Training in progress, epoch 1, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96485eb7c607920cd754505017469a3214f305e887335f74ec1294359ec8fba7
+oid sha256:e6ac607c4b4c16928e7543894b1342e51724717ce3480383f8c838c31d4c04a4
 size 1256

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afb7005eeedf6895d3e5b147f0e299d7d5c3f1bbc19bbb111a50846f82e55bb9
+oid sha256:ae28f9b2f5015b95ad2f650d54d1979a68d40e31cc70d2fd5c54ddf3ae4a6519
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4950342cbbaedd0bab0603999a400a1f5307e42dd9ea5ac4333478fb245f0ffd
+oid sha256:fac550c17bc81a5a61f579be7c3cd944957f99fac9afc8af96fb956eda27f781
 size 1064

last-checkpoint/trainer_state.json

@@ -1,129 +1,56 @@
 {
-  "best_metric": 2.7745249271392822,
-  "best_model_checkpoint": "dq158/pingusPongus/checkpoint-6378",
-  "epoch": 2.0,
+  "best_metric": 3.066662549972534,
+  "best_model_checkpoint": "dq158/pingusPongus/checkpoint-1581",
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 12756,
+  "global_step": 1581,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.16,
-      "learning_rate": 0.00039920947174116906,
-      "loss": 2.8811,
-      "step": 1000
-    },
-    {
-      "epoch": 0.31,
-      "learning_rate": 0.00039648480371823173,
-      "loss": 2.8589,
-      "step": 2000
-    },
-    {
-      "epoch": 0.47,
-      "learning_rate": 0.0003918428175464395,
-      "loss": 2.8896,
-      "step": 3000
+      "epoch": 0.32,
+      "learning_rate": 4.967667032675337e-05,
+      "loss": 3.2269,
+      "step": 500
     },
     {
       "epoch": 0.63,
-      "learning_rate": 0.0003853288101859922,
-      "loss": 2.8554,
-      "step": 4000
-    },
-    {
-      "epoch": 0.78,
-      "learning_rate": 0.0003770063459650089,
-      "loss": 2.9077,
-      "step": 5000
+      "learning_rate": 4.837746407304061e-05,
+      "loss": 3.2202,
+      "step": 1000
     },
     {
-      "epoch": 0.94,
-      "learning_rate": 0.0003669566363125271,
-      "loss": 2.8994,
-      "step": 6000
+      "epoch": 0.95,
+      "learning_rate": 4.613457734930978e-05,
+      "loss": 3.2179,
+      "step": 1500
     },
     {
       "epoch": 1.0,
       "eval_bleu": 1.0,
       "eval_brevity_penalty": 1.0,
       "eval_length_ratio": 1.0,
-      "eval_loss": 2.7745249271392822,
-      "eval_precisions": [
-        1.0,
-        1.0,
-        1.0,
-        1.0
-      ],
-      "eval_reference_length": 5805056,
-      "eval_runtime": 7760.7176,
-      "eval_samples_per_second": 1.461,
-      "eval_steps_per_second": 0.091,
-      "eval_translation_length": 5805056,
-      "step": 6378
-    },
-    {
-      "epoch": 1.1,
-      "learning_rate": 0.00035527774728934524,
-      "loss": 2.9036,
-      "step": 7000
-    },
-    {
-      "epoch": 1.25,
-      "learning_rate": 0.00034208364264970225,
-      "loss": 2.8998,
-      "step": 8000
-    },
-    {
-      "epoch": 1.41,
-      "learning_rate": 0.00032750307177169117,
-      "loss": 2.8735,
-      "step": 9000
-    },
-    {
-      "epoch": 1.57,
-      "learning_rate": 0.00031167831330809374,
-      "loss": 2.8724,
-      "step": 10000
-    },
-    {
-      "epoch": 1.72,
-      "learning_rate": 0.00029476378681721313,
-      "loss": 2.8833,
-      "step": 11000
-    },
-    {
-      "epoch": 1.88,
-      "learning_rate": 0.00027692454592155135,
-      "loss": 2.878,
-      "step": 12000
-    },
-    {
-      "epoch": 2.0,
-      "eval_bleu": 1.0,
-      "eval_brevity_penalty": 1.0,
-      "eval_length_ratio": 1.0,
-      "eval_loss": 2.7745249271392822,
+      "eval_loss": 3.066662549972534,
       "eval_precisions": [
         1.0,
         1.0,
         1.0,
         1.0
       ],
-      "eval_reference_length": 5805056,
-      "eval_runtime": 7896.2252,
-      "eval_samples_per_second": 1.436,
-      "eval_steps_per_second": 0.09,
-      "eval_translation_length": 5805056,
-      "step": 12756
+      "eval_reference_length": 1439232,
+      "eval_runtime": 868.8432,
+      "eval_samples_per_second": 3.235,
+      "eval_steps_per_second": 0.203,
+      "eval_translation_length": 1439232,
+      "step": 1581
     }
   ],
-  "logging_steps": 1000,
-  "max_steps": 31890,
+  "logging_steps": 500,
+  "max_steps": 7905,
   "num_train_epochs": 5,
-  "save_steps": 1000,
-  "total_flos": 1.748349136542892e+18,
+  "save_steps": 500,
+  "total_flos": 2.1666322696686797e+17,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dd2903933121e6a92a30122c80cc9994899cd1aaaedd34cd64d7035bcbbb24c
+oid sha256:20086b87ec5232c7b02847cb5e045ab682b690baae2571d7dc3765d177a13545
 size 4728