 0.7455982135188526,
+      "eval_Recall": 0.8850035681516975,
+      "eval_loss": 0.39591678977012634,
+      "eval_runtime": 88.8717,
+      "eval_samples_per_second": 305.058,
+      "eval_steps_per_second": 38.134,
+      "step": 10168
+    },
+    {
+      "epoch": 2.07,
+      "grad_norm": 1.7149969339370728,
+      "learning_rate": 2.4183713611329664e-05,
+      "loss": 0.3975,
+      "step": 10500
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 0.5414048433303833,
+      "learning_rate": 2.29543666404406e-05,
+      "loss": 0.4078,
+      "step": 11000
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 1.5238455533981323,
+      "learning_rate": 2.1725019669551537e-05,
+      "loss": 0.5382,
+      "step": 11500
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 0.6814860105514526,
+      "learning_rate": 2.0495672698662473e-05,
+      "loss": 0.6048,
+      "step": 12000
+    },
+    {
+      "epoch": 2.46,
+      "grad_norm": 0.6721811294555664,
+      "learning_rate": 1.9266325727773406e-05,
+      "loss": 0.602,
+      "step": 12500
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 1.559476375579834,
+      "learning_rate": 1.8036978756884342e-05,
+      "loss": 0.5172,
+      "step": 13000
+    },
+    {
+      "epoch": 2.66,
+      "grad_norm": 0.9714244604110718,
+      "learning_rate": 1.6807631785995282e-05,
+      "loss": 0.397,
+      "step": 13500
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 2.5964913368225098,
+      "learning_rate": 1.5578284815106218e-05,
+      "loss": 0.362,
+      "step": 14000
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 4.127317905426025,
+      "learning_rate": 1.4348937844217153e-05,
+      "loss": 0.3589,
+      "step": 14500
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 1.4614758491516113,
+      "learning_rate": 1.3119590873328089e-05,
+      "loss": 0.3309,
+      "step": 15000
+    },
+    {
+      "epoch": 3.0,
+      "eval_Accuracy": 0.8821880417542695,
+      "eval_F1": 0.8272019043497079,
+      "eval_Precision": 0.8812680115273775,
+      "eval_Recall": 0.7793862779080436,
+      "eval_loss": 0.3385286331176758,
+      "eval_runtime": 88.8552,
+      "eval_samples_per_second": 305.114,
+      "eval_steps_per_second": 38.141,
+      "step": 15252
+    },
+    {
+      "epoch": 3.05,
+      "grad_norm": 6.725005149841309,
+      "learning_rate": 1.1890243902439025e-05,
+      "loss": 0.3115,
+      "step": 15500
+    },
+    {
+      "epoch": 3.15,
+      "grad_norm": 1.5747590065002441,
+      "learning_rate": 1.0660896931549961e-05,
+      "loss": 0.303,
+      "step": 16000
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 2.4709486961364746,
+      "learning_rate": 9.431549960660898e-06,
+      "loss": 0.3001,
+      "step": 16500
+    },
+    {
+      "epoch": 3.34,
+      "grad_norm": 0.9706057906150818,
+      "learning_rate": 8.202202989771832e-06,
+      "loss": 0.3016,
+      "step": 17000
+    },
+    {
+      "epoch": 3.44,
+      "grad_norm": 4.0229597091674805,
+      "learning_rate": 6.97285601888277e-06,
+      "loss": 0.2914,
+      "step": 17500
+    },
+    {
+      "epoch": 3.54,
+      "grad_norm": 39.496726989746094,
+      "learning_rate": 5.743509047993706e-06,
+      "loss": 0.2712,
+      "step": 18000
+    },
+    {
+      "epoch": 3.64,
+      "grad_norm": 1.7884820699691772,
+      "learning_rate": 4.514162077104643e-06,
+      "loss": 0.2692,
+      "step": 18500
+    },
+    {
+      "epoch": 3.74,
+      "grad_norm": 5.432505130767822,
+      "learning_rate": 3.284815106215578e-06,
+      "loss": 0.2691,
+      "step": 19000
+    },
+    {
+      "epoch": 3.84,
+      "grad_norm": 11.744521141052246,
+      "learning_rate": 2.0554681353265145e-06,
+      "loss": 0.2621,
+      "step": 19500
+    },
+    {
+      "epoch": 3.93,
+      "grad_norm": 4.194027423858643,
+      "learning_rate": 8.261211644374508e-07,
+      "loss": 0.254,
+      "step": 20000
+    },
+    {
+      "epoch": 4.0,
+      "eval_Accuracy": 0.8947290767585113,
+      "eval_F1": 0.8524759640235707,
+      "eval_Precision": 0.8646324840096467,
+      "eval_Recall": 0.8406565399123254,
+      "eval_loss": 0.26431554555892944,
+      "eval_runtime": 88.602,
+      "eval_samples_per_second": 305.986,
+      "eval_steps_per_second": 38.25,
+      "step": 20336
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 20336,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 1.610614078168308e+16,
+  "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-aiqm0bwn/checkpoint-20336/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f591bcc7bb3d751c372b9e555545d558094f5e42774fe55fce79687d449affc
+size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36f43d303dbbb2c39c797d7b76fdbe02eceb981576a6fbb433d6cf9e3a096152
+oid sha256:2f591bcc7bb3d751c372b9e555545d558094f5e42774fe55fce79687d449affc
 size 4920