Training in progress, epoch 3, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c4363d06929aee26c9e927701774792fb7453e840d38a5ad5a3f1d36b1be96b
+oid sha256:33cd6ceaf3e5c0a15820c9055970f910107122ac5f2692ee038a552928978e93
 size 1980860410

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96e4c9ef9cd2909c6491e22429888102a5089a17edf046aff201c9c1677a0ddc
+oid sha256:3b2efc889d52b2d6c0784b72b631f0fe873c965bb89fe3a1d443214cc2dcc088
 size 990409330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:240c04ca9a3cb29b976a770fef919a933d604a3470e1df27947f582528033848
+oid sha256:3af69a82a1b91d6e5092406535f43bc1f304899b494dcf1053de5c4be7029152
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9ba60403de9780e4b1c2244a6784efea5c6643ffcd4f768f2fe7e0521babfed
+oid sha256:8d45ce75f87aaa5b92cdc5c7abdc86c8b62d1ae1a014d3240669d9630def6c5a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.3292136192321777,
-  "best_model_checkpoint": "dq158/morbius/checkpoint-6326",
-  "epoch": 2.0,
+  "best_metric": 2.3189847469329834,
+  "best_model_checkpoint": "dq158/morbius/checkpoint-9489",
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 6326,
+  "global_step": 9489,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -117,13 +117,68 @@
       "eval_steps_per_second": 0.626,
       "eval_translation_length": 53147,
       "step": 6326
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 6.8433222607963194e-06,
+      "loss": 2.4242,
+      "step": 6500
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 6.816361474374877e-06,
+      "loss": 2.4037,
+      "step": 7000
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 6.787323321691012e-06,
+      "loss": 2.3952,
+      "step": 7500
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 6.7562259922211045e-06,
+      "loss": 2.4106,
+      "step": 8000
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 6.723088965308281e-06,
+      "loss": 2.4145,
+      "step": 8500
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 6.68793299796057e-06,
+      "loss": 2.356,
+      "step": 9000
+    },
+    {
+      "epoch": 3.0,
+      "eval_bleu": 1.0,
+      "eval_brevity_penalty": 1.0,
+      "eval_length_ratio": 1.0,
+      "eval_loss": 2.3189847469329834,
+      "eval_precisions": [
+        1.0,
+        1.0,
+        1.0,
+        1.0
+      ],
+      "eval_reference_length": 53040,
+      "eval_runtime": 561.5646,
+      "eval_samples_per_second": 5.007,
+      "eval_steps_per_second": 0.627,
+      "eval_translation_length": 53040,
+      "step": 9489
     }
   ],
   "logging_steps": 500,
   "max_steps": 63260,
   "num_train_epochs": 20,
   "save_steps": 500,
-  "total_flos": 3.465283057798349e+16,
+  "total_flos": 5.197924586697523e+16,
   "trial_name": null,
   "trial_params": null
 }