Training in progress, step 180000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:957a0b613730bb1f7e18c8182652c293421c706a14fa7ef89a59100dcf03486e
+oid sha256:c252e94704b7a7c1ede22c27b6ef39fca3801557bccc58914230d05284a2fc8f
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a436af1cb440949a8156a3e0bac95099a250179167b60f6ba2300e45f023d5ef
+oid sha256:2cf77efb61849887c31eb27074736092c24c74904d823d7c3253ad56e6671aad
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d68f14caf8efc58720b158ce68c4b79c768a79abd691f1fedf44aea3a645296
+oid sha256:d40d94dc7bd499834f4880f664b6b9f079b31c0f8fd8c132e11901a67089a9c7
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d68f14caf8efc58720b158ce68c4b79c768a79abd691f1fedf44aea3a645296
+oid sha256:d40d94dc7bd499834f4880f664b6b9f079b31c0f8fd8c132e11901a67089a9c7
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d68f14caf8efc58720b158ce68c4b79c768a79abd691f1fedf44aea3a645296
+oid sha256:d40d94dc7bd499834f4880f664b6b9f079b31c0f8fd8c132e11901a67089a9c7
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d68f14caf8efc58720b158ce68c4b79c768a79abd691f1fedf44aea3a645296
+oid sha256:d40d94dc7bd499834f4880f664b6b9f079b31c0f8fd8c132e11901a67089a9c7
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d68f14caf8efc58720b158ce68c4b79c768a79abd691f1fedf44aea3a645296
+oid sha256:d40d94dc7bd499834f4880f664b6b9f079b31c0f8fd8c132e11901a67089a9c7
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d68f14caf8efc58720b158ce68c4b79c768a79abd691f1fedf44aea3a645296
+oid sha256:d40d94dc7bd499834f4880f664b6b9f079b31c0f8fd8c132e11901a67089a9c7
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d68f14caf8efc58720b158ce68c4b79c768a79abd691f1fedf44aea3a645296
+oid sha256:d40d94dc7bd499834f4880f664b6b9f079b31c0f8fd8c132e11901a67089a9c7
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d68f14caf8efc58720b158ce68c4b79c768a79abd691f1fedf44aea3a645296
+oid sha256:d40d94dc7bd499834f4880f664b6b9f079b31c0f8fd8c132e11901a67089a9c7
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd2861f0d820018c213fdc57cc6eebc5c8df9d5485c4072b9ac9a4ac6f902e69
+oid sha256:7a265c146087c7b525f93e19ac9e51ad44bfb6af09ebd3ea4e38ee99de52c725
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.332534787705796,
-  "global_step": 170000,
+  "epoch": 4.587389775217901,
+  "global_step": 180000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3406,11 +3406,211 @@
       "eval_samples_per_second": 788.617,
       "eval_steps_per_second": 12.618,
       "step": 170000
+    },
+    {
+      "epoch": 4.35,
+      "learning_rate": 0.0002378846657362306,
+      "loss": 0.2997,
+      "step": 170500
+    },
+    {
+      "epoch": 4.36,
+      "learning_rate": 0.00023749076897000928,
+      "loss": 0.2997,
+      "step": 171000
+    },
+    {
+      "epoch": 4.36,
+      "eval_loss": 0.8417762517929077,
+      "eval_runtime": 1.3079,
+      "eval_samples_per_second": 764.585,
+      "eval_steps_per_second": 12.233,
+      "step": 171000
+    },
+    {
+      "epoch": 4.37,
+      "learning_rate": 0.00023709597009795465,
+      "loss": 0.2982,
+      "step": 171500
+    },
+    {
+      "epoch": 4.38,
+      "learning_rate": 0.000236700273437524,
+      "loss": 0.2975,
+      "step": 172000
+    },
+    {
+      "epoch": 4.38,
+      "eval_loss": 0.8321195244789124,
+      "eval_runtime": 1.2352,
+      "eval_samples_per_second": 809.602,
+      "eval_steps_per_second": 12.954,
+      "step": 172000
+    },
+    {
+      "epoch": 4.4,
+      "learning_rate": 0.0002363036833159925,
+      "loss": 0.2973,
+      "step": 172500
+    },
+    {
+      "epoch": 4.41,
+      "learning_rate": 0.00023590620407040633,
+      "loss": 0.2988,
+      "step": 173000
+    },
+    {
+      "epoch": 4.41,
+      "eval_loss": 0.8193117380142212,
