Training in progress, step 490000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e105dcd563eccd369d2a15a8d826ee474582d21896c7ba849cca414eb2db7cc
+oid sha256:04556cb11706d3015b54a3833cc4ab2399848632d8b3574e432d9d26ca86dd6c
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d933c34c102b4178ee716eb81d1f01382f48d07eee5e12f98d8b7a95d45f44db
+oid sha256:00240df886e866d9b8adc06a07729b4b469a354fe39ac54cefe302442e7a0f3d
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22c399106377503c4589b87d720815d689b51969b30f957ad0a603fe2cdb4ddd
+oid sha256:9d9db2260bbac96fa46455e77871b2996f9d6671e86576cded7ba308075e016b
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22c399106377503c4589b87d720815d689b51969b30f957ad0a603fe2cdb4ddd
+oid sha256:9d9db2260bbac96fa46455e77871b2996f9d6671e86576cded7ba308075e016b
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22c399106377503c4589b87d720815d689b51969b30f957ad0a603fe2cdb4ddd
+oid sha256:9d9db2260bbac96fa46455e77871b2996f9d6671e86576cded7ba308075e016b
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22c399106377503c4589b87d720815d689b51969b30f957ad0a603fe2cdb4ddd
+oid sha256:9d9db2260bbac96fa46455e77871b2996f9d6671e86576cded7ba308075e016b
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22c399106377503c4589b87d720815d689b51969b30f957ad0a603fe2cdb4ddd
+oid sha256:9d9db2260bbac96fa46455e77871b2996f9d6671e86576cded7ba308075e016b
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22c399106377503c4589b87d720815d689b51969b30f957ad0a603fe2cdb4ddd
+oid sha256:9d9db2260bbac96fa46455e77871b2996f9d6671e86576cded7ba308075e016b
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22c399106377503c4589b87d720815d689b51969b30f957ad0a603fe2cdb4ddd
+oid sha256:9d9db2260bbac96fa46455e77871b2996f9d6671e86576cded7ba308075e016b
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22c399106377503c4589b87d720815d689b51969b30f957ad0a603fe2cdb4ddd
+oid sha256:9d9db2260bbac96fa46455e77871b2996f9d6671e86576cded7ba308075e016b
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d89c33267da2eca03288d19643b70286b13de68f683e137d6b6c77f428e64db6
+oid sha256:74800ce917e328df8d2e651e5da6a2b131e41e32b116f92b00e5f62a5503f854
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.353378762700333,
-  "global_step": 480000,
+  "epoch": 5.4649074869232575,
+  "global_step": 490000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -9606,11 +9606,211 @@
       "eval_samples_per_second": 903.348,
       "eval_steps_per_second": 14.158,
       "step": 480000
+    },
+    {
+      "epoch": 5.36,
+      "learning_rate": 9.02639775229644e-05,
+      "loss": 0.2124,
+      "step": 480500
+    },
+    {
+      "epoch": 5.36,
+      "learning_rate": 9.014947164477721e-05,
+      "loss": 0.2126,
+      "step": 481000
+    },
+    {
+      "epoch": 5.36,
+      "eval_loss": 0.20033051073551178,
+      "eval_runtime": 2.4935,
+      "eval_samples_per_second": 921.209,
+      "eval_steps_per_second": 14.438,
+      "step": 481000
+    },
+    {
+      "epoch": 5.37,
+      "learning_rate": 9.003493801832213e-05,
+      "loss": 0.212,
+      "step": 481500
+    },
+    {
+      "epoch": 5.38,
+      "learning_rate": 8.992037695672967e-05,
+      "loss": 0.2127,
+      "step": 482000
+    },
+    {
+      "epoch": 5.38,
+      "eval_loss": 0.2025318741798401,
+      "eval_runtime": 2.5419,
+      "eval_samples_per_second": 903.65,
+      "eval_steps_per_second": 14.163,
+      "step": 482000
+    },
+    {
+      "epoch": 5.38,
+      "learning_rate": 8.980578877320544e-05,
+      "loss": 0.2128,
+      "step": 482500
+    },
+    {
+      "epoch": 5.39,
+      "learning_rate": 8.969117378102912e-05,
+      "loss": 0.2122,
+      "step": 483000
+    },
+    {
+      "epoch": 5.39,
+      "eval_loss": 0.2024153620004654,
