Training in progress, step 500000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abdc666b2f3669fde2f13b1cbce8537a9750ab5e917c8e2f654b514fc145c70c
+oid sha256:4a329db70ea5526ba5e4b910d073864205b498f32a4378b384003610aada51d6
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99bd6ef8a1b85dd6a22f6aedd2dc916de7e85d96497ce03a01c5ad35aba260ef
+oid sha256:c3a4d73b67517b389449be9b81a6d62f88071ffeb1fb6ad679e4c42b56b14bda
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5a73351b78231930c5e38a85e2db75ffb99765eca05e9e6dd123f382ddd4cb3
-size 14503
+oid sha256:d512ffa1b18c6ccc8dac4806c6008b76bb8f78c31b60a4336ad6a2a9fa9bb7a3
+size 14439

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7260623fa55e4f39900f0d796a360342ed8e000aa7fbed24d40632bf5f5532f3
-size 14439
+oid sha256:f66cebabe552d21647073ceeabf71a9c5fddbc9e0c70066a6914d3a038a79677
+size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccfe48daf5b331e0d6c664328074c7da11a0476f84c219e54335158a88175b91
+oid sha256:572120ff5e1d57786cb947f3c52e750254c5a4ff2a5c06ef2608f45e6a4e60de
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cff816a3de440d565f73bab1c06a61b794b87400c0cb82ffdc2d9ef43530b338
-size 14503
+oid sha256:ed3efb56468deb71f34f2a6667b3f91c0deb4e0556b62db345c7c959c339450d
+size 14439

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74800ce917e328df8d2e651e5da6a2b131e41e32b116f92b00e5f62a5503f854
+oid sha256:61639df917cea6bc1eea9e7a1f48d3f6c9acb9557d8752aa9847613f1b857ad8
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.482401087238689,
-  "global_step": 490000,
+  "epoch": 7.63510315024356,
+  "global_step": 500000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3632,11 +3632,85 @@
       "eval_samples_per_second": 930.213,
       "eval_steps_per_second": 14.883,
       "step": 490000
+    },
+    {
+      "epoch": 7.5,
+      "learning_rate": 8.78539438398963e-05,
+      "loss": 0.2655,
+      "step": 491000
+    },
+    {
+      "epoch": 7.51,
+      "learning_rate": 8.762387720245008e-05,
+      "loss": 0.2656,
+      "step": 492000
+    },
+    {
+      "epoch": 7.53,
+      "learning_rate": 8.73937271915042e-05,
+      "loss": 0.2655,
+      "step": 493000
+    },
+    {
+      "epoch": 7.54,
+      "learning_rate": 8.716349632394235e-05,
+      "loss": 0.2652,
+      "step": 494000
+    },
+    {
+      "epoch": 7.56,
+      "learning_rate": 8.69331871175324e-05,
+      "loss": 0.2651,
+      "step": 495000
+    },
+    {
+      "epoch": 7.56,
+      "eval_runtime": 1.1978,
+      "eval_samples_per_second": 834.871,
+      "eval_steps_per_second": 13.358,
+      "step": 495000
+    },
+    {
+      "epoch": 7.57,
+      "learning_rate": 8.67028020908989e-05,
+      "loss": 0.2647,
+      "step": 496000
+    },
+    {
+      "epoch": 7.59,
+      "learning_rate": 8.647234376349565e-05,
+      "loss": 0.2653,
+      "step": 497000
+    },
+    {
+      "epoch": 7.6,
+      "learning_rate": 8.624181465557794e-05,
+      "loss": 0.2649,
+      "step": 498000
+    },
+    {
+      "epoch": 7.62,
+      "learning_rate": 8.601121728817519e-05,
+      "loss": 0.2647,
+      "step": 499000
+    },
+    {
+      "epoch": 7.64,
+      "learning_rate": 8.578055418306327e-05,
+      "loss": 0.2654,
+      "step": 500000
+    },
+    {
+      "epoch": 7.64,
+      "eval_runtime": 1.1022,
+      "eval_samples_per_second": 907.298,
+      "eval_steps_per_second": 14.517,
+      "step": 500000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 3.434908191009969e+22,
+  "total_flos": 3.505008452040316e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99bd6ef8a1b85dd6a22f6aedd2dc916de7e85d96497ce03a01c5ad35aba260ef
+oid sha256:c3a4d73b67517b389449be9b81a6d62f88071ffeb1fb6ad679e4c42b56b14bda
 size 449471589