Training in progress, step 560000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2ed2d2ebacd7c7bc94a9d5b359875612bcd82c11229aa6d78716aa5ee16a33b
+oid sha256:0b1cc1f37f7674d19f50d0ac065ef69529e5d29f5bb20b814471f7b204857988
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b156aacca311d8af63ef36e1ded9f1bccccc04c94ee9871c381f73fe7e5ad577
+oid sha256:e49d2c84e31d61487864f2465a53de7f412017d3a4351764e556c2063f04b645
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b69156129ac8d15ff24024e58191195a53f5f104d191324494328fe5de76a632
+oid sha256:48b59e1e03e49cc431ae4100dc25b1494b2774eb8a3efc82fdd3d6eb3cf7405c
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b69156129ac8d15ff24024e58191195a53f5f104d191324494328fe5de76a632
+oid sha256:48b59e1e03e49cc431ae4100dc25b1494b2774eb8a3efc82fdd3d6eb3cf7405c
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b69156129ac8d15ff24024e58191195a53f5f104d191324494328fe5de76a632
+oid sha256:48b59e1e03e49cc431ae4100dc25b1494b2774eb8a3efc82fdd3d6eb3cf7405c
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b69156129ac8d15ff24024e58191195a53f5f104d191324494328fe5de76a632
+oid sha256:48b59e1e03e49cc431ae4100dc25b1494b2774eb8a3efc82fdd3d6eb3cf7405c
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b69156129ac8d15ff24024e58191195a53f5f104d191324494328fe5de76a632
+oid sha256:48b59e1e03e49cc431ae4100dc25b1494b2774eb8a3efc82fdd3d6eb3cf7405c
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b69156129ac8d15ff24024e58191195a53f5f104d191324494328fe5de76a632
+oid sha256:48b59e1e03e49cc431ae4100dc25b1494b2774eb8a3efc82fdd3d6eb3cf7405c
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b69156129ac8d15ff24024e58191195a53f5f104d191324494328fe5de76a632
+oid sha256:48b59e1e03e49cc431ae4100dc25b1494b2774eb8a3efc82fdd3d6eb3cf7405c
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b69156129ac8d15ff24024e58191195a53f5f104d191324494328fe5de76a632
+oid sha256:48b59e1e03e49cc431ae4100dc25b1494b2774eb8a3efc82fdd3d6eb3cf7405c
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8de7df7ff53e44669a043f69e39b55baa82d81ac1777f09e2f6159ffcb51dd66
+oid sha256:af9a25b33d29c3fd157c79676adec6abbe35f3978d907c7efc857fe0437c64ac
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.134079832260799,
-  "global_step": 550000,
+  "epoch": 6.245608556483722,
+  "global_step": 560000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11006,11 +11006,211 @@
       "eval_samples_per_second": 898.971,
       "eval_steps_per_second": 14.089,
       "step": 550000
+    },
+    {
+      "epoch": 6.14,
+      "learning_rate": 7.410410620480651e-05,
+      "loss": 0.2065,
+      "step": 550500
+    },
+    {
+      "epoch": 6.15,
+      "learning_rate": 7.39887827118248e-05,
+      "loss": 0.2063,
+      "step": 551000
+    },
+    {
+      "epoch": 6.15,
+      "eval_loss": 0.1966421753168106,
+      "eval_runtime": 2.4465,
+      "eval_samples_per_second": 938.899,
+      "eval_steps_per_second": 14.715,
+      "step": 551000
+    },
+    {
+      "epoch": 6.15,
+      "learning_rate": 7.38734756532816e-05,
+      "loss": 0.2062,
+      "step": 551500
+    },
+    {
+      "epoch": 6.16,
+      "learning_rate": 7.375818534442207e-05,
+      "loss": 0.2063,
+      "step": 552000
+    },
+    {
+      "epoch": 6.16,
+      "eval_loss": 0.19533967971801758,
+      "eval_runtime": 2.4902,
+      "eval_samples_per_second": 922.429,
+      "eval_steps_per_second": 14.457,
+      "step": 552000
+    },
+    {
+      "epoch": 6.16,
+      "learning_rate": 7.364291210044542e-05,
+      "loss": 0.2058,
+      "step": 552500
+    },
+    {
+      "epoch": 6.17,
+      "learning_rate": 7.352765623650435e-05,
+      "loss": 0.2061,
+      "step": 553000
+    },
+    {
+      "epoch": 6.17,
+      "eval_loss": 0.1968429684638977,
