Training in progress, epoch 11, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cc9ebe55774e98f2e8ad86775f276cd8ded7b6363c560e8cc4381d87b67445a
-size 2371770
+oid sha256:8b685eb47baafc7984a2354c64f3a633c89ac5489423119e83feaa1b146cbedb
+size 2372346

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47450dc9e0b278d77248d05ef1c34bd97409b0d7111b42d8afdb381c61b6751c
+oid sha256:6600748b28844d6445286c2db32da87f8f4ae7df8cb2643db5bb76ae67233234
 size 990409330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:754c90914edc0d2f5f5e31691433ae62d48ae18f50b17f4f75d023288dda9b5a
+oid sha256:4073b96953e05453b4b6e4a3030f1c740fa0e02670dbb4843214e79d4e7e84c5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:694cd02885166a75e3403878712069706f257db461ded2ae6ad6c41b84f22bf2
+oid sha256:b44cd738bffad7be53bf491009475d442fa0e6452600c820ee5979a9a8ce3a05
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.5654487609863281,
   "best_model_checkpoint": "dq158/pingusPongus/checkpoint-6323",
-  "epoch": 10.0,
+  "epoch": 11.0,
   "eval_steps": 500,
-  "global_step": 63230,
+  "global_step": 69553,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -953,13 +953,110 @@
       "eval_steps_per_second": 1.037,
       "eval_translation_length": 52485,
       "step": 63230
+    },
+    {
+      "epoch": 10.04,
+      "learning_rate": 2.498752940408342e-06,
+      "loss": 1.7938,
+      "step": 63500
+    },
+    {
+      "epoch": 10.12,
+      "learning_rate": 2.4675773582364977e-06,
+      "loss": 1.7688,
+      "step": 64000
+    },
+    {
+      "epoch": 10.2,
+      "learning_rate": 2.436406818231583e-06,
+      "loss": 1.7701,
+      "step": 64500
+    },
+    {
+      "epoch": 10.28,
+      "learning_rate": 2.4052461678414753e-06,
+      "loss": 1.7821,
+      "step": 65000
+    },
+    {
+      "epoch": 10.36,
+      "learning_rate": 2.37410025297608e-06,
+      "loss": 1.8251,
+      "step": 65500
+    },
+    {
+      "epoch": 10.44,
+      "learning_rate": 2.342973917253726e-06,
+      "loss": 1.7384,
+      "step": 66000
+    },
+    {
+      "epoch": 10.52,
+      "learning_rate": 2.3118720012479183e-06,
+      "loss": 1.8001,
+      "step": 66500
+    },
+    {
+      "epoch": 10.6,
+      "learning_rate": 2.280799341734556e-06,
+      "loss": 1.8386,
+      "step": 67000
+    },
+    {
+      "epoch": 10.68,
+      "learning_rate": 2.249760770939754e-06,
+      "loss": 1.8098,
+      "step": 67500
+    },
+    {
+      "epoch": 10.75,
+      "learning_rate": 2.218761115788362e-06,
+      "loss": 1.8059,
+      "step": 68000
+    },
+    {
+      "epoch": 10.83,
+      "learning_rate": 2.1878051971533093e-06,
+      "loss": 1.757,
+      "step": 68500
+    },
+    {
+      "epoch": 10.91,
+      "learning_rate": 2.156897829105898e-06,
+      "loss": 1.8037,
+      "step": 69000
+    },
+    {
+      "epoch": 10.99,
+      "learning_rate": 2.1260438181671446e-06,
+      "loss": 1.7714,
+      "step": 69500
+    },
+    {
+      "epoch": 11.0,
+      "eval_bleu": 1.0,
+      "eval_brevity_penalty": 1.0,
+      "eval_length_ratio": 1.0,
+      "eval_loss": 1.5735211372375488,
+      "eval_precisions": [
+        1.0,
+        1.0,
+        1.0,
+        1.0
+      ],
+      "eval_reference_length": 52469,
+      "eval_runtime": 678.026,
+      "eval_samples_per_second": 4.146,
+      "eval_steps_per_second": 1.037,
+      "eval_translation_length": 52469,
+      "step": 69553
     }
   ],
   "logging_steps": 500,
   "max_steps": 126460,
   "num_train_epochs": 20,
   "save_steps": 500,
-  "total_flos": 1.7318198200762368e+17,
+  "total_flos": 1.9050018020838605e+17,
   "trial_name": null,
   "trial_params": null
 }