+      "eval_runtime": 1.3026,
+      "eval_samples_per_second": 767.685,
+      "eval_steps_per_second": 12.283,
+      "step": 173000
+    },
+    {
+      "epoch": 4.42,
+      "learning_rate": 0.00023550784004753471,
+      "loss": 0.2981,
+      "step": 173500
+    },
+    {
+      "epoch": 4.43,
+      "learning_rate": 0.0002351085956038229,
+      "loss": 0.2979,
+      "step": 174000
+    },
+    {
+      "epoch": 4.43,
+      "eval_loss": 0.8212565779685974,
+      "eval_runtime": 1.3056,
+      "eval_samples_per_second": 765.951,
+      "eval_steps_per_second": 12.255,
+      "step": 174000
+    },
+    {
+      "epoch": 4.45,
+      "learning_rate": 0.00023470847510534407,
+      "loss": 0.2979,
+      "step": 174500
+    },
+    {
+      "epoch": 4.46,
+      "learning_rate": 0.00023430748292775188,
+      "loss": 0.2973,
+      "step": 175000
+    },
+    {
+      "epoch": 4.46,
+      "eval_loss": 0.8219558000564575,
+      "eval_runtime": 1.2557,
+      "eval_samples_per_second": 796.365,
+      "eval_steps_per_second": 12.742,
+      "step": 175000
+    },
+    {
+      "epoch": 4.47,
+      "learning_rate": 0.0002339056234562326,
+      "loss": 0.2971,
+      "step": 175500
+    },
+    {
+      "epoch": 4.49,
+      "learning_rate": 0.00023350290108545694,
+      "loss": 0.2967,
+      "step": 176000
+    },
+    {
+      "epoch": 4.49,
+      "eval_loss": 0.8285974264144897,
+      "eval_runtime": 1.2416,
+      "eval_samples_per_second": 805.395,
+      "eval_steps_per_second": 12.886,
+      "step": 176000
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 0.00023309932021953238,
+      "loss": 0.2971,
+      "step": 176500
+    },
+    {
+      "epoch": 4.51,
+      "learning_rate": 0.00023269488527195446,
+      "loss": 0.2969,
+      "step": 177000
+    },
+    {
+      "epoch": 4.51,
+      "eval_loss": 0.8219101428985596,
+      "eval_runtime": 1.2379,
+      "eval_samples_per_second": 807.823,
+      "eval_steps_per_second": 12.925,
+      "step": 177000
+    },
+    {
+      "epoch": 4.52,
+      "learning_rate": 0.00023228960066555907,
+      "loss": 0.297,
+      "step": 177500
+    },
+    {
+      "epoch": 4.54,
+      "learning_rate": 0.00023188347083247365,
+      "loss": 0.2966,
+      "step": 178000
+    },
+    {
+      "epoch": 4.54,
+      "eval_loss": 0.8279162645339966,
+      "eval_runtime": 1.2407,
+      "eval_samples_per_second": 805.969,
+      "eval_steps_per_second": 12.895,
+      "step": 178000
+    },
+    {
+      "epoch": 4.55,
+      "learning_rate": 0.00023147650021406905,
+      "loss": 0.2975,
+      "step": 178500
+    },
+    {
+      "epoch": 4.56,
+      "learning_rate": 0.00023106869326091075,
+      "loss": 0.2966,
+      "step": 179000
+    },
+    {
+      "epoch": 4.56,
+      "eval_loss": 0.8254020810127258,
+      "eval_runtime": 1.2293,
+      "eval_samples_per_second": 813.461,
+      "eval_steps_per_second": 13.015,
+      "step": 179000
+    },
+    {
+      "epoch": 4.57,
+      "learning_rate": 0.00023066005443271017,
+      "loss": 0.2976,
+      "step": 179500
+    },
+    {
+      "epoch": 4.59,
+      "learning_rate": 0.00023025058819827618,
+      "loss": 0.2968,
+      "step": 180000
+    },
+    {
+      "epoch": 4.59,
+      "eval_loss": 0.8309011459350586,
+      "eval_runtime": 1.2373,
+      "eval_samples_per_second": 808.182,
+      "eval_steps_per_second": 12.931,
+      "step": 180000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 5.43122744351432e+21,
+  "total_flos": 5.75071458228882e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a436af1cb440949a8156a3e0bac95099a250179167b60f6ba2300e45f023d5ef
+oid sha256:2cf77efb61849887c31eb27074736092c24c74904d823d7c3253ad56e6671aad
 size 102501541