Training in progress, step 490000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:125a953eae139b71c861d769dd5fcb3f2876cb3ba5332474ace67ff7903ad282
+oid sha256:abdc666b2f3669fde2f13b1cbce8537a9750ab5e917c8e2f654b514fc145c70c
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cb09afc7f60da26cfbf13286b33ee5d8eaf949d0691655a730175e631e257c3
+oid sha256:99bd6ef8a1b85dd6a22f6aedd2dc916de7e85d96497ce03a01c5ad35aba260ef
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8310a18059ec0119b7d5189ac12986b598d8b8b1ef1bbfc8c8957369e8337ad7
+oid sha256:f5a73351b78231930c5e38a85e2db75ffb99765eca05e9e6dd123f382ddd4cb3
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4a54b152e9b8fc53442ea8e45557e4a5adac5097977f729107da5bb580c1c20
-size 14503
+oid sha256:7260623fa55e4f39900f0d796a360342ed8e000aa7fbed24d40632bf5f5532f3
+size 14439

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c3be6e2beda8fd5ff4d10e6a6d31003cc62098e71db295fd431821efbbfb1a9
+oid sha256:ccfe48daf5b331e0d6c664328074c7da11a0476f84c219e54335158a88175b91
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1acdc1aa6e4187c8d0aa9e0711043619de98803eb54f6ce34ce5eccae47291d
-size 14567
+oid sha256:cff816a3de440d565f73bab1c06a61b794b87400c0cb82ffdc2d9ef43530b338
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d89c33267da2eca03288d19643b70286b13de68f683e137d6b6c77f428e64db6
+oid sha256:74800ce917e328df8d2e651e5da6a2b131e41e32b116f92b00e5f62a5503f854
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.329699024233817,
-  "global_step": 480000,
+  "epoch": 7.482401087238689,
+  "global_step": 490000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3558,11 +3558,85 @@
       "eval_samples_per_second": 966.468,
       "eval_steps_per_second": 15.463,
       "step": 480000
+    },
+    {
+      "epoch": 7.34,
+      "learning_rate": 9.014947164477721e-05,
+      "loss": 0.2663,
+      "step": 481000
+    },
+    {
+      "epoch": 7.36,
+      "learning_rate": 8.992037695672967e-05,
+      "loss": 0.267,
+      "step": 482000
+    },
+    {
+      "epoch": 7.38,
+      "learning_rate": 8.969117378102912e-05,
+      "loss": 0.2665,
+      "step": 483000
+    },
+    {
+      "epoch": 7.39,
+      "learning_rate": 8.946186462420478e-05,
+      "loss": 0.2662,
+      "step": 484000
+    },
+    {
+      "epoch": 7.41,
+      "learning_rate": 8.923245199394482e-05,
+      "loss": 0.2662,
+      "step": 485000
+    },
+    {
+      "epoch": 7.41,
+      "eval_runtime": 1.0079,
+      "eval_samples_per_second": 992.191,
+      "eval_steps_per_second": 15.875,
+      "step": 485000
+    },
+    {
+      "epoch": 7.42,
+      "learning_rate": 8.900293839906903e-05,
+      "loss": 0.2664,
+      "step": 486000
+    },
+    {
+      "epoch": 7.44,
+      "learning_rate": 8.87733263495013e-05,
+      "loss": 0.2658,
+      "step": 487000
+    },
+    {
+      "epoch": 7.45,
+      "learning_rate": 8.85436183562422e-05,
+      "loss": 0.2659,
+      "step": 488000
+    },
+    {
+      "epoch": 7.47,
+      "learning_rate": 8.83138169313416e-05,
+      "loss": 0.2663,
+      "step": 489000
+    },
+    {
+      "epoch": 7.48,
+      "learning_rate": 8.808392458787103e-05,
+      "loss": 0.2656,
+      "step": 490000
+    },
+    {
+      "epoch": 7.48,
+      "eval_runtime": 1.075,
+      "eval_samples_per_second": 930.213,
+      "eval_steps_per_second": 14.883,
+      "step": 490000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 3.3648079299796217e+22,
+  "total_flos": 3.434908191009969e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cb09afc7f60da26cfbf13286b33ee5d8eaf949d0691655a730175e631e257c3
+oid sha256:99bd6ef8a1b85dd6a22f6aedd2dc916de7e85d96497ce03a01c5ad35aba260ef
 size 449471589