Training in progress, step 470000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e074c33dcba955530635f7c301cc0616d35e94c4d9e25f501a0d9edd512370f3
+oid sha256:48d4808dde71eac80e04b5355e71b14ceb9b5e0ae529d95a233b51272607ab83
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e2e3c76b0bd22486ffeb7f1582064821337785eddce5493639f753ea7af7c21
+oid sha256:7103687c38405c622f568188c0f14e1563ef023c455f4c1710827b01ab80bb17
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f07bf259da4db58c67f5752e41be50bd05dbfaf1912a8b5878788f3ede910eb7
+oid sha256:a4e056df33e676753147b05c71aab5efb8704dfd8ee13e008fdf53d8cdac44b2
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e069aee1aca48a60052a1c66c7d1551fec7d9dcab99912ac030e1863b14f6a1
+oid sha256:7049055dea9713813a526e48cc1a4819519bd8bf226d421b09446678fec8fd94
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:642ba2efc3dad359eda3b33bb6c5d67fffdc0e921c5ed6b47ef80068231cbd4a
-size 14439
+oid sha256:ae399cb1dd5e413a3579163a8c5c2dc1f7fefe685aeb37d572263aef6a0f1ce1
+size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5475a56a8e58f3a6d30456ecb3d60c907f9c5dd05e43f39a9dbfefa6d303c24c
-size 14503
+oid sha256:0032134f185d3f5485217ef8125c850bc4af9658f5890ff772fcbabf723e2b09
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d470fe106a7d346e8d83a1e5754bc519572ca0d497bb4adce56ffd8f58de945f
+oid sha256:0f611622a5002fa681af11a66fadbdf979555ccde290d546f60b9105024e7e63
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.024294898224075,
-  "global_step": 460000,
+  "epoch": 7.176996961228946,
+  "global_step": 470000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3410,11 +3410,85 @@
       "eval_samples_per_second": 978.034,
       "eval_steps_per_second": 15.649,
       "step": 460000
+    },
+    {
+      "epoch": 7.04,
+      "learning_rate": 9.47047343697216e-05,
+      "loss": 0.269,
+      "step": 461000
+    },
+    {
+      "epoch": 7.05,
+      "learning_rate": 9.447833377876176e-05,
+      "loss": 0.269,
+      "step": 462000
+    },
+    {
+      "epoch": 7.07,
+      "learning_rate": 9.425177485506336e-05,
+      "loss": 0.2688,
+      "step": 463000
+    },
+    {
+      "epoch": 7.09,
+      "learning_rate": 9.402506007623848e-05,
+      "loss": 0.269,
+      "step": 464000
+    },
+    {
+      "epoch": 7.1,
+      "learning_rate": 9.379819192160362e-05,
+      "loss": 0.2692,
+      "step": 465000
+    },
+    {
+      "epoch": 7.1,
+      "eval_runtime": 1.1401,
+      "eval_samples_per_second": 877.142,
+      "eval_steps_per_second": 14.034,
+      "step": 465000
+    },
+    {
+      "epoch": 7.12,
+      "learning_rate": 9.357117287215258e-05,
+      "loss": 0.2682,
+      "step": 466000
+    },
+    {
+      "epoch": 7.13,
+      "learning_rate": 9.334400541052928e-05,
+      "loss": 0.2683,
+      "step": 467000
+    },
+    {
+      "epoch": 7.15,
+      "learning_rate": 9.311669202100073e-05,
+      "loss": 0.2693,
+      "step": 468000
+    },
+    {
+      "epoch": 7.16,
+      "learning_rate": 9.288923518942968e-05,
+      "loss": 0.2683,
+      "step": 469000
+    },
+    {
+      "epoch": 7.18,
+      "learning_rate": 9.26616374032477e-05,
+      "loss": 0.2677,
+      "step": 470000
+    },
+    {
+      "epoch": 7.18,
+      "eval_runtime": 0.8954,
+      "eval_samples_per_second": 1116.774,
+      "eval_steps_per_second": 17.868,
+      "step": 470000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 3.2246074079189274e+22,
+  "total_flos": 3.2947076689492745e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e2e3c76b0bd22486ffeb7f1582064821337785eddce5493639f753ea7af7c21
+oid sha256:7103687c38405c622f568188c0f14e1563ef023c455f4c1710827b01ab80bb17
 size 449471589