End of training

README.md

@@ -16,6 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 # debug_seq2seq_squad
 
 This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the squad_v2 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.9764
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 1.976380467414856,
+    "eval_runtime": 106.9772,
+    "eval_samples": 12267,
+    "eval_samples_per_second": 114.669,
+    "eval_steps_per_second": 14.34,
+    "train_loss": 1.9922608349204722,
+    "train_runtime": 7012.8751,
+    "train_samples": 130319,
+    "train_samples_per_second": 37.166,
+    "train_steps_per_second": 3.097
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 1.976380467414856,
+    "eval_runtime": 106.9772,
+    "eval_samples": 12267,
+    "eval_samples_per_second": 114.669,
+    "eval_steps_per_second": 14.34
+}

runs/Nov28_09-28-45_43fe4c10e15a/events.out.tfevents.1701171037.43fe4c10e15a.986.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1097f27eaa6bbdf4dbc23871c78e38ff3ea4911c2026e93a0419e300e55a5e22
+size 364

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 1.9922608349204722,
+    "train_runtime": 7012.8751,
+    "train_samples": 130319,
+    "train_samples_per_second": 37.166,
+    "train_steps_per_second": 3.097
+}

trainer_state.json

@@ -0,0 +1,286 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 21720,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.930939226519337e-05,
+      "loss": 2.0443,
+      "step": 500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.861878453038674e-05,
+      "loss": 2.0083,
+      "step": 1000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.7928176795580113e-05,
+      "loss": 2.0213,
+      "step": 1500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 2.7237569060773482e-05,
+      "loss": 2.0025,
+      "step": 2000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 2.6546961325966852e-05,
+      "loss": 1.976,
+      "step": 2500
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 2.585635359116022e-05,
+      "loss": 2.0151,
+      "step": 3000
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 2.516574585635359e-05,
+      "loss": 1.9824,
+      "step": 3500
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 2.4475138121546964e-05,
+      "loss": 1.9815,
+      "step": 4000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.3784530386740334e-05,
+      "loss": 1.988,
+      "step": 4500
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.3093922651933703e-05,
+      "loss": 1.9769,
+      "step": 5000
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.2403314917127073e-05,
+      "loss": 1.9668,
+      "step": 5500
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.1712707182320442e-05,
+      "loss": 1.9765,
+      "step": 6000
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 2.1022099447513815e-05,
+      "loss": 2.0408,
+      "step": 6500
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 2.0331491712707185e-05,
+      "loss": 2.052,
+      "step": 7000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.9640883977900554e-05,
+      "loss": 2.0649,
+      "step": 7500
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.8950276243093924e-05,
+      "loss": 2.0353,
+      "step": 8000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.825966850828729e-05,
+      "loss": 2.0307,
+      "step": 8500
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.7569060773480663e-05,
+      "loss": 2.0445,
+      "step": 9000
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.6878453038674033e-05,
+      "loss": 2.0231,
+      "step": 9500
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.6187845303867402e-05,
+      "loss": 2.0082,
+      "step": 10000
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.5497237569060772e-05,
+      "loss": 2.0162,
+      "step": 10500
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.4806629834254145e-05,
+      "loss": 2.0191,
+      "step": 11000
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.4116022099447514e-05,
+      "loss": 1.9899,
+      "step": 11500
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.3425414364640886e-05,
+      "loss": 2.0006,
+      "step": 12000
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.2734806629834255e-05,
+      "loss": 1.9936,
+      "step": 12500
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.2044198895027623e-05,
+      "loss": 1.9787,
+      "step": 13000
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.1353591160220994e-05,
+      "loss": 1.9711,
+      "step": 13500
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.0662983425414364e-05,
+      "loss": 1.953,
+      "step": 14000
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 9.972375690607735e-06,
+      "loss": 1.9803,
+      "step": 14500
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 9.281767955801105e-06,
+      "loss": 1.9653,
+      "step": 15000
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 8.591160220994474e-06,
+      "loss": 1.9643,
+      "step": 15500
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 7.900552486187846e-06,
+      "loss": 1.9663,
+      "step": 16000
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 7.209944751381215e-06,
+      "loss": 1.9701,
+      "step": 16500
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 6.519337016574586e-06,
+      "loss": 1.9657,
+      "step": 17000
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 5.828729281767956e-06,
+      "loss": 1.9622,
+      "step": 17500
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 5.1381215469613265e-06,
+      "loss": 1.9683,
+      "step": 18000
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 4.447513812154697e-06,
+      "loss": 1.9654,
+      "step": 18500
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 3.756906077348067e-06,
+      "loss": 1.9609,
+      "step": 19000
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 3.0662983425414365e-06,
+      "loss": 1.9639,
+      "step": 19500
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 2.375690607734807e-06,
+      "loss": 1.9848,
+      "step": 20000
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.6850828729281769e-06,
+      "loss": 1.975,
+      "step": 20500
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 9.944751381215469e-07,
+      "loss": 1.9509,
+      "step": 21000
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 3.0386740331491715e-07,
+      "loss": 1.9651,
+      "step": 21500
+    },
+    {
+      "epoch": 2.0,
+      "step": 21720,
+      "total_flos": 2.645641233904435e+16,
+      "train_loss": 1.9922608349204722,
+      "train_runtime": 7012.8751,
+      "train_samples_per_second": 37.166,
+      "train_steps_per_second": 3.097
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 21720,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 2.645641233904435e+16,
+  "trial_name": null,
+  "trial_params": null
+}