+      "eval_runtime": 2.5406,
+      "eval_samples_per_second": 904.131,
+      "eval_steps_per_second": 14.17,
+      "step": 483000
+    },
+    {
+      "epoch": 5.39,
+      "learning_rate": 8.957653229355374e-05,
+      "loss": 0.212,
+      "step": 483500
+    },
+    {
+      "epoch": 5.4,
+      "learning_rate": 8.946186462420478e-05,
+      "loss": 0.2123,
+      "step": 484000
+    },
+    {
+      "epoch": 5.4,
+      "eval_loss": 0.20227807760238647,
+      "eval_runtime": 2.6148,
+      "eval_samples_per_second": 878.471,
+      "eval_steps_per_second": 13.768,
+      "step": 484000
+    },
+    {
+      "epoch": 5.4,
+      "learning_rate": 8.934717108647922e-05,
+      "loss": 0.2122,
+      "step": 484500
+    },
+    {
+      "epoch": 5.41,
+      "learning_rate": 8.923245199394482e-05,
+      "loss": 0.2123,
+      "step": 485000
+    },
+    {
+      "epoch": 5.41,
+      "eval_loss": 0.2004445344209671,
+      "eval_runtime": 2.6169,
+      "eval_samples_per_second": 877.747,
+      "eval_steps_per_second": 13.757,
+      "step": 485000
+    },
+    {
+      "epoch": 5.41,
+      "learning_rate": 8.911770766023921e-05,
+      "loss": 0.212,
+      "step": 485500
+    },
+    {
+      "epoch": 5.42,
+      "learning_rate": 8.900293839906903e-05,
+      "loss": 0.2113,
+      "step": 486000
+    },
+    {
+      "epoch": 5.42,
+      "eval_loss": 0.20107805728912354,
+      "eval_runtime": 2.6497,
+      "eval_samples_per_second": 866.906,
+      "eval_steps_per_second": 13.587,
+      "step": 486000
+    },
+    {
+      "epoch": 5.43,
+      "learning_rate": 8.888814452420903e-05,
+      "loss": 0.2238,
+      "step": 486500
+    },
+    {
+      "epoch": 5.43,
+      "learning_rate": 8.87733263495013e-05,
+      "loss": 0.2125,
+      "step": 487000
+    },
+    {
+      "epoch": 5.43,
+      "eval_loss": 0.20239748060703278,
+      "eval_runtime": 2.6391,
+      "eval_samples_per_second": 870.377,
+      "eval_steps_per_second": 13.641,
+      "step": 487000
+    },
+    {
+      "epoch": 5.44,
+      "learning_rate": 8.865848418885434e-05,
+      "loss": 0.2116,
+      "step": 487500
+    },
+    {
+      "epoch": 5.44,
+      "learning_rate": 8.85436183562422e-05,
+      "loss": 0.2117,
+      "step": 488000
+    },
+    {
+      "epoch": 5.44,
+      "eval_loss": 0.20209769904613495,
+      "eval_runtime": 2.6167,
+      "eval_samples_per_second": 877.814,
+      "eval_steps_per_second": 13.758,
+      "step": 488000
+    },
+    {
+      "epoch": 5.45,
+      "learning_rate": 8.842872916570374e-05,
+      "loss": 0.2117,
+      "step": 488500
+    },
+    {
+      "epoch": 5.45,
+      "learning_rate": 8.83138169313416e-05,
+      "loss": 0.2117,
+      "step": 489000
+    },
+    {
+      "epoch": 5.45,
+      "eval_loss": 0.20107334852218628,
+      "eval_runtime": 2.6263,
+      "eval_samples_per_second": 874.613,
+      "eval_steps_per_second": 13.707,
+      "step": 489000
+    },
+    {
+      "epoch": 5.46,
+      "learning_rate": 8.819888196732144e-05,
+      "loss": 0.2116,
+      "step": 489500
+    },
+    {
+      "epoch": 5.46,
+      "learning_rate": 8.808392458787103e-05,
+      "loss": 0.2116,
+      "step": 490000
+    },
+    {
+      "epoch": 5.46,
+      "eval_loss": 0.2020297795534134,
+      "eval_runtime": 2.6641,
+      "eval_samples_per_second": 862.22,
+      "eval_steps_per_second": 13.513,
+      "step": 490000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 12,
-  "total_flos": 3.364785147219085e+22,
+  "total_flos": 3.434885408249432e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d933c34c102b4178ee716eb81d1f01382f48d07eee5e12f98d8b7a95d45f44db
+oid sha256:00240df886e866d9b8adc06a07729b4b469a354fe39ac54cefe302442e7a0f3d
 size 449471589