End of training

README.md

@@ -3,9 +3,23 @@ license: apache-2.0
 base_model: google/t5-small-lm-adapt
 tags:
 - generated_from_trainer
+datasets:
+- Isotonic/planner_dataset
+metrics:
+- rouge
 model-index:
 - name: plan_t5
-  results: []
+  results:
+  - task:
+      name: Summarization
+      type: summarization
+    dataset:
+      name: Isotonic/planner_dataset
+      type: Isotonic/planner_dataset
+    metrics:
+    - name: Rouge1
+      type: rouge
+      value: 58.1207
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -13,7 +27,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 # plan_t5
 
-This model is a fine-tuned version of [google/t5-small-lm-adapt](https://huggingface.co/google/t5-small-lm-adapt) on an unknown dataset.
+This model is a fine-tuned version of [google/t5-small-lm-adapt](https://huggingface.co/google/t5-small-lm-adapt) on the Isotonic/planner_dataset dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4444
+- Rouge1: 58.1207
+- Rouge2: 24.3398
+- Rougel: 58.1271
+- Rougelsum: 58.1292
+- Gen Len: 7.9747
 
 ## Model description
 

all_results.json

@@ -0,0 +1,18 @@
+{
+    "epoch": 1.0,
+    "eval_gen_len": 7.9747384536871655,
+    "eval_loss": 1.4443535804748535,
+    "eval_rouge1": 58.1207,
+    "eval_rouge2": 24.3398,
+    "eval_rougeL": 58.1271,
+    "eval_rougeLsum": 58.1292,
+    "eval_runtime": 237.0503,
+    "eval_samples": 7838,
+    "eval_samples_per_second": 33.065,
+    "eval_steps_per_second": 4.134,
+    "train_loss": 1.643041113804542,
+    "train_runtime": 148.4875,
+    "train_samples": 31349,
+    "train_samples_per_second": 211.122,
+    "train_steps_per_second": 26.393
+}

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_gen_len": 7.9747384536871655,
+    "eval_loss": 1.4443535804748535,
+    "eval_rouge1": 58.1207,
+    "eval_rouge2": 24.3398,
+    "eval_rougeL": 58.1271,
+    "eval_rougeLsum": 58.1292,
+    "eval_runtime": 237.0503,
+    "eval_samples": 7838,
+    "eval_samples_per_second": 33.065,
+    "eval_steps_per_second": 4.134
+}

generation_config.json

@@ -1,5 +1,4 @@
 {
-  "_from_model_config": true,
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.643041113804542,
+    "train_runtime": 148.4875,
+    "train_samples": 31349,
+    "train_samples_per_second": 211.122,
+    "train_steps_per_second": 26.393
+}

trainer_state.json

@@ -0,0 +1,79 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 3919,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13,
+      "grad_norm": 1.9183778762817383,
+      "learning_rate": 3.188775510204082e-05,
+      "loss": 2.8223,
+      "step": 500
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 2.046781539916992,
+      "learning_rate": 4.655502392344498e-05,
+      "loss": 1.5043,
+      "step": 1000
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.9903734922409058,
+      "learning_rate": 3.8580542264752795e-05,
+      "loss": 1.4817,
+      "step": 1500
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 1.7653305530548096,
+      "learning_rate": 3.060606060606061e-05,
+      "loss": 1.4671,
+      "step": 2000
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.9060845375061035,
+      "learning_rate": 2.2631578947368423e-05,
+      "loss": 1.4637,
+      "step": 2500
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 1.784713625907898,
+      "learning_rate": 1.4657097288676236e-05,
+      "loss": 1.4588,
+      "step": 3000
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 1.737605094909668,
+      "learning_rate": 6.6826156299840516e-06,
+      "loss": 1.4615,
+      "step": 3500
+    },
+    {
+      "epoch": 1.0,
+      "step": 3919,
+      "total_flos": 102290970089472.0,
+      "train_loss": 1.643041113804542,
+      "train_runtime": 148.4875,
+      "train_samples_per_second": 211.122,
+      "train_steps_per_second": 26.393
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3919,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 102290970089472.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}