Training in progress, epoch 2, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9dab3c237778abcdc6020386d5d6aa7d91bf8f2f12d9072e55f02ac241a9d8f
+oid sha256:46abff71e7026647c05fbaf7f699e8ee421c0a2e584b794f2fb0c530d4b1f4b4
 size 1980859973

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f7fa3bbd5872f4ad1210653805e664a05fa2a4d3c7b54fcc57b41c643262594
+oid sha256:95635d8117e24e5efeb681934dc5313da771c7b857de60f1ac43e8245d9484ab
 size 990408885

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f886a97068c2df9888daf16e7cbd0ea9a12de504b206548c880a0b888a429bcb
+oid sha256:4844a5d656111932c3ceada711e9cbb272e49c0cfedd858f395737c72b4c6992
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73a4b9df454edb9352836894520e4dbf710c154432a1dc2d702b1ac3e1210897
+oid sha256:5371d45631fd7dd6529335dfaa6166f363409fc22e7123a04a9a24603e02dcb6
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.766650676727295,
-  "best_model_checkpoint": "dq158/morbius/checkpoint-3042",
-  "epoch": 1.0,
+  "best_metric": 2.6461355686187744,
+  "best_model_checkpoint": "dq158/morbius/checkpoint-6084",
+  "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 3042,
+  "global_step": 6084,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -62,13 +62,68 @@
       "eval_steps_per_second": 2.008,
       "eval_translation_length": 20952,
       "step": 3042
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 3.849441157133465e-05,
+      "loss": 2.8856,
+      "step": 3500
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 3.685075608152531e-05,
+      "loss": 2.7807,
+      "step": 4000
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 3.520710059171598e-05,
+      "loss": 2.8137,
+      "step": 4500
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 3.356344510190664e-05,
+      "loss": 2.7763,
+      "step": 5000
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 3.191978961209731e-05,
+      "loss": 2.7614,
+      "step": 5500
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 3.027613412228797e-05,
+      "loss": 2.7698,
+      "step": 6000
+    },
+    {
+      "epoch": 2.0,
+      "eval_bleu": 0.02664930121135747,
+      "eval_brevity_penalty": 0.3202391817768093,
+      "eval_length_ratio": 0.4675765758163868,
+      "eval_loss": 2.6461355686187744,
+      "eval_precisions": [
+        0.19675163546131288,
+        0.11093931194433707,
+        0.04774781185511991,
+        0.04601380414124237
+      ],
+      "eval_reference_length": 47404,
+      "eval_runtime": 185.4708,
+      "eval_samples_per_second": 21.869,
+      "eval_steps_per_second": 1.822,
+      "eval_translation_length": 22165,
+      "step": 6084
     }
   ],
   "logging_steps": 500,
   "max_steps": 15210,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 2.499021957758976e+16,
+  "total_flos": 4.998043915517952e+16,
   "trial_name": null,
   "trial_params": null
 }