Training in progress, step 730000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a026519ac0ff0c3f1289d77d525568015b7857390a799b13b0638f4259cfacf4
+oid sha256:c26fc7d85d9f02e6a64dd6a80217974cd29a1b0b54ea54e9b185baad200d5cbf
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1129389ce9bcf343c0f3cd3aed67df3cad67444a99046ba4741058e82d747211
+oid sha256:e4d2617dcaf424c89a4b688e6f4da6209c2c4f8b6273e0866be4b1e433d0bac8
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aae7d49de4956e7c91d479fafd3b4d2ed56ba19e47ab8cacf05f2f824d1b2a28
+oid sha256:b88df4274470d41979d3cdbe4a25129230446986c8181439f49998ce0a51f2de
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cebea51ed6ff0008f8a6cacb32ade3887e6067fbd934b29f2ec5132ff8c8883a
+oid sha256:be607f7560436df027ef62ca453f5afb8d7770ec356ed4a4ec23eedf6a0db7f4
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b973a3a6eadc1982d4cc67d2b41bd0f42e96e285ea7f0a54482ed3274795569d
+oid sha256:29def8111a742b9412e55fb093f94afe63bb7e770d7ed5d28292a3cdbf42c223
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41cae4c446a75e16a0da874d105e34b48768289141d592a014669a4b78d9fe62
+oid sha256:bb6393653f317c7043e9a8b3debb3d85fe1b374103dd2a08137b8029e1480248
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed967cda4343e3de3b9b5189aaee239028fc09bd89309a5564f84c1374d13bfc
+oid sha256:95cdcd8f948ae7991b3b8cef0a5275b9e2e19dc1c57b631487377d234a0e9f31
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.994548536350726,
-  "global_step": 720000,
+  "epoch": 11.147250599355598,
+  "global_step": 730000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5334,11 +5334,85 @@
       "eval_samples_per_second": 1289.466,
       "eval_steps_per_second": 20.631,
       "step": 720000
+    },
+    {
+      "epoch": 11.01,
+      "learning_rate": 3.7739549441414945e-05,
+      "loss": 0.2427,
+      "step": 721000
+    },
+    {
+      "epoch": 11.03,
+      "learning_rate": 3.755524134615825e-05,
+      "loss": 0.2429,
+      "step": 722000
+    },
+    {
+      "epoch": 11.04,
+      "learning_rate": 3.7371397419981925e-05,
+      "loss": 0.2428,
+      "step": 723000
+    },
+    {
+      "epoch": 11.06,
+      "learning_rate": 3.7188019673373706e-05,
+      "loss": 0.2431,
+      "step": 724000
+    },
+    {
+      "epoch": 11.07,
+      "learning_rate": 3.700511011172325e-05,
+      "loss": 0.2436,
+      "step": 725000
+    },
+    {
+      "epoch": 11.07,
+      "eval_runtime": 0.7297,
+      "eval_samples_per_second": 1370.472,
+      "eval_steps_per_second": 21.928,
+      "step": 725000
+    },
+    {
+      "epoch": 11.09,
+      "learning_rate": 3.682267073530023e-05,
+      "loss": 0.243,
+      "step": 726000
+    },
+    {
+      "epoch": 11.1,
+      "learning_rate": 3.664070353923245e-05,
+      "loss": 0.2424,
+      "step": 727000
+    },
+    {
+      "epoch": 11.12,
+      "learning_rate": 3.645921051348396e-05,
+      "loss": 0.2423,
+      "step": 728000
+    },
+    {
+      "epoch": 11.13,
+      "learning_rate": 3.627819364283345e-05,
+      "loss": 0.2456,
+      "step": 729000
+    },
+    {
+      "epoch": 11.15,
+      "learning_rate": 3.6097654906852405e-05,
+      "loss": 0.2431,
+      "step": 730000
+    },
+    {
+      "epoch": 11.15,
+      "eval_runtime": 0.7906,
+      "eval_samples_per_second": 1264.795,
+      "eval_steps_per_second": 20.237,
+      "step": 730000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 5.047212223503507e+22,
+  "total_flos": 5.117311827465705e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1129389ce9bcf343c0f3cd3aed67df3cad67444a99046ba4741058e82d747211
+oid sha256:e4d2617dcaf424c89a4b688e6f4da6209c2c4f8b6273e0866be4b1e433d0bac8
 size 449471589