Training in progress, epoch 2, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ab5328b63a8ec3b53c2f26a99111049d2792ac322fccebc0739829ebfab0879
+oid sha256:6393b8f0ca5e88756c2083d1f2a1907a0f9a6dbb6883be0a4876e58b8454d9e5
 size 1980860410

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0afe6c8cd50d6bcf5ad6cb45258efb15f89d523168c877fac499ab3891b636e
+oid sha256:c614a827b995ce3eaf6b4ca43b101bd027894d4a25801ccc43d2a50633f617fc
 size 990409330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52a28bc3541f02e8de86363b8d2f634108f83fb8b7a33f774c760cce0869599d
+oid sha256:86155979fa4274be782ec567e9a698db195e65592845142c9f3ce5d5d0bead1a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5afd8d09736ea35ab4f783803d2aca249bf98e9d0591be216198fe2ebe96a3c3
+oid sha256:0d9908d10066d14a0312f52aee3b01a644d08d03fb490399a3d67eceed366c84
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4803038835525513,
-  "best_model_checkpoint": "dq158/morbius/checkpoint-1475",
-  "epoch": 1.0,
+  "best_metric": 1.4565129280090332,
+  "best_model_checkpoint": "dq158/morbius/checkpoint-2950",
+  "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 1475,
+  "global_step": 2950,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -38,13 +38,50 @@
       "eval_steps_per_second": 0.555,
       "eval_translation_length": 35996,
       "step": 1475
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 3.983050847457627e-05,
+      "loss": 1.7275,
+      "step": 1500
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 3.644067796610169e-05,
+      "loss": 1.6924,
+      "step": 2000
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 3.305084745762712e-05,
+      "loss": 1.6815,
+      "step": 2500
+    },
+    {
+      "epoch": 2.0,
+      "eval_bleu": 1.0,
+      "eval_brevity_penalty": 1.0,
+      "eval_length_ratio": 1.0,
+      "eval_loss": 1.4565129280090332,
+      "eval_precisions": [
+        1.0,
+        1.0,
+        1.0,
+        1.0
+      ],
+      "eval_reference_length": 35935,
+      "eval_runtime": 291.4973,
+      "eval_samples_per_second": 6.744,
+      "eval_steps_per_second": 0.563,
+      "eval_translation_length": 35935,
+      "step": 2950
     }
   ],
   "logging_steps": 500,
   "max_steps": 7375,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 1.2116096594214912e+16,
+  "total_flos": 2.4232193188429824e+16,
   "trial_name": null,
   "trial_params": null
 }