End of training

README.md

@@ -1,14 +1,29 @@
 ---
 library_name: transformers
+language:
+- en
 license: apache-2.0
 base_model: gokulsrinivasagan/tinybert_train_book_ent_15p
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - spearmanr
 model-index:
 - name: tinybert_train_book_ent_15p_stsb
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE STSB
+      type: glue
+      args: stsb
+    metrics:
+    - name: Spearmanr
+      type: spearmanr
+      value: 0.21041199925604162
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,12 +31,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tinybert_train_book_ent_15p_stsb
 
-This model is a fine-tuned version of [gokulsrinivasagan/tinybert_train_book_ent_15p](https://huggingface.co/gokulsrinivasagan/tinybert_train_book_ent_15p) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/tinybert_train_book_ent_15p](https://huggingface.co/gokulsrinivasagan/tinybert_train_book_ent_15p) on the GLUE STSB dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.7564
-- Pearson: 0.2357
-- Spearmanr: 0.2491
-- Combined Score: 0.2424
+- Loss: 2.2779
+- Pearson: 0.2196
+- Spearmanr: 0.2104
+- Combined Score: 0.2150
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 9.0,
+    "eval_combined_score": 0.21502963923574336,
+    "eval_loss": 2.2779486179351807,
+    "eval_pearson": 0.21964727921544513,
+    "eval_runtime": 0.622,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 2411.544,
+    "eval_spearmanr": 0.21041199925604162,
+    "eval_steps_per_second": 9.646,
+    "total_flos": 1356793384840704.0,
+    "train_loss": 1.7060688590081994,
+    "train_runtime": 46.683,
+    "train_samples": 5749,
+    "train_samples_per_second": 6157.489,
+    "train_steps_per_second": 24.634
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 9.0,
+    "eval_combined_score": 0.21502963923574336,
+    "eval_loss": 2.2779486179351807,
+    "eval_pearson": 0.21964727921544513,
+    "eval_runtime": 0.622,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 2411.544,
+    "eval_spearmanr": 0.21041199925604162,
+    "eval_steps_per_second": 9.646
+}

logs/events.out.tfevents.1744160249.ki-g0008.1515235.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a5db0ca2774206c34f5dde92b3d9164b74b50bba06e7de040cc70aa07291fe3
+size 521

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 9.0,
+    "total_flos": 1356793384840704.0,
+    "train_loss": 1.7060688590081994,
+    "train_runtime": 46.683,
+    "train_samples": 5749,
+    "train_samples_per_second": 6157.489,
+    "train_steps_per_second": 24.634
+}

