Training in progress, step 390000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c700adab32c9c77d19e150bd97404af77c8ea4f249d7d8819f10ecd29a7599aa
+oid sha256:4e4182e3962d3a040ab734b61da56d604a525bd5f2d61cf2e3f5b36f5f0ee5bc
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b70ffcb599d0cbcc5aa0449b31396d7f0aecaf32d47481cf0cbeb78e7394dcdc
+oid sha256:bf099ec439cbdff64f3d3b55ea1f32c5386c40432f4a5418054927a7f60a7a71
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:074f082b7918427797301b29e7c6af54e31efb39ae44b35e4533a95f5b0a9f49
-size 14503
+oid sha256:c992fbbd7cb3ac4ba0d93a3c933e4f1384224ccab41105813a52127e0943be99
+size 14439

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65f237a078b5c1beb61259bf8b7bce0aab72bc1a5221890351cf7a2047a3cdcc
-size 14439
+oid sha256:a56d30c04eda66f1451428a4a1783f0e0b3c6401e9dc47a22a9a23c6f9d71d1c
+size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3427e04a13ecc5863d163d8b4c944bb2837f27676722003cb6abda2606ce2015
+oid sha256:252bfaee072432d2b9efeeb2414b13c69cfea81ef8749ee867aa8e12e0fa2d52
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dab2092ac253f5c93a298eee50fba2933b65f4ea17b7fc517f028648f502ea43
+oid sha256:b9e684c71dc83c29adb7891edadb6f809a0f52fc37575c6edaa71e9c79dd0a26
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f21b3afd8d405fcd9461eae3cafa8a4894a77b6f36c354aa188329ab6dfe547a
+oid sha256:1d1c67928001883576d4a56b44f4eee5262f60a7be50b274805186459e2f4ae5
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.802678394185105,
-  "global_step": 380000,
+  "epoch": 5.955380457189976,
+  "global_step": 390000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2818,11 +2818,85 @@
       "eval_samples_per_second": 808.112,
       "eval_steps_per_second": 12.93,
       "step": 380000
+    },
+    {
+      "epoch": 5.82,
+      "learning_rate": 0.00011208832574099368,
+      "loss": 0.2788,
+      "step": 381000
+    },
+    {
+      "epoch": 5.83,
+      "learning_rate": 0.00011188241916068993,
+      "loss": 0.2785,
+      "step": 382000
+    },
+    {
+      "epoch": 5.85,
+      "learning_rate": 0.00011167616391935826,
+      "loss": 0.2783,
+      "step": 383000
+    },
+    {
+      "epoch": 5.86,
+      "learning_rate": 0.00011146956227257293,
+      "loss": 0.2785,
+      "step": 384000
+    },
+    {
+      "epoch": 5.88,
+      "learning_rate": 0.00011126261647969645,
+      "loss": 0.2781,
+      "step": 385000
+    },
+    {
+      "epoch": 5.88,
+      "eval_runtime": 1.0191,
+      "eval_samples_per_second": 981.273,
+      "eval_steps_per_second": 15.7,
+      "step": 385000
+    },
+    {
+      "epoch": 5.89,
+      "learning_rate": 0.00011105532880385487,
+      "loss": 0.2782,
+      "step": 386000
+    },
+    {
+      "epoch": 5.91,
+      "learning_rate": 0.00011084770151191299,
+      "loss": 0.2782,
+      "step": 387000
+    },
+    {
+      "epoch": 5.92,
+      "learning_rate": 0.00011063973687444962,
+      "loss": 0.2779,
+      "step": 388000
+    },
+    {
+      "epoch": 5.94,
+      "learning_rate": 0.00011043143716573272,
+      "loss": 0.2774,
+      "step": 389000
+    },
+    {
+      "epoch": 5.96,
+      "learning_rate": 0.00011022280466369448,
+      "loss": 0.2776,
+      "step": 390000
+    },
+    {
+      "epoch": 5.96,
+      "eval_runtime": 1.0236,
+      "eval_samples_per_second": 976.954,
+      "eval_steps_per_second": 15.631,
+      "step": 390000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 2.6638066338124477e+22,
+  "total_flos": 2.733906894842795e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b70ffcb599d0cbcc5aa0449b31396d7f0aecaf32d47481cf0cbeb78e7394dcdc
+oid sha256:bf099ec439cbdff64f3d3b55ea1f32c5386c40432f4a5418054927a7f60a7a71
 size 449471589