Training in progress, epoch 5, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de02ef88a9c06d1c4c39ca3c4c2f1202553b57c8ad4795abcd030e9f5ec610f8
+oid sha256:0a719ae057e05af32962d3c0b0a042e87e0340cd8be875b7011b5d7c0a11eb6c
 size 1980860410

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef45bf07e4aa6ce72fbbd0a19258dbb992063d4bf6b046ce62330fa93b06089d
+oid sha256:20dab4a02d1fc1823157099879eca284bd66f0c8febf3dba5cfc87be7c9c9028
 size 990409330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c1fd7d1cea75e4e374c54e815a21a8bbeecb72f564c49061658d53b541359df
+oid sha256:bfda48251ec49dae4ce59144bf0a41ddf1eaebff873a2c756112a5149466e4b8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dde9ec5a9c5afe2585b7bb2f95d066fbcef5ffc592770aca32d5e4130db08ddc
+oid sha256:d5cbe3af0ede50d3acac3ddaa7d06c821cbab27a0479e23f99d3fb100db2c5e0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.8330533504486084,
-  "best_model_checkpoint": "dq158/morbius/checkpoint-38272",
-  "epoch": 4.0,
+  "best_metric": 1.8320603370666504,
+  "best_model_checkpoint": "dq158/morbius/checkpoint-47840",
+  "epoch": 5.0,
   "eval_steps": 500,
-  "global_step": 38272,
+  "global_step": 47840,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -539,13 +539,146 @@
       "eval_steps_per_second": 1.311,
       "eval_translation_length": 105535,
       "step": 38272
+    },
+    {
+      "epoch": 4.02,
+      "learning_rate": 9.76170568561873e-06,
+      "loss": 1.9148,
+      "step": 38500
+    },
+    {
+      "epoch": 4.08,
+      "learning_rate": 9.239130434782608e-06,
+      "loss": 1.9031,
+      "step": 39000
+    },
+    {
+      "epoch": 4.13,
+      "learning_rate": 8.716555183946488e-06,
+      "loss": 1.8884,
+      "step": 39500
+    },
+    {
+      "epoch": 4.18,
+      "learning_rate": 8.193979933110369e-06,
+      "loss": 1.8267,
+      "step": 40000
+    },
+    {
+      "epoch": 4.23,
+      "learning_rate": 7.671404682274248e-06,
+      "loss": 1.8556,
+      "step": 40500
+    },
+    {
+      "epoch": 4.29,
+      "learning_rate": 7.148829431438127e-06,
+      "loss": 1.9098,
+      "step": 41000
+    },
+    {
+      "epoch": 4.34,
+      "learning_rate": 6.6262541806020064e-06,
+      "loss": 1.8693,
+      "step": 41500
+    },
+    {
+      "epoch": 4.39,
+      "learning_rate": 6.103678929765887e-06,
+      "loss": 1.8622,
+      "step": 42000
+    },
+    {
+      "epoch": 4.44,
+      "learning_rate": 5.581103678929766e-06,
+      "loss": 1.8848,
+      "step": 42500
+    },
+    {
+      "epoch": 4.49,
+      "learning_rate": 5.0585284280936456e-06,
+      "loss": 1.8998,
+      "step": 43000
+    },
+    {
+      "epoch": 4.55,
+      "learning_rate": 4.535953177257525e-06,
+      "loss": 1.9059,
+      "step": 43500
+    },
+    {
+      "epoch": 4.6,
+      "learning_rate": 4.013377926421405e-06,
+      "loss": 1.8852,
+      "step": 44000
+    },
+    {
+      "epoch": 4.65,
+      "learning_rate": 3.4908026755852843e-06,
+      "loss": 1.8984,
+      "step": 44500
+    },
+    {
+      "epoch": 4.7,
+      "learning_rate": 2.968227424749164e-06,
+      "loss": 1.8517,
+      "step": 45000
+    },
+    {
+      "epoch": 4.76,
+      "learning_rate": 2.4456521739130437e-06,
+      "loss": 1.917,
+      "step": 45500
+    },
+    {
+      "epoch": 4.81,
+      "learning_rate": 1.9230769230769234e-06,
+      "loss": 1.9134,
+      "step": 46000
+    },
+    {
+      "epoch": 4.86,
+      "learning_rate": 1.4005016722408027e-06,
+      "loss": 1.8772,
+      "step": 46500
+    },
+    {
+      "epoch": 4.91,
+      "learning_rate": 8.779264214046823e-07,
+      "loss": 1.8938,
+      "step": 47000
+    },
+    {
+      "epoch": 4.96,
+      "learning_rate": 3.553511705685619e-07,
+      "loss": 1.8652,
+      "step": 47500
+    },
+    {
+      "epoch": 5.0,
+      "eval_bleu": 0.08741495854193439,
+      "eval_brevity_penalty": 0.7850055548072304,
+      "eval_length_ratio": 0.8051111774362035,
+      "eval_loss": 1.8320603370666504,
+      "eval_precisions": [
+        0.1860501756239516,
+        0.11514125956444968,
+        0.08657509646419298,
+        0.08290830945558739
+      ],
+      "eval_reference_length": 134020,
+      "eval_runtime": 812.8238,
+      "eval_samples_per_second": 15.695,
+      "eval_steps_per_second": 1.309,
+      "eval_translation_length": 107901,
+      "step": 47840
     }
   ],
   "logging_steps": 500,
   "max_steps": 47840,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 3.1445701042058035e+17,
+  "total_flos": 3.9307126302572544e+17,
   "trial_name": null,
   "trial_params": null
 }