End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/distilbert_km_100_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - spearmanr
 model-index:
 - name: distilbert_km_100_v1_stsb
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE STSB
+      type: glue
+      args: stsb
+    metrics:
+    - name: Spearmanr
+      type: spearmanr
+      value: 0.2022387665178333
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,12 +30,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # distilbert_km_100_v1_stsb
 
-This model is a fine-tuned version of [Hartunka/distilbert_km_100_v1](https://huggingface.co/Hartunka/distilbert_km_100_v1) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/distilbert_km_100_v1](https://huggingface.co/Hartunka/distilbert_km_100_v1) on the GLUE STSB dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.7263
-- Pearson: 0.2373
-- Spearmanr: 0.2258
-- Combined Score: 0.2315
+- Loss: 2.2273
+- Pearson: 0.2185
+- Spearmanr: 0.2022
+- Combined Score: 0.2103
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 6.0,
+    "eval_combined_score": 0.2103449930157198,
+    "eval_loss": 2.2272627353668213,
+    "eval_pearson": 0.21845121951360627,
+    "eval_runtime": 0.6611,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 2268.946,
+    "eval_spearmanr": 0.2022387665178333,
+    "eval_steps_per_second": 9.076,
+    "total_flos": 2284624480859136.0,
+    "train_loss": 1.748459249302961,
+    "train_runtime": 42.8961,
+    "train_samples": 5749,
+    "train_samples_per_second": 6701.069,
+    "train_steps_per_second": 26.809
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 6.0,
+    "eval_combined_score": 0.2103449930157198,
+    "eval_loss": 2.2272627353668213,
+    "eval_pearson": 0.21845121951360627,
+    "eval_runtime": 0.6611,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 2268.946,
+    "eval_spearmanr": 0.2022387665178333,
+    "eval_steps_per_second": 9.076
+}

logs/events.out.tfevents.1744908907.s_005_m.2758941.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89d97c74dd7756cdfd9fcb4fde64cb6c999a9ba65fb3209cb623bb94b4cf0e3c
+size 473

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "total_flos": 2284624480859136.0,
+    "train_loss": 1.748459249302961,
+    "train_runtime": 42.8961,
+    "train_samples": 5749,
+    "train_samples_per_second": 6701.069,
+    "train_steps_per_second": 26.809
+}

trainer_state.json

@@ -0,0 +1,160 @@
+{
+  "best_global_step": 23,
+  "best_metric": 2.2272627353668213,
+  "best_model_checkpoint": "distilbert_km_100_v1_stsb/checkpoint-23",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 138,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.1863901615142822,
+      "learning_rate": 4.9e-05,
+      "loss": 3.0026,
+      "step": 23
+    },
+    {
+      "epoch": 1.0,
+      "eval_combined_score": 0.2103449930157198,
+      "eval_loss": 2.2272627353668213,
+      "eval_pearson": 0.21845121951360627,
+      "eval_runtime": 0.6251,
+      "eval_samples_per_second": 2399.454,
+      "eval_spearmanr": 0.2022387665178333,
+      "eval_steps_per_second": 9.598,
+      "step": 23
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.856623411178589,
+      "learning_rate": 4.8e-05,
+      "loss": 1.99,
+      "step": 46
+    },
+    {
+      "epoch": 2.0,
+      "eval_combined_score": 0.1171634239646927,
+      "eval_loss": 2.658442497253418,
+      "eval_pearson": 0.12410055898736613,
+      "eval_runtime": 0.6353,
+      "eval_samples_per_second": 2360.971,
+      "eval_spearmanr": 0.11022628894201927,
+      "eval_steps_per_second": 9.444,
+      "step": 46
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 5.957757472991943,
+      "learning_rate": 4.7e-05,
+      "loss": 1.8033,
+      "step": 69
+    },
+    {
+      "epoch": 3.0,
+      "eval_combined_score": 0.22858532041676666,
+      "eval_loss": 2.31754732131958,
+      "eval_pearson": 0.2347264879979243,
+      "eval_runtime": 0.6371,
+      "eval_samples_per_second": 2354.308,
+      "eval_spearmanr": 0.22244415283560898,
+      "eval_steps_per_second": 9.417,
+      "step": 69
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 8.772383689880371,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 1.5606,
+      "step": 92
+    },
+    {
+      "epoch": 4.0,
+      "eval_combined_score": 0.26908921883156806,
+      "eval_loss": 2.341899871826172,
+      "eval_pearson": 0.2693202474352846,
+      "eval_runtime": 0.6125,
+      "eval_samples_per_second": 2448.895,
+      "eval_spearmanr": 0.2688581902278515,
+      "eval_steps_per_second": 9.796,
+      "step": 92
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 9.251775741577148,
+      "learning_rate": 4.5e-05,
+      "loss": 1.2238,
+      "step": 115
+    },
+    {
+      "epoch": 5.0,
+      "eval_combined_score": 0.23459611625142823,
+      "eval_loss": 2.5834755897521973,
+      "eval_pearson": 0.23783220697235988,
+      "eval_runtime": 0.6212,
+      "eval_samples_per_second": 2414.699,
+      "eval_spearmanr": 0.2313600255304966,
+      "eval_steps_per_second": 9.659,
+      "step": 115
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 13.212778091430664,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.9104,
+      "step": 138
+    },
+    {
+      "epoch": 6.0,
+      "eval_combined_score": 0.23154618932985382,
+      "eval_loss": 2.726290464401245,
+      "eval_pearson": 0.23729568178830282,
+      "eval_runtime": 0.6275,
+      "eval_samples_per_second": 2390.389,
+      "eval_spearmanr": 0.2257966968714048,
+      "eval_steps_per_second": 9.562,
+      "step": 138
+    },
+    {
+      "epoch": 6.0,
+      "step": 138,
+      "total_flos": 2284624480859136.0,
+      "train_loss": 1.748459249302961,
+      "train_runtime": 42.8961,
+      "train_samples_per_second": 6701.069,
+      "train_steps_per_second": 26.809
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1150,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 5
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2284624480859136.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}