Training in progress, epoch 0, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbb86fa29711cf73451d69e586219dc470cb08aab773a082701f4b0fcbdaf4c7
+oid sha256:de9f7349e10ab07fbbab35c81b7c16c073894cf48a4823d5a647d9beb10ab1d9
 size 1980860410

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aac2642f5ba22de9083d70a10604febed07cca571c19c26458004ebbdac32966
+oid sha256:ee592dbae667820974bbd15f0c1b0ae8e0fefa72082fd091f319110fafb11fea
 size 990409330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0918241e306ad03e3674267c638e43ba42adbfe63c16a1af28aeac15987292e
+oid sha256:9cea44ad93fec8c4df820561aaed097d102f17e9be600b9a116f68fe9875b8e4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09b06431adab47657a4d073f438d7ff4af6825fbc0fd1c3f5af310d4b27c3079
+oid sha256:3748f341e085f7325569224502631ef6799be280580e4e62c27664eaf0caf83b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,232 +1,44 @@
 {
-  "best_metric": 1.9787917137145996,
+  "best_metric": 2.020920515060425,
   "best_model_checkpoint": "dq158/morbius/checkpoint-790",
-  "epoch": 8.999051533354411,
+  "epoch": 0.9993674889310563,
   "eval_steps": 500,
-  "global_step": 3558,
+  "global_step": 790,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 1.0,
-      "eval_bleu": 1.0,
-      "eval_brevity_penalty": 1.0,
-      "eval_length_ratio": 1.0,
-      "eval_loss": 1.9788066148757935,
-      "eval_precisions": [
-        1.0,
-        1.0,
-        1.0,
-        1.0
-      ],
-      "eval_reference_length": 52082,
-      "eval_runtime": 562.3039,
-      "eval_samples_per_second": 5.001,
-      "eval_steps_per_second": 0.626,
-      "eval_translation_length": 52082,
-      "step": 395
-    },
-    {
-      "epoch": 1.26,
+      "epoch": 0.63,
       "learning_rate": 7e-06,
-      "loss": 2.1674,
+      "loss": 2.15,
       "step": 500
     },
     {
-      "epoch": 2.0,
+      "epoch": 1.0,
       "eval_bleu": 1.0,
       "eval_brevity_penalty": 1.0,
       "eval_length_ratio": 1.0,
-      "eval_loss": 1.9787917137145996,
+      "eval_loss": 2.020920515060425,
       "eval_precisions": [
         1.0,
         1.0,
         1.0,
         1.0
       ],
-      "eval_reference_length": 52066,
-      "eval_runtime": 558.9789,
-      "eval_samples_per_second": 5.031,
-      "eval_steps_per_second": 0.63,
-      "eval_translation_length": 52066,
+      "eval_reference_length": 51925,
+      "eval_runtime": 586.8865,
+      "eval_samples_per_second": 4.79,
+      "eval_steps_per_second": 0.6,
+      "eval_translation_length": 51925,
       "step": 790
-    },
-    {
-      "epoch": 2.53,
-      "learning_rate": 6.921443336316902e-06,
-      "loss": 2.1635,
-      "step": 1000
-    },
-    {
-      "epoch": 3.0,
-      "eval_bleu": 1.0,
-      "eval_brevity_penalty": 1.0,
-      "eval_length_ratio": 1.0,
-      "eval_loss": 1.9789754152297974,
-      "eval_precisions": [
-        1.0,
-        1.0,
-        1.0,
-        1.0
-      ],
-      "eval_reference_length": 51990,
-      "eval_runtime": 559.2395,
-      "eval_samples_per_second": 5.028,
-      "eval_steps_per_second": 0.629,
-      "eval_translation_length": 51990,
-      "step": 1186
-    },
-    {
-      "epoch": 3.79,
-      "learning_rate": 6.689299716358475e-06,
-      "loss": 2.1668,
-      "step": 1500
-    },
-    {
-      "epoch": 4.0,
-      "eval_bleu": 1.0,
-      "eval_brevity_penalty": 1.0,
-      "eval_length_ratio": 1.0,
-      "eval_loss": 1.9790551662445068,
-      "eval_precisions": [
-        1.0,
-        1.0,
-        1.0,
-        1.0
