Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bc1878e1ff49ef7dcd5ebe71b8ed5f921c8aca169b5d6948188a45ca5ec0964
+oid sha256:02eaab22eaf8b7f8499f06678b23398635fad086bb02fe61157a53590d6697f5
 size 498612824

run-zo8katke/checkpoint-15252/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-zo8katke/checkpoint-15252/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02eaab22eaf8b7f8499f06678b23398635fad086bb02fe61157a53590d6697f5
+size 498612824

run-zo8katke/checkpoint-15252/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd38019883ac1f0464c44baf37f60bd5cd6d34bc8ec9cb38951a280356ce547b
+size 997345530

run-zo8katke/checkpoint-15252/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df02faedab852f807617f8933290d202c50ade6d4e353f56d00c3ab24306b56f
+size 14180

run-zo8katke/checkpoint-15252/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5422aa04245c13090637df819a0fdf71206858ea97185e94aa73332f0cbfdd17
+size 1064

run-zo8katke/checkpoint-15252/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-zo8katke/checkpoint-15252/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-zo8katke/checkpoint-15252/trainer_state.json

@@ -0,0 +1,274 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 15252,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "grad_norm": 10.69678783416748,
+      "learning_rate": 1.9508261211644376e-05,
+      "loss": 0.3531,
+      "step": 500
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 5.511493682861328,
+      "learning_rate": 1.901652242328875e-05,
+      "loss": 0.294,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 5.709312915802002,
+      "learning_rate": 1.8524783634933125e-05,
+      "loss": 0.2837,
+      "step": 1500
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 11.061399459838867,
+      "learning_rate": 1.80330448465775e-05,
+      "loss": 0.2758,
+      "step": 2000
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 5.5632524490356445,
+      "learning_rate": 1.7541306058221874e-05,
+      "loss": 0.2515,
+      "step": 2500
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 6.892866611480713,
+      "learning_rate": 1.704956726986625e-05,
+      "loss": 0.2622,
+      "step": 3000
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 10.700236320495605,
+      "learning_rate": 1.6557828481510623e-05,
+      "loss": 0.2426,
+      "step": 3500
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 9.654351234436035,
+      "learning_rate": 1.6066089693154998e-05,
+      "loss": 0.2385,
+      "step": 4000
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 17.919334411621094,
+      "learning_rate": 1.5574350904799372e-05,
+      "loss": 0.2309,
+      "step": 4500
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 8.213055610656738,
+      "learning_rate": 1.5082612116443747e-05,
+      "loss": 0.2173,
+      "step": 5000
+    },
+    {
+      "epoch": 1.0,
+      "eval_Accuracy": 0.9088192984397477,
+      "eval_F1": 0.8799533799533799,
+      "eval_Precision": 0.8402114439395344,
+      "eval_Recall": 0.9236415536751963,
+      "eval_loss": 0.23545658588409424,
+      "eval_runtime": 101.9279,
+      "eval_samples_per_second": 265.982,
+      "eval_steps_per_second": 33.249,
+      "step": 5084
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 38.14435958862305,
+      "learning_rate": 1.459087332808812e-05,
+      "loss": 0.201,
+      "step": 5500
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 19.82416534423828,
+      "learning_rate": 1.4099134539732496e-05,
+      "loss": 0.1806,
+      "step": 6000
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 19.148880004882812,
+      "learning_rate": 1.360739575137687e-05,
+      "loss": 0.1844,
+      "step": 6500
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 25.127595901489258,
+      "learning_rate": 1.3115656963021243e-05,
+      "loss": 0.1727,
+      "step": 7000
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 14.535310745239258,
+      "learning_rate": 1.262391817466562e-05,
+      "loss": 0.1768,
+      "step": 7500
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 27.249629974365234,
+      "learning_rate": 1.2132179386309992e-05,
+      "loss": 0.1714,
+      "step": 8000
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 14.9617338180542,
+      "learning_rate": 1.1640440597954368e-05,
+      "loss": 0.1664,
+      "step": 8500
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 3.1620168685913086,
+      "learning_rate": 1.1148701809598743e-05,
+      "loss": 0.1692,
+      "step": 9000
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 16.152080535888672,
+      "learning_rate": 1.0656963021243116e-05,
+      "loss": 0.1731,
+      "step": 9500
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 2.696207284927368,
+      "learning_rate": 1.0165224232887492e-05,
+      "loss": 0.1682,
+      "step": 10000
+    },
+    {
+      "epoch": 2.0,
+      "eval_Accuracy": 0.9403194275386374,
+      "eval_F1": 0.9149674164389321,
+      "eval_Precision": 0.9442455797808873,
+      "eval_Recall": 0.8874503007442145,
+      "eval_loss": 0.20848818123340607,
+      "eval_runtime": 102.0755,
+      "eval_samples_per_second": 265.598,
+      "eval_steps_per_second": 33.201,
+      "step": 10168
+    },
+    {
+      "epoch": 2.07,
+      "grad_norm": 0.6836585402488708,
+      "learning_rate": 9.673485444531866e-06,
+      "loss": 0.1449,
+      "step": 10500
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 10.865861892700195,
+      "learning_rate": 9.18174665617624e-06,
+      "loss": 0.1383,
+      "step": 11000
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 52.6215934753418,
+      "learning_rate": 8.690007867820615e-06,
+      "loss": 0.1336,
+      "step": 11500
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 0.1384744495153427,
+      "learning_rate": 8.198269079464988e-06,
+      "loss": 0.1249,
+      "step": 12000
+    },
+    {
+      "epoch": 2.46,
+      "grad_norm": 7.174988746643066,
+      "learning_rate": 7.706530291109363e-06,
+      "loss": 0.1268,
+      "step": 12500
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 78.13346099853516,
+      "learning_rate": 7.214791502753737e-06,
+      "loss": 0.1266,
+      "step": 13000
+    },
+    {
+      "epoch": 2.66,
+      "grad_norm": 86.22885131835938,
+      "learning_rate": 6.7230527143981125e-06,
+      "loss": 0.1323,
+      "step": 13500
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 69.18795776367188,
+      "learning_rate": 6.231313926042487e-06,
+      "loss": 0.1286,
+      "step": 14000
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 31.10812759399414,
+      "learning_rate": 5.7395751376868615e-06,
+      "loss": 0.126,
+      "step": 14500
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 0.26176807284355164,
+      "learning_rate": 5.247836349331236e-06,
+      "loss": 0.1198,
+      "step": 15000
+    },
+    {
+      "epoch": 3.0,
+      "eval_Accuracy": 0.9514588174541699,
+      "eval_F1": 0.9318628973801388,
+      "eval_Precision": 0.9467648605996843,
+      "eval_Recall": 0.9174227750025487,
+      "eval_loss": 0.2540927231311798,
+      "eval_runtime": 102.358,
+      "eval_samples_per_second": 264.864,
+      "eval_steps_per_second": 33.109,
+      "step": 15252
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 20336,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 1.210754289284262e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "_wandb": {},
+    "assignments": {},
+    "learning_rate": 2e-05,
+    "metric": "eval/loss",
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16
+  }
+}

run-zo8katke/checkpoint-15252/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36f43d303dbbb2c39c797d7b76fdbe02eceb981576a6fbb433d6cf9e3a096152
+size 4920

training_args.bin

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