End of training

README.md

@@ -1,4 +1,6 @@
 ---
+language:
+- en
 tags:
 - generated_from_trainer
 datasets:
@@ -12,7 +14,7 @@ model-index:
       name: Text Classification
       type: text-classification
     dataset:
-      name: glue
+      name: GLUE RTE
       type: glue
       config: rte
       split: validation
@@ -28,7 +30,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # add_BERT_no_pretrain_rte
 
-This model is a fine-tuned version of [](https://huggingface.co/) on the glue dataset.
+This model is a fine-tuned version of [](https://huggingface.co/) on the GLUE RTE dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.6917
 - Accuracy: 0.5271

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 12.0,
+    "eval_accuracy": 0.5270758122743683,
+    "eval_loss": 0.6916900277137756,
+    "eval_runtime": 0.4398,
+    "eval_samples": 277,
+    "eval_samples_per_second": 629.814,
+    "eval_steps_per_second": 6.821,
+    "train_loss": 0.8102153817812602,
+    "train_runtime": 192.7212,
+    "train_samples": 2490,
+    "train_samples_per_second": 646.011,
+    "train_steps_per_second": 5.189
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 12.0,
+    "eval_accuracy": 0.5270758122743683,
+    "eval_loss": 0.6916900277137756,
+    "eval_runtime": 0.4398,
+    "eval_samples": 277,
+    "eval_samples_per_second": 629.814,
+    "eval_steps_per_second": 6.821
+}

logs/events.out.tfevents.1685350951.serv-9215.1440072.14

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74b60a03a2adf2210fd8f6421e820ff16353e302ad268e21676cf26c3f215285
+size 363

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 12.0,
+    "train_loss": 0.8102153817812602,
+    "train_runtime": 192.7212,
+    "train_samples": 2490,
+    "train_samples_per_second": 646.011,
+    "train_steps_per_second": 5.189
+}

trainer_state.json

@@ -0,0 +1,205 @@
+{
+  "best_metric": 0.6916900277137756,
+  "best_model_checkpoint": "add_BERT_no_pretrain_rte/checkpoint-140",
+  "epoch": 12.0,
+  "global_step": 240,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.000491,
+      "loss": 1.9285,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.730164647102356,
+      "eval_runtime": 0.4422,
+      "eval_samples_per_second": 626.451,
+      "eval_steps_per_second": 6.785,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.000481,
+      "loss": 0.7216,
+      "step": 40
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6919297575950623,
+      "eval_runtime": 0.4417,
+      "eval_samples_per_second": 627.184,
+      "eval_steps_per_second": 6.793,
+      "step": 40
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.000471,
+      "loss": 0.7641,
+      "step": 60
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.7044311761856079,
+      "eval_runtime": 0.4414,
+      "eval_samples_per_second": 627.498,
+      "eval_steps_per_second": 6.796,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.00046100000000000004,
+      "loss": 0.7002,
+      "step": 80
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.7476167678833008,
+      "eval_runtime": 0.4419,
+      "eval_samples_per_second": 626.82,
+      "eval_steps_per_second": 6.789,
+      "step": 80
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.000451,
+      "loss": 0.7253,
+      "step": 100
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.7223910093307495,
+      "eval_runtime": 0.441,
+      "eval_samples_per_second": 628.089,
+      "eval_steps_per_second": 6.802,
+      "step": 100
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.000441,
+      "loss": 0.7081,
+      "step": 120
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.7065941095352173,
+      "eval_runtime": 0.4416,
+      "eval_samples_per_second": 627.262,
+      "eval_steps_per_second": 6.793,
+      "step": 120
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 0.000431,
+      "loss": 0.6975,
+      "step": 140
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6916900277137756,
+      "eval_runtime": 0.4423,
+      "eval_samples_per_second": 626.273,
+      "eval_steps_per_second": 6.783,
+      "step": 140
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 0.000421,
+      "loss": 0.698,
+      "step": 160
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.693280041217804,
+      "eval_runtime": 0.4459,
+      "eval_samples_per_second": 621.162,
+      "eval_steps_per_second": 6.727,
+      "step": 160
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 0.00041099999999999996,
+      "loss": 0.6967,
+      "step": 180
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6917147040367126,
+      "eval_runtime": 0.4434,
+      "eval_samples_per_second": 624.713,
+      "eval_steps_per_second": 6.766,
+      "step": 180
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.00040100000000000004,
+      "loss": 0.6926,
+      "step": 200
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.715362012386322,
+      "eval_runtime": 0.4422,
+      "eval_samples_per_second": 626.383,
+      "eval_steps_per_second": 6.784,
+      "step": 200
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 0.000391,
+      "loss": 0.696,
+      "step": 220
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.6963789463043213,
+      "eval_runtime": 0.4402,
+      "eval_samples_per_second": 629.307,
+      "eval_steps_per_second": 6.816,
+      "step": 220
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 0.000381,
+      "loss": 0.694,
+      "step": 240
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6917306780815125,
+      "eval_runtime": 0.4402,
+      "eval_samples_per_second": 629.308,
+      "eval_steps_per_second": 6.816,
+      "step": 240
+    },
+    {
+      "epoch": 12.0,
+      "step": 240,
+      "total_flos": 4267580168601600.0,
+      "train_loss": 0.8102153817812602,
+      "train_runtime": 192.7212,
+      "train_samples_per_second": 646.011,
+      "train_steps_per_second": 5.189
+    }
+  ],
+  "max_steps": 1000,
+  "num_train_epochs": 50,
+  "total_flos": 4267580168601600.0,
+  "trial_name": null,
+  "trial_params": null
+}