+      "eval_runtime": 2.5279,
+      "eval_samples_per_second": 908.659,
+      "eval_steps_per_second": 14.241,
+      "step": 553000
+    },
+    {
+      "epoch": 6.17,
+      "learning_rate": 7.341241806770399e-05,
+      "loss": 0.2064,
+      "step": 553500
+    },
+    {
+      "epoch": 6.18,
+      "learning_rate": 7.329719790910108e-05,
+      "loss": 0.2056,
+      "step": 554000
+    },
+    {
+      "epoch": 6.18,
+      "eval_loss": 0.19725964963436127,
+      "eval_runtime": 2.5134,
+      "eval_samples_per_second": 913.905,
+      "eval_steps_per_second": 14.323,
+      "step": 554000
+    },
+    {
+      "epoch": 6.18,
+      "learning_rate": 7.318199607570318e-05,
+      "loss": 0.2057,
+      "step": 554500
+    },
+    {
+      "epoch": 6.19,
+      "learning_rate": 7.30668128824676e-05,
+      "loss": 0.2061,
+      "step": 555000
+    },
+    {
+      "epoch": 6.19,
+      "eval_loss": 0.19744634628295898,
+      "eval_runtime": 2.5342,
+      "eval_samples_per_second": 906.409,
+      "eval_steps_per_second": 14.206,
+      "step": 555000
+    },
+    {
+      "epoch": 6.2,
+      "learning_rate": 7.295164864430088e-05,
+      "loss": 0.2056,
+      "step": 555500
+    },
+    {
+      "epoch": 6.2,
+      "learning_rate": 7.283650367605764e-05,
+      "loss": 0.2062,
+      "step": 556000
+    },
+    {
+      "epoch": 6.2,
+      "eval_loss": 0.19634658098220825,
+      "eval_runtime": 2.4766,
+      "eval_samples_per_second": 927.495,
+      "eval_steps_per_second": 14.536,
+      "step": 556000
+    },
+    {
+      "epoch": 6.21,
+      "learning_rate": 7.272137829253983e-05,
+      "loss": 0.2059,
+      "step": 556500
+    },
+    {
+      "epoch": 6.21,
+      "learning_rate": 7.260627280849581e-05,
+      "loss": 0.2061,
+      "step": 557000
+    },
+    {
+      "epoch": 6.21,
+      "eval_loss": 0.19559474289417267,
+      "eval_runtime": 2.4504,
+      "eval_samples_per_second": 937.415,
+      "eval_steps_per_second": 14.692,
+      "step": 557000
+    },
+    {
+      "epoch": 6.22,
+      "learning_rate": 7.249118753861958e-05,
+      "loss": 0.2056,
+      "step": 557500
+    },
+    {
+      "epoch": 6.22,
+      "learning_rate": 7.23761227975499e-05,
+      "loss": 0.2055,
+      "step": 558000
+    },
+    {
+      "epoch": 6.22,
+      "eval_loss": 0.1950286328792572,
+      "eval_runtime": 2.5356,
+      "eval_samples_per_second": 905.898,
+      "eval_steps_per_second": 14.198,
+      "step": 558000
+    },
+    {
+      "epoch": 6.23,
+      "learning_rate": 7.22610788998694e-05,
+      "loss": 0.2056,
+      "step": 558500
+    },
+    {
+      "epoch": 6.23,
+      "learning_rate": 7.21460561601037e-05,
+      "loss": 0.2055,
+      "step": 559000
+    },
+    {
+      "epoch": 6.23,
+      "eval_loss": 0.19409525394439697,
+      "eval_runtime": 2.5975,
+      "eval_samples_per_second": 884.304,
+      "eval_steps_per_second": 13.859,
+      "step": 559000
+    },
+    {
+      "epoch": 6.24,
+      "learning_rate": 7.203105489272053e-05,
+      "loss": 0.2055,
+      "step": 559500
+    },
+    {
+      "epoch": 6.25,
+      "learning_rate": 7.191607541212897e-05,
+      "loss": 0.2057,
+      "step": 560000
+    },
+    {
+      "epoch": 6.25,
+      "eval_loss": 0.19587305188179016,
+      "eval_runtime": 2.6038,
+      "eval_samples_per_second": 882.169,
+      "eval_steps_per_second": 13.826,
+      "step": 560000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 12,
-  "total_flos": 3.855481497983999e+22,
+  "total_flos": 3.925581759014346e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b156aacca311d8af63ef36e1ded9f1bccccc04c94ee9871c381f73fe7e5ad577
+oid sha256:e49d2c84e31d61487864f2465a53de7f412017d3a4351764e556c2063f04b645
 size 449471589