Training in progress, epoch 4, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6050f38120b0e933aecb28cd28fb9c7925ebc96441d3fad1965b4adf303d89fd
+oid sha256:4ff7f9757e809d561c115e2938e4b1e054f12512e4faa14683175bf1da61b830
 size 1980859973

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a7994a97f599475aa5874b645c4945821ebf2eb2b2f90ad0971c97bb6cef71b
+oid sha256:298ba19a4609d7dd947bbb269dd9f6739bce5396313593cc5c633140fa54700e
 size 990408885

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d79d8043ba95baf61ac1e0e9419f144c2c0f76428640c86753d23d96ba746f8
+oid sha256:71cc14f2f2a99ed544f7de8010d2c41e8d37087bf31674d350dddb637d0ba4aa
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9508142e5058d0d70d25ee8e25948935ec2c9917db374dac6856edde91f4a56
+oid sha256:b3fb20f868db7426ac2664add45589679b3c5c8958de4e6a4cecd76b00023e37
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.596039056777954,
-  "best_model_checkpoint": "dq158/morbius/checkpoint-9126",
-  "epoch": 3.0,
+  "best_metric": 2.574343204498291,
+  "best_model_checkpoint": "dq158/morbius/checkpoint-12168",
+  "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 9126,
+  "global_step": 12168,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -172,13 +172,68 @@
       "eval_steps_per_second": 1.852,
       "eval_translation_length": 21857,
       "step": 9126
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 1.8770545693622618e-05,
+      "loss": 2.623,
+      "step": 9500
+    },
+    {
+      "epoch": 3.29,
+      "learning_rate": 1.712689020381328e-05,
+      "loss": 2.5525,
+      "step": 10000
+    },
+    {
+      "epoch": 3.45,
+      "learning_rate": 1.5483234714003947e-05,
+      "loss": 2.588,
+      "step": 10500
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 1.383957922419461e-05,
+      "loss": 2.5647,
+      "step": 11000
+    },
+    {
+      "epoch": 3.78,
+      "learning_rate": 1.2195923734385272e-05,
+      "loss": 2.6204,
+      "step": 11500
+    },
+    {
+      "epoch": 3.94,
+      "learning_rate": 1.0552268244575937e-05,
+      "loss": 2.5252,
+      "step": 12000
+    },
+    {
+      "epoch": 4.0,
+      "eval_bleu": 0.03287297231720298,
+      "eval_brevity_penalty": 0.43553095757456056,
+      "eval_length_ratio": 0.5460931566956375,
+      "eval_loss": 2.574343204498291,
+      "eval_precisions": [
+        0.1792405454475219,
+        0.09962896798131098,
+        0.044444444444444446,
+        0.040892193308550186
+      ],
+      "eval_reference_length": 47404,
+      "eval_runtime": 209.5543,
+      "eval_samples_per_second": 19.355,
+      "eval_steps_per_second": 1.613,
+      "eval_translation_length": 25887,
+      "step": 12168
     }
   ],
   "logging_steps": 500,
   "max_steps": 15210,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 7.497065873276928e+16,
+  "total_flos": 9.996087831035904e+16,
   "trial_name": null,
   "trial_params": null
 }