Training in progress, step 380000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8e6e5d6289bafd465e0f93748ab1bb630e682cf3fe16da7f34107958c699159
+oid sha256:c700adab32c9c77d19e150bd97404af77c8ea4f249d7d8819f10ecd29a7599aa
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0f65f9d24c194387d73c6d6206aa2a527cc855b09f2bbd98f42e2d70ffdd0e6
+oid sha256:b70ffcb599d0cbcc5aa0449b31396d7f0aecaf32d47481cf0cbeb78e7394dcdc
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a14c2ca87be8d848b5b7a5987a7e41580ee4714e56c6a11b74724ade62186fac
+oid sha256:074f082b7918427797301b29e7c6af54e31efb39ae44b35e4533a95f5b0a9f49
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14c65884de0d108ce0c8462f58d63c86fe3c03bc71ad62ad4517385a4a06be4d
-size 14503
+oid sha256:65f237a078b5c1beb61259bf8b7bce0aab72bc1a5221890351cf7a2047a3cdcc
+size 14439

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d71883cda87e2e2a13d7e90ee7788adac16f770d7d78f7236989f184f7851175
+oid sha256:3427e04a13ecc5863d163d8b4c944bb2837f27676722003cb6abda2606ce2015
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebafa49c46a1fb807fcc2cd7ad8adabd30b87b658f944a88ac912fe32d5b60d0
-size 14567
+oid sha256:dab2092ac253f5c93a298eee50fba2933b65f4ea17b7fc517f028648f502ea43
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:540b632982ca1e514de58c2d575a52863f5386c323edbc210ecc94c61bdc1b4b
+oid sha256:f21b3afd8d405fcd9461eae3cafa8a4894a77b6f36c354aa188329ab6dfe547a
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.649976331180234,
-  "global_step": 370000,
+  "epoch": 5.802678394185105,
+  "global_step": 380000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2744,11 +2744,85 @@
       "eval_samples_per_second": 820.56,
       "eval_steps_per_second": 13.129,
       "step": 370000
+    },
+    {
+      "epoch": 5.67,
+      "learning_rate": 0.00011412772171899904,
+      "loss": 0.2819,
+      "step": 371000
+    },
+    {
+      "epoch": 5.68,
+      "learning_rate": 0.00011392542495456556,
+      "loss": 0.28,
+      "step": 372000
+    },
+    {
+      "epoch": 5.7,
+      "learning_rate": 0.00011372275718712006,
+      "loss": 0.2797,
+      "step": 373000
+    },
+    {
+      "epoch": 5.71,
+      "learning_rate": 0.00011351972063300484,
+      "loss": 0.2797,
+      "step": 374000
+    },
+    {
+      "epoch": 5.73,
+      "learning_rate": 0.00011331631751259515,
+      "loss": 0.2801,
+      "step": 375000
+    },
+    {
+      "epoch": 5.73,
+      "eval_runtime": 1.0146,
+      "eval_samples_per_second": 985.631,
+      "eval_steps_per_second": 15.77,
+      "step": 375000
+    },
+    {
+      "epoch": 5.74,
+      "learning_rate": 0.00011311255005027487,
+      "loss": 0.2789,
+      "step": 376000
+    },
+    {
+      "epoch": 5.76,
+      "learning_rate": 0.00011290842047441232,
+      "loss": 0.2791,
+      "step": 377000
+    },
+    {
+      "epoch": 5.77,
+      "learning_rate": 0.00011270393101733585,
+      "loss": 0.279,
+      "step": 378000
+    },
+    {
+      "epoch": 5.79,
+      "learning_rate": 0.00011249908391530946,
+      "loss": 0.279,
+      "step": 379000
+    },
+    {
+      "epoch": 5.8,
+      "learning_rate": 0.00011229388140850814,
+      "loss": 0.279,
+      "step": 380000
+    },
+    {
+      "epoch": 5.8,
+      "eval_runtime": 1.2375,
+      "eval_samples_per_second": 808.112,
+      "eval_steps_per_second": 12.93,
+      "step": 380000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 2.5937063727821006e+22,
+  "total_flos": 2.6638066338124477e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0f65f9d24c194387d73c6d6206aa2a527cc855b09f2bbd98f42e2d70ffdd0e6
+oid sha256:b70ffcb599d0cbcc5aa0449b31396d7f0aecaf32d47481cf0cbeb78e7394dcdc
 size 449471589