Training in progress, epoch 5

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ef44161ee4b3549af5c37289a7673ad175f739be8495862c1a540497649f697
+oid sha256:2c24b768b57937e739aadb95b361dad441af6d95f6e3823f3f6da0c7a57a369f
 size 437955572

tmp-checkpoint-90/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "yimiwang/bert-petco-emailbody-ctr",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

tmp-checkpoint-90/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4740fe85b20791645b3d374361f63e379bafb69baef3e7508edc2fc24ee157bf
+size 437955572

tmp-checkpoint-90/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dc168cb1182110fe959dd40ece6caf41d89676a702ac955ae85a2c15b79e235
+size 876032250

tmp-checkpoint-90/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0838536b2a0d9f02d9d2df5343df774521dde339fbfe6e7bc21383c1e9f5bddb
+size 14244

tmp-checkpoint-90/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e6cce6b995779c2ccf35df683ba225aa194d8f8f2d8f50adc37ff2250079a94
+size 1064

tmp-checkpoint-90/trainer_state.json

@@ -0,0 +1,135 @@
+{
+  "best_metric": 168.2034149169922,
+  "best_model_checkpoint": "roberta-petco-fullemailbody-ctr/checkpoint-90",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 90,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 633.0380859375,
+      "learning_rate": 9.5e-06,
+      "loss": 270.8182,
+      "step": 15
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 255.3511199951172,
+      "eval_mae": 14.281704902648926,
+      "eval_mse": 255.35110473632812,
+      "eval_r2": -3.979249295308054,
+      "eval_rmse": 15.97970962524414,
+      "eval_runtime": 2.323,
+      "eval_samples_per_second": 25.828,
+      "eval_steps_per_second": 1.722,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 482.0528869628906,
+      "learning_rate": 9e-06,
+      "loss": 233.984,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 232.40538024902344,
+      "eval_mae": 13.456147193908691,
+      "eval_mse": 232.40542602539062,
+      "eval_r2": -3.531816663730682,
+      "eval_rmse": 15.24484920501709,
+      "eval_runtime": 2.3646,
+      "eval_samples_per_second": 25.374,
+      "eval_steps_per_second": 1.692,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 424.8625793457031,
+      "learning_rate": 8.5e-06,
+      "loss": 213.3705,
+      "step": 45
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 211.15115356445312,
+      "eval_mae": 12.64023494720459,
+      "eval_mse": 211.1511688232422,
+      "eval_r2": -3.1173671236809426,
+      "eval_rmse": 14.531041145324707,
+      "eval_runtime": 2.3659,
+      "eval_samples_per_second": 25.36,
+      "eval_steps_per_second": 1.691,
+      "step": 45
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 342.81646728515625,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 194.8535,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 193.54568481445312,
+      "eval_mae": 11.927023887634277,
+      "eval_mse": 193.54566955566406,
+      "eval_r2": -2.774066276180696,
+      "eval_rmse": 13.912069320678711,
+      "eval_runtime": 2.3935,
+      "eval_samples_per_second": 25.068,
+      "eval_steps_per_second": 1.671,
+      "step": 60
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 379.5366516113281,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 179.8182,
+      "step": 75
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 179.9423065185547,
+      "eval_mae": 11.341310501098633,
+      "eval_mse": 179.94229125976562,
+      "eval_r2": -2.508806199489563,
+      "eval_rmse": 13.414257049560547,
+      "eval_runtime": 2.6076,
+      "eval_samples_per_second": 23.01,
+      "eval_steps_per_second": 1.534,
+      "step": 75
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 419.7530212402344,
+      "learning_rate": 7e-06,
+      "loss": 167.2209,
+      "step": 90
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 168.2034149169922,
+      "eval_mae": 10.810791015625,
+      "eval_mse": 168.20339965820312,
+      "eval_r2": -2.279901978526021,
+      "eval_rmse": 12.969325065612793,
+      "eval_runtime": 2.4373,
+      "eval_samples_per_second": 24.618,
+      "eval_steps_per_second": 1.641,
+      "step": 90
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 300,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "total_flos": 378876517908480.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

tmp-checkpoint-90/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcc3e2b5541663547af4e3c848444336d88de385d296c206ff4ca38f98009dc2
+size 4920