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 STSB
       type: glue
       config: stsb
       split: validation
@@ -20,7 +22,7 @@ model-index:
     metrics:
     - name: Spearmanr
       type: spearmanr
-      value: -0.03083348480803597
+      value: .nan
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -28,12 +30,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hBERTv1_no_pretrain_stsb
 
-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 STSB dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.2761
-- Pearson: -0.0294
-- Spearmanr: -0.0308
-- Combined Score: -0.0301
+- Loss: 2.2500
+- Pearson: nan
+- Spearmanr: nan
+- Combined Score: nan
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 11.0,
+    "eval_combined_score": NaN,
+    "eval_loss": 2.25003981590271,
+    "eval_pearson": NaN,
+    "eval_runtime": 2.6167,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 573.232,
+    "eval_spearmanr": NaN,
+    "eval_steps_per_second": 4.586,
+    "train_loss": 2.9389028992315733,
+    "train_runtime": 427.7269,
+    "train_samples": 5749,
+    "train_samples_per_second": 672.041,
+    "train_steps_per_second": 5.26
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 11.0,
+    "eval_combined_score": NaN,
+    "eval_loss": 2.25003981590271,
+    "eval_pearson": NaN,
+    "eval_runtime": 2.6167,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 573.232,
+    "eval_spearmanr": NaN,
+    "eval_steps_per_second": 4.586
+}

logs/events.out.tfevents.1685359597.serv-9225.2840720.20

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f00cb29ad0315c1dc43947f628203ebbbd542c2d0d5b76fb03725c12bb92ff70
+size 473

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 11.0,
+    "train_loss": 2.9389028992315733,
+    "train_runtime": 427.7269,
+    "train_samples": 5749,
+    "train_samples_per_second": 672.041,
+    "train_steps_per_second": 5.26
+}

trainer_state.json

@@ -0,0 +1,212 @@
+{
+  "best_metric": 2.25003981590271,
+  "best_model_checkpoint": "hBERTv1_no_pretrain_stsb/checkpoint-270",
+  "epoch": 11.0,
+  "global_step": 495,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0004915555555555556,
+      "loss": 9.9697,
+      "step": 45
+    },
+    {
+      "epoch": 1.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 3.3733878135681152,
+      "eval_pearson": NaN,
+      "eval_runtime": 2.6161,
+      "eval_samples_per_second": 573.365,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 4.587,
+      "step": 45
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0004815555555555556,
+      "loss": 2.313,
+      "step": 90
+    },
+    {
+      "epoch": 2.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 2.294187068939209,
+      "eval_pearson": NaN,
+      "eval_runtime": 2.6297,
+      "eval_samples_per_second": 570.404,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 4.563,
+      "step": 90
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0004715555555555556,
+      "loss": 2.2395,
+      "step": 135
+    },
+    {
+      "epoch": 3.0,
+      "eval_combined_score": -0.022127587058030855,
+      "eval_loss": 2.381610870361328,
+      "eval_pearson": -0.022376532916427817,
+      "eval_runtime": 2.6313,
+      "eval_samples_per_second": 570.062,
+      "eval_spearmanr": -0.021878641199633897,
+      "eval_steps_per_second": 4.56,
+      "step": 135
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.00046155555555555555,
+      "loss": 2.2079,
+      "step": 180
+    },
+    {
+      "epoch": 4.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 2.4113330841064453,
+      "eval_pearson": NaN,
+      "eval_runtime": 2.6261,
+      "eval_samples_per_second": 571.19,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 4.57,
+      "step": 180
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0004515555555555556,
+      "loss": 2.2351,
+      "step": 225
+    },
+    {
+      "epoch": 5.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 2.290961980819702,
+      "eval_pearson": NaN,
+      "eval_runtime": 2.6281,
+      "eval_samples_per_second": 570.76,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 4.566,
+      "step": 225
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.00044155555555555555,
+      "loss": 2.2341,
+      "step": 270
+    },
+    {
+      "epoch": 6.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 2.25003981590271,
+      "eval_pearson": NaN,
+      "eval_runtime": 2.6296,
+      "eval_samples_per_second": 570.425,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 4.563,
+      "step": 270
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 0.0004315555555555556,
+      "loss": 2.2359,
+      "step": 315
+    },
+    {
+      "epoch": 7.0,
+      "eval_combined_score": 0.013435231524120657,
+      "eval_loss": 2.299790143966675,
+      "eval_pearson": 0.013168742876553664,
+      "eval_runtime": 2.6287,
+      "eval_samples_per_second": 570.63,
+      "eval_spearmanr": 0.01370172017168765,
+      "eval_steps_per_second": 4.565,
+      "step": 315
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 0.0004215555555555556,
+      "loss": 2.2026,
+      "step": 360
+    },
+    {
+      "epoch": 8.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 2.5151796340942383,
+      "eval_pearson": NaN,
+      "eval_runtime": 2.6302,
+      "eval_samples_per_second": 570.305,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 4.562,
+      "step": 360
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 0.0004115555555555556,
+      "loss": 2.2182,
+      "step": 405
+    },
+    {
+      "epoch": 9.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 2.2501604557037354,
+      "eval_pearson": NaN,
+      "eval_runtime": 2.6294,
+      "eval_samples_per_second": 570.48,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 4.564,
+      "step": 405
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.00040155555555555555,
+      "loss": 2.2771,
+      "step": 450
+    },
+    {
+      "epoch": 10.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 2.6595544815063477,
+      "eval_pearson": NaN,
+      "eval_runtime": 2.6297,
+      "eval_samples_per_second": 570.398,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 4.563,
+      "step": 450
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 0.0003915555555555556,
+      "loss": 2.1948,
+      "step": 495
+    },
+    {
+      "epoch": 11.0,
+      "eval_combined_score": -0.03009925464966003,
+      "eval_loss": 2.2760612964630127,
+      "eval_pearson": -0.02936502449128409,
+      "eval_runtime": 2.6228,
+      "eval_samples_per_second": 571.9,
+      "eval_spearmanr": -0.03083348480803597,
+      "eval_steps_per_second": 4.575,
+      "step": 495
+    },
+    {
+      "epoch": 11.0,
+      "step": 495,
+      "total_flos": 9365417243967488.0,
+      "train_loss": 2.9389028992315733,
+      "train_runtime": 427.7269,
+      "train_samples_per_second": 672.041,
+      "train_steps_per_second": 5.26
+    }
+  ],
+  "max_steps": 2250,
+  "num_train_epochs": 50,
+  "total_flos": 9365417243967488.0,
+  "trial_name": null,
+  "trial_params": null
+}