trainer_state.json

@@ -0,0 +1,213 @@
+{
+  "best_metric": 2.2779486179351807,
+  "best_model_checkpoint": "tinybert_train_book_ent_15p_stsb/checkpoint-92",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 207,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.346718788146973,
+      "learning_rate": 4.9e-05,
+      "loss": 3.1125,
+      "step": 23
+    },
+    {
+      "epoch": 1.0,
+      "eval_combined_score": 0.09771961858160437,
+      "eval_loss": 2.4240827560424805,
+      "eval_pearson": 0.0970349594322995,
+      "eval_runtime": 0.6241,
+      "eval_samples_per_second": 2403.619,
+      "eval_spearmanr": 0.09840427773090923,
+      "eval_steps_per_second": 9.614,
+      "step": 23
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.733392238616943,
+      "learning_rate": 4.8e-05,
+      "loss": 2.0404,
+      "step": 46
+    },
+    {
+      "epoch": 2.0,
+      "eval_combined_score": 0.0992997903966123,
+      "eval_loss": 2.612762928009033,
+      "eval_pearson": 0.10371006568293557,
+      "eval_runtime": 0.6305,
+      "eval_samples_per_second": 2379.059,
+      "eval_spearmanr": 0.09488951511028902,
+      "eval_steps_per_second": 9.516,
+      "step": 46
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.547567129135132,
+      "learning_rate": 4.7e-05,
+      "loss": 1.9426,
+      "step": 69
+    },
+    {
+      "epoch": 3.0,
+      "eval_combined_score": 0.13820986105259186,
+      "eval_loss": 2.3644304275512695,
+      "eval_pearson": 0.14567412654407727,
+      "eval_runtime": 0.6334,
+      "eval_samples_per_second": 2368.347,
+      "eval_spearmanr": 0.13074559556110643,
+      "eval_steps_per_second": 9.473,
+      "step": 69
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 15.069281578063965,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 1.8491,
+      "step": 92
+    },
+    {
+      "epoch": 4.0,
+      "eval_combined_score": 0.21502963923574336,
+      "eval_loss": 2.2779486179351807,
+      "eval_pearson": 0.21964727921544513,
+      "eval_runtime": 0.6204,
+      "eval_samples_per_second": 2417.774,
+      "eval_spearmanr": 0.21041199925604162,
+      "eval_steps_per_second": 9.671,
+      "step": 92
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 15.94198226928711,
+      "learning_rate": 4.5e-05,
+      "loss": 1.6662,
+      "step": 115
+    },
+    {
+      "epoch": 5.0,
+      "eval_combined_score": 0.1905724034749247,
+      "eval_loss": 2.5923008918762207,
+      "eval_pearson": 0.18814472493433657,
+      "eval_runtime": 0.6199,
+      "eval_samples_per_second": 2419.658,
+      "eval_spearmanr": 0.19300008201551283,
+      "eval_steps_per_second": 9.679,
+      "step": 115
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 7.709235191345215,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 1.4804,
+      "step": 138
+    },
+    {
+      "epoch": 6.0,
+      "eval_combined_score": 0.24015263217163996,
+      "eval_loss": 2.4731264114379883,
+      "eval_pearson": 0.23435596441251114,
+      "eval_runtime": 0.6372,
+      "eval_samples_per_second": 2353.913,
+      "eval_spearmanr": 0.2459492999307688,
+      "eval_steps_per_second": 9.416,
+      "step": 138
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 7.703160762786865,
+      "learning_rate": 4.3e-05,
+      "loss": 1.277,
+      "step": 161
+    },
+    {
+      "epoch": 7.0,
+      "eval_combined_score": 0.24546556526970081,
+      "eval_loss": 2.4953572750091553,
+      "eval_pearson": 0.2410173992819928,
+      "eval_runtime": 0.6815,
+      "eval_samples_per_second": 2200.875,
+      "eval_spearmanr": 0.2499137312574088,
+      "eval_steps_per_second": 8.803,
+      "step": 161
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 13.957864761352539,
+      "learning_rate": 4.2e-05,
+      "loss": 1.0894,
+      "step": 184
+    },
+    {
+      "epoch": 8.0,
+      "eval_combined_score": 0.2499256010994313,
+      "eval_loss": 2.6198463439941406,
+      "eval_pearson": 0.24235584833882048,
+      "eval_runtime": 0.6686,
+      "eval_samples_per_second": 2243.565,
+      "eval_spearmanr": 0.25749535386004213,
+      "eval_steps_per_second": 8.974,
+      "step": 184
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 17.061662673950195,
+      "learning_rate": 4.1e-05,
+      "loss": 0.8971,
+      "step": 207
+    },
+    {
+      "epoch": 9.0,
+      "eval_combined_score": 0.24241359968147133,
+      "eval_loss": 2.7564404010772705,
+      "eval_pearson": 0.23568574636172288,
+      "eval_runtime": 0.6566,
+      "eval_samples_per_second": 2284.41,
+      "eval_spearmanr": 0.2491414530012198,
+      "eval_steps_per_second": 9.138,
+      "step": 207
+    },
+    {
+      "epoch": 9.0,
+      "step": 207,
+      "total_flos": 1356793384840704.0,
+      "train_loss": 1.7060688590081994,
+      "train_runtime": 46.683,
+      "train_samples_per_second": 6157.489,
+      "train_steps_per_second": 24.634
+    }
+  ],
+  "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": 1356793384840704.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}