Training in progress, epoch 12, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b685eb47baafc7984a2354c64f3a633c89ac5489423119e83feaa1b146cbedb
+oid sha256:41341b31785ed0a2fbc8630488a4926f852161ef06ea08cc89540c9c37dc6630
 size 2372346

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6600748b28844d6445286c2db32da87f8f4ae7df8cb2643db5bb76ae67233234
+oid sha256:7137ffdadd3d98f6eb4df58e0d93207f78d2d3a226609b6aa51f825be2c62570
 size 990409330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4073b96953e05453b4b6e4a3030f1c740fa0e02670dbb4843214e79d4e7e84c5
+oid sha256:81575766e0f892673e3292549b8eae61ee2367f845a1b2b10898b9e83a3ef05f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b44cd738bffad7be53bf491009475d442fa0e6452600c820ee5979a9a8ce3a05
+oid sha256:0fc3d9b89093dc44b3f8ae65848b5c79017341da78ff50d3adcc276738c797e7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.5654487609863281,
   "best_model_checkpoint": "dq158/pingusPongus/checkpoint-6323",
-  "epoch": 11.0,
+  "epoch": 12.0,
   "eval_steps": 500,
-  "global_step": 69553,
+  "global_step": 75876,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1050,13 +1050,104 @@
       "eval_steps_per_second": 1.037,
       "eval_translation_length": 52469,
       "step": 69553
+    },
+    {
+      "epoch": 11.07,
+      "learning_rate": 2.0952479625603017e-06,
+      "loss": 1.7783,
+      "step": 70000
+    },
+    {
+      "epoch": 11.15,
+      "learning_rate": 2.0645150514646657e-06,
+      "loss": 1.7443,
+      "step": 70500
+    },
+    {
+      "epoch": 11.23,
+      "learning_rate": 2.0338498642707977e-06,
+      "loss": 1.7678,
+      "step": 71000
+    },
+    {
+      "epoch": 11.31,
+      "learning_rate": 2.0032571698372577e-06,
+      "loss": 1.7786,
+      "step": 71500
+    },
+    {
+      "epoch": 11.39,
+      "learning_rate": 1.9727417257489874e-06,
+      "loss": 1.7768,
+      "step": 72000
+    },
+    {
+      "epoch": 11.47,
+      "learning_rate": 1.9423082775774337e-06,
+      "loss": 1.7953,
+      "step": 72500
+    },
+    {
+      "epoch": 11.55,
+      "learning_rate": 1.9119615581425524e-06,
+      "loss": 1.7715,
+      "step": 73000
+    },
+    {
+      "epoch": 11.62,
+      "learning_rate": 1.881706286776785e-06,
+      "loss": 1.8047,
+      "step": 73500
+    },
+    {
+      "epoch": 11.7,
+      "learning_rate": 1.8515471685911402e-06,
+      "loss": 1.7781,
+      "step": 74000
+    },
+    {
+      "epoch": 11.78,
+      "learning_rate": 1.821488893743488e-06,
+      "loss": 1.8197,
+      "step": 74500
+    },
+    {
+      "epoch": 11.86,
+      "learning_rate": 1.7915361367091677e-06,
+      "loss": 1.8159,
+      "step": 75000
+    },
+    {
+      "epoch": 11.94,
+      "learning_rate": 1.7616935555540475e-06,
+      "loss": 1.8004,
+      "step": 75500
+    },
+    {
+      "epoch": 12.0,
+      "eval_bleu": 1.0,
+      "eval_brevity_penalty": 1.0,
+      "eval_length_ratio": 1.0,
+      "eval_loss": 1.5739296674728394,
+      "eval_precisions": [
+        1.0,
+        1.0,
+        1.0,
+        1.0
+      ],
+      "eval_reference_length": 52457,
+      "eval_runtime": 676.9983,
+      "eval_samples_per_second": 4.152,
+      "eval_steps_per_second": 1.038,
+      "eval_translation_length": 52457,
+      "step": 75876
     }
   ],
   "logging_steps": 500,
   "max_steps": 126460,
   "num_train_epochs": 20,
   "save_steps": 500,
-  "total_flos": 1.9050018020838605e+17,
+  "total_flos": 2.078183784091484e+17,
   "trial_name": null,
   "trial_params": null
 }