Training in progress, step 240000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:133edef03c1d84d7f47c379bb8627e715102779ac7fbfbbc81cf76fdb3857138
+oid sha256:95219d59f6e21a9a0cd580ed60c0915e8162896fe27e6f7170a921f2e0d281bd
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef3e57cb5c11d79b27478df38200399f2d7e69d1e9da7282bcbb17ee802e3b1d
+oid sha256:58d9a817ebedb7184a71cca1a13709576b2d1a51f03c46a318ad05be242513b5
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a04cad25c1edacc0a2853d5253114151a48b6b991129f2e052e17228b772e940
+oid sha256:8419ed7583455ff96bd8dc55fc07544cbd4508b78a00a26bb6c6297cac401ebd
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a04cad25c1edacc0a2853d5253114151a48b6b991129f2e052e17228b772e940
+oid sha256:8419ed7583455ff96bd8dc55fc07544cbd4508b78a00a26bb6c6297cac401ebd
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a04cad25c1edacc0a2853d5253114151a48b6b991129f2e052e17228b772e940
+oid sha256:8419ed7583455ff96bd8dc55fc07544cbd4508b78a00a26bb6c6297cac401ebd
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a04cad25c1edacc0a2853d5253114151a48b6b991129f2e052e17228b772e940
+oid sha256:8419ed7583455ff96bd8dc55fc07544cbd4508b78a00a26bb6c6297cac401ebd
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a04cad25c1edacc0a2853d5253114151a48b6b991129f2e052e17228b772e940
+oid sha256:8419ed7583455ff96bd8dc55fc07544cbd4508b78a00a26bb6c6297cac401ebd
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a04cad25c1edacc0a2853d5253114151a48b6b991129f2e052e17228b772e940
+oid sha256:8419ed7583455ff96bd8dc55fc07544cbd4508b78a00a26bb6c6297cac401ebd
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a04cad25c1edacc0a2853d5253114151a48b6b991129f2e052e17228b772e940
+oid sha256:8419ed7583455ff96bd8dc55fc07544cbd4508b78a00a26bb6c6297cac401ebd
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a04cad25c1edacc0a2853d5253114151a48b6b991129f2e052e17228b772e940
+oid sha256:8419ed7583455ff96bd8dc55fc07544cbd4508b78a00a26bb6c6297cac401ebd
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a2bb37359d05bc7917d91ab1261ba8c4d8f00648cd8cb2d11c677b6c91ddb27
+oid sha256:a310455c0ab00dbcb4f4c26c03e0304d748fbc8c3e547006fb15346d32ac70da
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.358931941564342,
-  "global_step": 230000,
+  "epoch": 5.591928982501923,
+  "global_step": 240000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4606,11 +4606,211 @@
       "eval_samples_per_second": 1525.752,
       "eval_steps_per_second": 24.295,
       "step": 230000
+    },
+    {
+      "epoch": 5.37,
+      "learning_rate": 0.00018545980690870903,
+      "loss": 0.276,
+      "step": 230500
+    },
+    {
+      "epoch": 5.38,
+      "learning_rate": 0.00018499083425600648,
+      "loss": 0.2753,
+      "step": 231000
+    },
+    {
+      "epoch": 5.38,
+      "eval_loss": 0.2578088045120239,
+      "eval_runtime": 1.4301,
+      "eval_samples_per_second": 1536.977,
+      "eval_steps_per_second": 24.474,
+      "step": 231000
+    },
+    {
+      "epoch": 5.39,
+      "learning_rate": 0.00018452153362834552,
+      "loss": 0.275,
+      "step": 231500
+    },
+    {
+      "epoch": 5.41,
+      "learning_rate": 0.00018405191015792254,
+      "loss": 0.2749,
+      "step": 232000
+    },
+    {
+      "epoch": 5.41,
+      "eval_loss": 0.25682488083839417,
+      "eval_runtime": 1.4507,
+      "eval_samples_per_second": 1515.179,
+      "eval_steps_per_second": 24.127,
+      "step": 232000
+    },
+    {
+      "epoch": 5.42,
+      "learning_rate": 0.0001835819689804646,
+      "loss": 0.2749,
+      "step": 232500
+    },
+    {
+      "epoch": 5.43,
+      "learning_rate": 0.0001831117152351732,
+      "loss": 0.2749,
+      "step": 233000
+    },
+    {
+      "epoch": 5.43,
+      "eval_loss": 0.25751060247421265,
