End of training

README.md

@@ -3,6 +3,8 @@ license: mit
 base_model: facebook/mbart-large-50
 tags:
 - generated_from_trainer
+datasets:
+- tiagoblima/qg_squad_v1_pt
 model-index:
 - name: mbart50-qg-aas
   results: []
@@ -13,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mbart50-qg-aas
 
-This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on an unknown dataset.
+This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on the tiagoblima/qg_squad_v1_pt dataset.
 It achieves the following results on the evaluation set:
 - Loss: 5.1971
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 5.0,
+    "eval_loss": 5.197052955627441,
+    "eval_runtime": 198.4096,
+    "eval_samples": 6327,
+    "eval_samples_per_second": 31.889,
+    "eval_steps_per_second": 7.973,
+    "train_loss": 4.983092109755714,
+    "train_runtime": 9308.9617,
+    "train_samples": 51704,
+    "train_samples_per_second": 27.771,
+    "train_steps_per_second": 0.434
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "eval_loss": 5.197052955627441,
+    "eval_runtime": 198.4096,
+    "eval_samples": 6327,
+    "eval_samples_per_second": 31.889,
+    "eval_steps_per_second": 7.973
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 4.983092109755714,
+    "train_runtime": 9308.9617,
+    "train_samples": 51704,
+    "train_samples_per_second": 27.771,
+    "train_steps_per_second": 0.434
+}

trainer_state.json

@@ -0,0 +1,308 @@
+{
+  "best_metric": 5.197052955627441,
+  "best_model_checkpoint": "/temp/mbart50-qg-aas/checkpoint-4040",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 4040,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.004876237623762376,
+      "loss": 7.263,
+      "step": 100
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.004752475247524752,
+      "loss": 6.8088,
+      "step": 200
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.004628712871287129,
+      "loss": 7.0507,
+      "step": 300
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0045049504950495055,
+      "loss": 7.0915,
+      "step": 400
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.004381188118811882,
+      "loss": 7.1477,
+      "step": 500
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.004257425742574258,
+      "loss": 7.0728,
+      "step": 600
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.004133663366336634,
+      "loss": 7.0668,
+      "step": 700
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00400990099009901,
+      "loss": 7.1258,
+      "step": 800
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 8.01647663116455,
+      "eval_runtime": 198.6559,
+      "eval_samples_per_second": 31.849,
+      "eval_steps_per_second": 7.964,
+      "step": 808
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0038861386138613866,
+      "loss": 6.0898,
+      "step": 900
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0037623762376237627,
+      "loss": 6.0248,
+      "step": 1000
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0036386138613861384,
+      "loss": 6.0612,
+      "step": 1100
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.0035148514851485145,
+      "loss": 6.0603,
+      "step": 1200
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.0033910891089108915,
+      "loss": 6.0599,
+      "step": 1300
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.0032673267326732676,
+      "loss": 5.9988,
+      "step": 1400
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 0.0031435643564356438,
+      "loss": 5.846,
+      "step": 1500
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 0.00301980198019802,
+      "loss": 5.7857,
+      "step": 1600
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 7.2192888259887695,
+      "eval_runtime": 198.5597,
+      "eval_samples_per_second": 31.864,
+      "eval_steps_per_second": 7.967,
+      "step": 1616
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 0.002896039603960396,
+      "loss": 5.0778,
+      "step": 1700
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 0.0027722772277227726,
+      "loss": 4.9976,
+      "step": 1800
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 0.0026485148514851487,
+      "loss": 4.9136,
+      "step": 1900
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 0.002524752475247525,
+      "loss": 4.9118,
+      "step": 2000
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 0.002400990099009901,
+      "loss": 4.8445,
+      "step": 2100
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 0.0022772277227722775,
+      "loss": 4.781,
+      "step": 2200
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 0.0021534653465346536,
+      "loss": 4.7046,
+      "step": 2300
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 0.0020297029702970298,
+      "loss": 4.6138,
+      "step": 2400
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 6.484571933746338,
+      "eval_runtime": 198.533,
+      "eval_samples_per_second": 31.869,
+      "eval_steps_per_second": 7.968,
+      "step": 2424
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 0.0019059405940594061,
+      "loss": 4.1564,
+      "step": 2500
+    },
+    {
+      "epoch": 3.22,
+      "learning_rate": 0.001782178217821782,
+      "loss": 4.031,
+      "step": 2600
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 0.0016584158415841586,
+      "loss": 4.0074,
+      "step": 2700
+    },
+    {
+      "epoch": 3.47,
+      "learning_rate": 0.0015346534653465347,
+      "loss": 3.9606,
+      "step": 2800
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 0.0014108910891089108,
+      "loss": 3.8929,
+      "step": 2900
+    },
+    {
+      "epoch": 3.71,
+      "learning_rate": 0.0012871287128712872,
+      "loss": 3.8122,
+      "step": 3000
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 0.0011633663366336635,
+      "loss": 3.8028,
+      "step": 3100
+    },
+    {
+      "epoch": 3.96,
+      "learning_rate": 0.0010396039603960397,
+      "loss": 3.6997,
+      "step": 3200
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 5.73320198059082,
+      "eval_runtime": 198.2238,
+      "eval_samples_per_second": 31.918,
+      "eval_steps_per_second": 7.981,
+      "step": 3232
+    },
+    {
+      "epoch": 4.08,
+      "learning_rate": 0.0009158415841584158,
+      "loss": 3.4137,
+      "step": 3300
+    },
+    {
+      "epoch": 4.21,
+      "learning_rate": 0.0007920792079207921,
+      "loss": 3.2744,
+      "step": 3400
+    },
+    {
+      "epoch": 4.33,
+      "learning_rate": 0.0006683168316831684,
+      "loss": 3.2317,
+      "step": 3500
+    },
+    {
+      "epoch": 4.46,
+      "learning_rate": 0.0005445544554455446,
+      "loss": 3.1649,
+      "step": 3600
+    },
+    {
+      "epoch": 4.58,
+      "learning_rate": 0.00042079207920792084,
+      "loss": 3.1132,
+      "step": 3700
+    },
+    {
+      "epoch": 4.7,
+      "learning_rate": 0.000297029702970297,
+      "loss": 3.0725,
+      "step": 3800
+    },
+    {
+      "epoch": 4.83,
+      "learning_rate": 0.00017326732673267329,
+      "loss": 3.0738,
+      "step": 3900
+    },
+    {
+      "epoch": 4.95,
+      "learning_rate": 4.950495049504951e-05,
+      "loss": 3.0051,
+      "step": 4000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 5.197052955627441,
+      "eval_runtime": 198.3119,
+      "eval_samples_per_second": 31.904,
+      "eval_steps_per_second": 7.977,
+      "step": 4040
+    },
+    {
+      "epoch": 5.0,
+      "step": 4040,
+      "total_flos": 3.6330926562607104e+17,
+      "train_loss": 4.983092109755714,
+      "train_runtime": 9308.9617,
+      "train_samples_per_second": 27.771,
+      "train_steps_per_second": 0.434
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 4040,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 3.6330926562607104e+17,
+  "trial_name": null,
+  "trial_params": null
+}