Training in progress, step 1550, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54bfdc5814a5788e32724cc7a8b78d4c264b7ed744956f1ae12967a460f966a3
+oid sha256:54d8a76550e312d12a91cc5832560b2acbf757d3afaa9f1ef006d9930d5dee73
 size 1612184459

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cc17ff3bed0a9716439364aade61f5bad0364b4c946b4ce25a52197f147dc4b
+oid sha256:6101567567161c38233b08fb2271b4b78706457d877f3ea5a7f54f5679d261ee
 size 806069967

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22099ffdac5bf2dbcb6d0dba5a9224accc8f51804f8161a7ec007a8969967b48
+oid sha256:d342066754ecfbd9b1ecb8226834c996c511c385e3a5f539eafa72576b871739
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11b676c2f0a59aa9351254878fd91590bffab13cd78e3f6d1bdc7ba9cf1f94b6
+oid sha256:2f5a2477159012c518c81b4a8d7d160fbfb4b7b3c1dca9998ecc892860de68c9
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 1300,
   "best_metric": 0.8713989853858948,
   "best_model_checkpoint": "./results_decoder_final/checkpoint-1000",
-  "epoch": 9.680713128038898,
+  "epoch": 10.0,
   "eval_steps": 100,
-  "global_step": 1500,
+  "global_step": 1550,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1186,6 +1186,41 @@
       "eval_samples_per_second": 189.096,
       "eval_steps_per_second": 1.513,
       "step": 1500
+    },
+    {
+      "epoch": 9.745542949756889,
+      "grad_norm": 0.2521146833896637,
+      "learning_rate": 2.6451612903225807e-06,
+      "loss": 0.6493,
+      "step": 1510
+    },
+    {
+      "epoch": 9.810372771474878,
+      "grad_norm": 0.3085962235927582,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.6482,
+      "step": 1520
+    },
+    {
+      "epoch": 9.875202593192869,
+      "grad_norm": 0.23055943846702576,
+      "learning_rate": 1.3548387096774193e-06,
+      "loss": 0.6502,
+      "step": 1530
+    },
+    {
+      "epoch": 9.94003241491086,
+      "grad_norm": 0.256622314453125,
+      "learning_rate": 7.096774193548388e-07,
+      "loss": 0.654,
+      "step": 1540
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.802431583404541,
+      "learning_rate": 6.451612903225807e-08,
+      "loss": 0.6508,
+      "step": 1550
     }
   ],
   "logging_steps": 10,
@@ -1200,12 +1235,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.7275609360328294e+17,
+  "total_flos": 4.8831577850904576e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null