Training in progress, epoch 4, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3185710f9ed48293a778de595fcd38098844825122d64b9829b1b93f6412f403
+oid sha256:de02ef88a9c06d1c4c39ca3c4c2f1202553b57c8ad4795abcd030e9f5ec610f8
 size 1980860410

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6d9360daf7120c5d39d8ef5625d204b3b6837a8189e798928f762e83a610468
+oid sha256:ef45bf07e4aa6ce72fbbd0a19258dbb992063d4bf6b046ce62330fa93b06089d
 size 990409330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbddb6a0f6f63e14b35b515dcd6478e86f1cce79a693afe0ccaec7cdbe6f4fcc
+oid sha256:0c1fd7d1cea75e4e374c54e815a21a8bbeecb72f564c49061658d53b541359df
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:727027b6d6031aa8f34a43940937c6f906ae36c7156fab65320547a0006b7c81
+oid sha256:dde9ec5a9c5afe2585b7bb2f95d066fbcef5ffc592770aca32d5e4130db08ddc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.835176944732666,
-  "best_model_checkpoint": "dq158/morbius/checkpoint-9568",
-  "epoch": 3.0,
+  "best_metric": 1.8330533504486084,
+  "best_model_checkpoint": "dq158/morbius/checkpoint-38272",
+  "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 28704,
+  "global_step": 38272,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -406,13 +406,146 @@
       "eval_steps_per_second": 1.315,
       "eval_translation_length": 107465,
       "step": 28704
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 1.9690635451505017e-05,
+      "loss": 1.9465,
+      "step": 29000
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 1.9168060200668896e-05,
+      "loss": 1.9071,
+      "step": 29500
+    },
+    {
+      "epoch": 3.14,
+      "learning_rate": 1.8645484949832775e-05,
+      "loss": 1.893,
+      "step": 30000
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 1.8122909698996657e-05,
+      "loss": 1.8895,
+      "step": 30500
+    },
+    {
+      "epoch": 3.24,
+      "learning_rate": 1.7600334448160536e-05,
+      "loss": 1.8914,
+      "step": 31000
+    },
+    {
+      "epoch": 3.29,
+      "learning_rate": 1.7077759197324418e-05,
+      "loss": 1.9214,
+      "step": 31500
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 1.6555183946488294e-05,
+      "loss": 1.8911,
+      "step": 32000
+    },
+    {
+      "epoch": 3.4,
+      "learning_rate": 1.6032608695652173e-05,
+      "loss": 1.9149,
+      "step": 32500
+    },
+    {
+      "epoch": 3.45,
+      "learning_rate": 1.5510033444816055e-05,
+      "loss": 1.902,
+      "step": 33000
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 1.4987458193979934e-05,
+      "loss": 1.9066,
+      "step": 33500
+    },
+    {
+      "epoch": 3.55,
+      "learning_rate": 1.4464882943143812e-05,
+      "loss": 1.9027,
+      "step": 34000
+    },
+    {
+      "epoch": 3.61,
+      "learning_rate": 1.3942307692307693e-05,
+      "loss": 1.9232,
+      "step": 34500
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 1.3419732441471572e-05,
+      "loss": 1.926,
+      "step": 35000
+    },
+    {
+      "epoch": 3.71,
+      "learning_rate": 1.2897157190635452e-05,
+      "loss": 1.87,
+      "step": 35500
+    },
+    {
+      "epoch": 3.76,
+      "learning_rate": 1.2374581939799331e-05,
+      "loss": 1.9055,
+      "step": 36000
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 1.1852006688963212e-05,
+      "loss": 1.952,
+      "step": 36500
+    },
+    {
+      "epoch": 3.87,
+      "learning_rate": 1.132943143812709e-05,
+      "loss": 1.8896,
+      "step": 37000
+    },
+    {
+      "epoch": 3.92,
+      "learning_rate": 1.080685618729097e-05,
+      "loss": 1.9144,
+      "step": 37500
+    },
+    {
+      "epoch": 3.97,
+      "learning_rate": 1.028428093645485e-05,
+      "loss": 1.9447,
+      "step": 38000
+    },
+    {
+      "epoch": 4.0,
+      "eval_bleu": 0.08669705678202416,
+      "eval_brevity_penalty": 0.7634478532624474,
+      "eval_length_ratio": 0.7874570959558275,
+      "eval_loss": 1.8330533504486084,
+      "eval_precisions": [
+        0.1886293646657507,
+        0.11698894134385307,
+        0.08828452928243054,
+        0.08536133232489508
+      ],
+      "eval_reference_length": 134020,
+      "eval_runtime": 811.3896,
+      "eval_samples_per_second": 15.722,
+      "eval_steps_per_second": 1.311,
+      "eval_translation_length": 105535,
+      "step": 38272
     }
   ],
   "logging_steps": 500,
   "max_steps": 47840,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 2.3584275781543526e+17,
+  "total_flos": 3.1445701042058035e+17,
   "trial_name": null,
   "trial_params": null
 }