Training in progress, step 430000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2f3d6b44eb31a5904720c6ef9f3e390e0825c4e9bc44d807b8966079fa39c18
+oid sha256:0c4a14a4b300dc1a5da67108d934f51ece4d032d74a5b22ddb6baf522fdb8c1c
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43bdf8dfd2503753ae90f61b7bb9fe12717af35ea212a47dbf67cd5903f5bff5
+oid sha256:29a338d7e31f1ebb55d71826f0de824d2a1d8633cac67c074239e146a6c6bf2d
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc2e9e51fe4eee7b642ed745674287b01af0553fd6bc1b8f03d1bfb83d45dd88
-size 14503
+oid sha256:10c521743622eed6f2a8ce22651670cd6f7fb24994288ac8323ec1f5d533e8a1
+size 14439

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7303688061045aa652b3652b66ace516eee8a80cc0cf60b455e243337822a42
+oid sha256:6dc65d4d1b61d6b6ec0b07de631a3fc7ef2baef1eecd8b2dd63afdc6d03ed25d
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f87a487e7aba37c8dacc6a7f2504b596187c112ee85cf9f5586b459f5ed62ff7
+oid sha256:2003a4ffe1876cade3b569b7c4b3d4c928a46e1a7a6a797e8245fc18980679e5
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8eef20e1504bbd40c9a4046a6d63e017b73406d2bc77b0cb51859e2e7910822
-size 14503
+oid sha256:8d19681008a4b6b5d37d79f13ad91bb5cfd25c6887d3949264aeea07e7705212
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ecb3d640c7c2649b2bba280f1d77ce8c7f1955289fab0ee4959a38aa2646819
+oid sha256:1c41e7c1f83dca8045fba481a590c3c5a6ca39c080efa3c795ba2e0db9ab191b
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.41348664620459,
-  "global_step": 420000,
+  "epoch": 6.566188709209461,
+  "global_step": 430000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3114,11 +3114,85 @@
       "eval_samples_per_second": 947.861,
       "eval_steps_per_second": 15.166,
       "step": 420000
+    },
+    {
+      "epoch": 6.43,
+      "learning_rate": 0.00010360272179666802,
+      "loss": 0.2742,
+      "step": 421000
+    },
+    {
+      "epoch": 6.44,
+      "learning_rate": 0.00010338466326683697,
+      "loss": 0.2733,
+      "step": 422000
+    },
+    {
+      "epoch": 6.46,
+      "learning_rate": 0.00010316634900607497,
+      "loss": 0.2737,
+      "step": 423000
+    },
+    {
+      "epoch": 6.47,
+      "learning_rate": 0.00010294778140183182,
+      "loss": 0.2732,
+      "step": 424000
+    },
+    {
+      "epoch": 6.49,
+      "learning_rate": 0.00010272896284432785,
+      "loss": 0.2733,
+      "step": 425000
+    },
+    {
+      "epoch": 6.49,
+      "eval_runtime": 1.0035,
+      "eval_samples_per_second": 996.544,
+      "eval_steps_per_second": 15.945,
+      "step": 425000
+    },
+    {
+      "epoch": 6.51,
+      "learning_rate": 0.00010250989572652766,
+      "loss": 0.2728,
+      "step": 426000
+    },
+    {
+      "epoch": 6.52,
+      "learning_rate": 0.00010229058244411427,
+      "loss": 0.2729,
+      "step": 427000
+    },
+    {
+      "epoch": 6.54,
+      "learning_rate": 0.00010207102539546251,
+      "loss": 0.2728,
+      "step": 428000
+    },
+    {
+      "epoch": 6.55,
+      "learning_rate": 0.00010185122698161311,
+      "loss": 0.2726,
+      "step": 429000
+    },
+    {
+      "epoch": 6.57,
+      "learning_rate": 0.00010163118960624632,
+      "loss": 0.2725,
+      "step": 430000
+    },
+    {
+      "epoch": 6.57,
+      "eval_runtime": 1.0983,
+      "eval_samples_per_second": 910.508,
+      "eval_steps_per_second": 14.568,
+      "step": 430000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 2.9442070208656875e+22,
+  "total_flos": 3.0143072818960347e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43bdf8dfd2503753ae90f61b7bb9fe12717af35ea212a47dbf67cd5903f5bff5
+oid sha256:29a338d7e31f1ebb55d71826f0de824d2a1d8633cac67c074239e146a6c6bf2d
 size 449471589