+      "eval_runtime": 1.429,
+      "eval_samples_per_second": 1538.092,
+      "eval_steps_per_second": 24.492,
+      "step": 233000
+    },
+    {
+      "epoch": 5.44,
+      "learning_rate": 0.00018264115406466778,
+      "loss": 0.2752,
+      "step": 233500
+    },
+    {
+      "epoch": 5.45,
+      "learning_rate": 0.00018217029061493007,
+      "loss": 0.2748,
+      "step": 234000
+    },
+    {
+      "epoch": 5.45,
+      "eval_loss": 0.2570262551307678,
+      "eval_runtime": 1.4679,
+      "eval_samples_per_second": 1497.347,
+      "eval_steps_per_second": 23.843,
+      "step": 234000
+    },
+    {
+      "epoch": 5.46,
+      "learning_rate": 0.00018169913003524717,
+      "loss": 0.2748,
+      "step": 234500
+    },
+    {
+      "epoch": 5.48,
+      "learning_rate": 0.00018122767747815594,
+      "loss": 0.2744,
+      "step": 235000
+    },
+    {
+      "epoch": 5.48,
+      "eval_loss": 0.2594066262245178,
+      "eval_runtime": 1.449,
+      "eval_samples_per_second": 1516.917,
+      "eval_steps_per_second": 24.155,
+      "step": 235000
+    },
+    {
+      "epoch": 5.49,
+      "learning_rate": 0.00018075593809938574,
+      "loss": 0.2746,
+      "step": 235500
+    },
+    {
+      "epoch": 5.5,
+      "learning_rate": 0.00018028391705780295,
+      "loss": 0.2748,
+      "step": 236000
+    },
+    {
+      "epoch": 5.5,
+      "eval_loss": 0.25915682315826416,
+      "eval_runtime": 1.4494,
+      "eval_samples_per_second": 1516.483,
+      "eval_steps_per_second": 24.148,
+      "step": 236000
+    },
+    {
+      "epoch": 5.51,
+      "learning_rate": 0.0001798116195153541,
+      "loss": 0.2745,
+      "step": 236500
+    },
+    {
+      "epoch": 5.52,
+      "learning_rate": 0.0001793390506370094,
+      "loss": 0.2742,
+      "step": 237000
+    },
+    {
+      "epoch": 5.52,
+      "eval_loss": 0.25850772857666016,
+      "eval_runtime": 1.4467,
+      "eval_samples_per_second": 1519.275,
+      "eval_steps_per_second": 24.192,
+      "step": 237000
+    },
+    {
+      "epoch": 5.53,
+      "learning_rate": 0.00017886621559070638,
+      "loss": 0.2743,
+      "step": 237500
+    },
+    {
+      "epoch": 5.55,
+      "learning_rate": 0.00017839311954729337,
+      "loss": 0.2742,
+      "step": 238000
+    },
+    {
+      "epoch": 5.55,
+      "eval_loss": 0.25702983140945435,
+      "eval_runtime": 1.4245,
+      "eval_samples_per_second": 1542.944,
+      "eval_steps_per_second": 24.569,
+      "step": 238000
+    },
+    {
+      "epoch": 5.56,
+      "learning_rate": 0.00017791976768047292,
+      "loss": 0.2738,
+      "step": 238500
+    },
+    {
+      "epoch": 5.57,
+      "learning_rate": 0.00017744616516674518,
+      "loss": 0.2743,
+      "step": 239000
+    },
+    {
+      "epoch": 5.57,
+      "eval_loss": 0.2567313611507416,
+      "eval_runtime": 1.5014,
+      "eval_samples_per_second": 1463.976,
+      "eval_steps_per_second": 23.312,
+      "step": 239000
+    },
+    {
+      "epoch": 5.58,
+      "learning_rate": 0.00017697231718535132,
+      "loss": 0.2742,
+      "step": 239500
+    },
+    {
+      "epoch": 5.59,
+      "learning_rate": 0.00017649822891821707,
+      "loss": 0.274,
+      "step": 240000
+    },
+    {
+      "epoch": 5.59,
+      "eval_loss": 0.25702497363090515,
+      "eval_runtime": 1.442,
+      "eval_samples_per_second": 1524.238,
+      "eval_steps_per_second": 24.271,
+      "step": 240000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 7.348191706858966e+21,
+  "total_flos": 7.667678845633466e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef3e57cb5c11d79b27478df38200399f2d7e69d1e9da7282bcbb17ee802e3b1d
+oid sha256:58d9a817ebedb7184a71cca1a13709576b2d1a51f03c46a318ad05be242513b5
 size 102501541