-      ],
-      "eval_reference_length": 52127,
-      "eval_runtime": 559.2844,
-      "eval_samples_per_second": 5.028,
-      "eval_steps_per_second": 0.629,
-      "eval_translation_length": 52127,
-      "step": 1581
-    },
-    {
-      "epoch": 5.0,
-      "eval_bleu": 1.0,
-      "eval_brevity_penalty": 1.0,
-      "eval_length_ratio": 1.0,
-      "eval_loss": 1.9790822267532349,
-      "eval_precisions": [
-        1.0,
-        1.0,
-        1.0,
-        1.0
-      ],
-      "eval_reference_length": 52050,
-      "eval_runtime": 559.5182,
-      "eval_samples_per_second": 5.026,
-      "eval_steps_per_second": 0.629,
-      "eval_translation_length": 52050,
-      "step": 1976
-    },
-    {
-      "epoch": 5.06,
-      "learning_rate": 6.313989956284292e-06,
-      "loss": 2.1554,
-      "step": 2000
-    },
-    {
-      "epoch": 6.0,
-      "eval_bleu": 1.0,
-      "eval_brevity_penalty": 1.0,
-      "eval_length_ratio": 1.0,
-      "eval_loss": 1.9794400930404663,
-      "eval_precisions": [
-        1.0,
-        1.0,
-        1.0,
-        1.0
-      ],
-      "eval_reference_length": 51951,
-      "eval_runtime": 559.0901,
-      "eval_samples_per_second": 5.03,
-      "eval_steps_per_second": 0.63,
-      "eval_translation_length": 51951,
-      "step": 2372
-    },
-    {
-      "epoch": 6.32,
-      "learning_rate": 5.812361531865285e-06,
-      "loss": 2.1567,
-      "step": 2500
-    },
-    {
-      "epoch": 7.0,
-      "eval_bleu": 1.0,
-      "eval_brevity_penalty": 1.0,
-      "eval_length_ratio": 1.0,
-      "eval_loss": 1.9794704914093018,
-      "eval_precisions": [
-        1.0,
-        1.0,
-        1.0,
-        1.0
-      ],
-      "eval_reference_length": 51995,
-      "eval_runtime": 560.6932,
-      "eval_samples_per_second": 5.015,
-      "eval_steps_per_second": 0.628,
-      "eval_translation_length": 51995,
-      "step": 2767
-    },
-    {
-      "epoch": 7.59,
-      "learning_rate": 5.2069323033477215e-06,
-      "loss": 2.1498,
-      "step": 3000
-    },
-    {
-      "epoch": 8.0,
-      "eval_bleu": 1.0,
-      "eval_brevity_penalty": 1.0,
-      "eval_length_ratio": 1.0,
-      "eval_loss": 1.9796102046966553,
-      "eval_precisions": [
-        1.0,
-        1.0,
-        1.0,
-        1.0
-      ],
-      "eval_reference_length": 51999,
-      "eval_runtime": 559.6356,
-      "eval_samples_per_second": 5.025,
-      "eval_steps_per_second": 0.629,
-      "eval_translation_length": 51999,
-      "step": 3163
-    },
-    {
-      "epoch": 8.85,
-      "learning_rate": 4.524879699467926e-06,
-      "loss": 2.156,
-      "step": 3500
-    },
-    {
-      "epoch": 9.0,
-      "eval_bleu": 1.0,
-      "eval_brevity_penalty": 1.0,
-      "eval_length_ratio": 1.0,
-      "eval_loss": 1.979423999786377,
-      "eval_precisions": [
-        1.0,
-        1.0,
-        1.0,
-        1.0
-      ],
-      "eval_reference_length": 52017,
-      "eval_runtime": 559.6401,
-      "eval_samples_per_second": 5.025,
-      "eval_steps_per_second": 0.629,
-      "eval_translation_length": 52017,
-      "step": 3558
     }
   ],
   "logging_steps": 500,
-  "max_steps": 7900,
+  "max_steps": 15800,
   "num_train_epochs": 20,
   "save_steps": 500,
-  "total_flos": 1.559377376009257e+17,
+  "total_flos": 1.7318198200762368e+16,
   "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:c408916aa246237e209139265c17d14ec7bf9a464d1448431deb99f86d00dad9
+oid sha256:7af9a47e418d2a9c2fe4c88063e63e0b297c00b773de28984542d2af72871b77
 size 4664