Training in progress, epoch 2, checkpoint

last-checkpoint/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e8387a6b711dbe733802091f3fb62ee7fa86c449abfedb4e65346acd48fe344
+oid sha256:bb462ee5d4ed0064da716ca2c5594e3e3e5e70319a6ab418abac9cfb7d0edee2
 size 18980874

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21afb3fbcfdf6ae8a3dbdda6079c6633801aedf8ea6d86885a05cb51c34e62b2
+oid sha256:a19be04da38748a1cb039e6c0dfe07bb27492e90ebdf0e33f955d798f4daa98f
 size 37990394

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97677b34e8dfeaf1cb59c897df795cae8a6cd1ffd721cb6a72c9218e318994ed
+oid sha256:911b0a95cae6d6f41378e1da173908f3c8007c9ee9c948ae7dbbb7364f4aa68a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d144a1c2bd6794181df2dc95832a4077b6570b2942de19e66d9c2cae2fcf7f99
+oid sha256:c109f720765794b94b48266e277c7993d9e80f89e80300af67dc66dd1122b7af
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.273033857345581,
-  "best_model_checkpoint": "dq158/pingusPongus/checkpoint-6323",
-  "epoch": 2.0,
+  "best_metric": 2.2457683086395264,
+  "best_model_checkpoint": "dq158/pingusPongus/checkpoint-9484",
+  "epoch": 2.9998418472244186,
   "eval_steps": 500,
-  "global_step": 6323,
+  "global_step": 9484,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -117,13 +117,68 @@
       "eval_steps_per_second": 0.629,
       "eval_translation_length": 53403,
       "step": 6323
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 0.00019775599595764338,
+      "loss": 2.3691,
+      "step": 6500
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 0.0001973932645621972,
+      "loss": 2.3412,
+      "step": 7000
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 0.00019700375482672989,
+      "loss": 2.3373,
+      "step": 7500
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 0.00019658757384719084,
+      "loss": 2.3416,
+      "step": 8000
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 0.0001961448360528051,
+      "loss": 2.3669,
+      "step": 8500
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 0.0001956756631746107,
+      "loss": 2.347,
+      "step": 9000
+    },
+    {
+      "epoch": 3.0,
+      "eval_bleu": 1.0,
+      "eval_brevity_penalty": 1.0,
+      "eval_length_ratio": 1.0,
+      "eval_loss": 2.2457683086395264,
+      "eval_precisions": [
+        1.0,
+        1.0,
+        1.0,
+        1.0
+      ],
+      "eval_reference_length": 53407,
+      "eval_runtime": 1141.3701,
+      "eval_samples_per_second": 2.463,
+      "eval_steps_per_second": 0.616,
+      "eval_translation_length": 53407,
+      "step": 9484
     }
   ],
   "logging_steps": 500,
   "max_steps": 94830,
   "num_train_epochs": 30,
   "save_steps": 500,
-  "total_flos": 4.3332645393373594e+17,
+  "total_flos": 6.499896809006039e+17,
   "trial_name": null,
   "trial_params": null
 }