Training in progress, epoch 1, checkpoint

last-checkpoint/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7eaa51169fb5f5f33b328f26090dcd19a47bde0a9efe64e78856dbbe04a07e7a
-size 888
+oid sha256:cb9389791a3d0c9a79fbca9528f0f75ee24f377d83500dbcb49237253a3e3582
+size 18980874

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:904b02e1e6c26215ea888d3f8f6d7aafb77206ed1937def3937a940637da0f1c
-size 2372346
+oid sha256:026c40db959a890a16600f2337a05279f713e0057d5184b566a36aa8e88d4325
+size 37990394

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07f9db347331ffb79c2e2cf5b87f5ee3885eb3ce501d58242d83ec8e3cae758d
+oid sha256:f8f8922c352ab63d1593bcb944e77d461472df192dcdc1202984e9e08f16a111
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae3274533ddd7159e50e851656ea6e92a09b25d95e547026de312a25757234d5
+oid sha256:7cf928e904a1da7eec5bc881ec510beaeb0bdf78d28158a3fd93dd9f7b26f2b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,100 +1,110 @@
 {
-  "best_metric": 2.2401010990142822,
-  "best_model_checkpoint": "dq158/pingusPongus/checkpoint-2371",
-  "epoch": 2.9993674889310564,
+  "best_metric": 2.4926838874816895,
+  "best_model_checkpoint": "dq158/pingusPongus/checkpoint-6323",
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 2371,
+  "global_step": 6323,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.63,
-      "learning_rate": 8.49777221180502e-05,
-      "loss": 2.8794,
+      "epoch": 0.08,
+      "learning_rate": 0.0003333333333333333,
+      "loss": 3.14,
       "step": 500
     },
     {
-      "epoch": 1.0,
-      "eval_bleu": 1.0,
-      "eval_brevity_penalty": 1.0,
-      "eval_length_ratio": 1.0,
-      "eval_loss": 2.392251491546631,
-      "eval_precisions": [
-        1.0,
-        1.0,
-        1.0,
-        1.0
-      ],
-      "eval_reference_length": 53098,
-      "eval_runtime": 1401.0268,
-      "eval_samples_per_second": 2.006,
-      "eval_steps_per_second": 0.126,
-      "eval_translation_length": 53098,
-      "step": 790
-    },
-    {
-      "epoch": 1.27,
-      "learning_rate": 9.445572420019074e-05,
-      "loss": 2.5652,
+      "epoch": 0.16,
+      "learning_rate": 0.0006666666666666666,
+      "loss": 2.6622,
       "step": 1000
     },
     {
-      "epoch": 1.9,
-      "learning_rate": 9.999999999999999e-05,
-      "loss": 2.468,
+      "epoch": 0.24,
+      "learning_rate": 0.001,
+      "loss": 2.7054,
       "step": 1500
     },
     {
-      "epoch": 2.0,
-      "eval_bleu": 1.0,
-      "eval_brevity_penalty": 1.0,
-      "eval_length_ratio": 1.0,
-      "eval_loss": 2.288722038269043,
-      "eval_precisions": [
-        1.0,
-        1.0,
-        1.0,
-        1.0
-      ],
-      "eval_reference_length": 53391,
-      "eval_runtime": 1340.9293,
-      "eval_samples_per_second": 2.096,
-      "eval_steps_per_second": 0.131,
-      "eval_translation_length": 53391,
-      "step": 1581
+      "epoch": 0.32,
+      "learning_rate": 0.0009999825825666724,
+      "loss": 2.6612,
+      "step": 2000
     },
     {
-      "epoch": 2.53,
-      "learning_rate": 0.0001,
-      "loss": 2.4165,
-      "step": 2000
+      "epoch": 0.4,
+      "learning_rate": 0.0009999303314801573,
+      "loss": 2.612,
+      "step": 2500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.000999843250380774,
+      "loss": 2.6543,
+      "step": 3000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0009997213453354398,
+      "loss": 2.6882,
+      "step": 3500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.000999564624837246,
+      "loss": 2.6739,
+      "step": 4000
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0009993730998048686,
+      "loss": 2.6112,
+      "step": 4500
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0009991467835818054,
+      "loss": 2.5963,
+      "step": 5000
     },
     {
-      "epoch": 3.0,
+      "epoch": 0.87,
+      "learning_rate": 0.000998885691935447,
+      "loss": 2.5945,
+      "step": 5500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.000998589843055979,
+      "loss": 2.5457,
+      "step": 6000
+    },
+    {
+      "epoch": 1.0,
       "eval_bleu": 1.0,
       "eval_brevity_penalty": 1.0,
       "eval_length_ratio": 1.0,
-      "eval_loss": 2.2401010990142822,
+      "eval_loss": 2.4926838874816895,
       "eval_precisions": [
         1.0,
         1.0,
         1.0,
         1.0
       ],
-      "eval_reference_length": 53401,
-      "eval_runtime": 1342.5303,
-      "eval_samples_per_second": 2.094,
-      "eval_steps_per_second": 0.131,
-      "eval_translation_length": 53401,
-      "step": 2371
+      "eval_reference_length": 50598,
+      "eval_runtime": 1532.5219,
+      "eval_samples_per_second": 1.834,
+      "eval_steps_per_second": 0.917,
+      "eval_translation_length": 50598,
+      "step": 6323
     }
   ],
   "logging_steps": 500,
-  "max_steps": 23700,
+  "max_steps": 189690,
   "num_train_epochs": 30,
   "save_steps": 500,
-  "total_flos": 1158039818207232.0,
+  "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 sha256:7619c25d1f961a939120b81d521c14f9d13e3f5fcb5ceba87a0c9e7d8c62891c
-size 6648
+oid sha256:a6b5c798b857e4f110f443e0cb3a626e3d708db5518d90ee31d9206407bec991
+size 4664