Training in progress, step 480000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:267d3df636a0162d33e130374595442a55c8d8e98b166e9f3f7d0083011ee911
+oid sha256:5ba54747756499885166d5b2a3615c3f228992a4cee7828e07b2b46d49d2b67c
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f2373aeb4dd8a73f874cd12197ac54e4d9ac9c719856821eb66aa7befcac8c3
+oid sha256:ee18b8656f6a0b3440508e619212cead3b138d9483fe935cb4bd5e4c76ccfc89
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:241694889d5343c5f04a75e7c4db1bba90bea2ebc6296d61306df81c3305c3d0
+oid sha256:53b80add2f721b313442c1bb213a82292246deee0ccb0a8adb5825cf71645364
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:241694889d5343c5f04a75e7c4db1bba90bea2ebc6296d61306df81c3305c3d0
+oid sha256:53b80add2f721b313442c1bb213a82292246deee0ccb0a8adb5825cf71645364
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:241694889d5343c5f04a75e7c4db1bba90bea2ebc6296d61306df81c3305c3d0
+oid sha256:53b80add2f721b313442c1bb213a82292246deee0ccb0a8adb5825cf71645364
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:241694889d5343c5f04a75e7c4db1bba90bea2ebc6296d61306df81c3305c3d0
+oid sha256:53b80add2f721b313442c1bb213a82292246deee0ccb0a8adb5825cf71645364
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:241694889d5343c5f04a75e7c4db1bba90bea2ebc6296d61306df81c3305c3d0
+oid sha256:53b80add2f721b313442c1bb213a82292246deee0ccb0a8adb5825cf71645364
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:241694889d5343c5f04a75e7c4db1bba90bea2ebc6296d61306df81c3305c3d0
+oid sha256:53b80add2f721b313442c1bb213a82292246deee0ccb0a8adb5825cf71645364
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:241694889d5343c5f04a75e7c4db1bba90bea2ebc6296d61306df81c3305c3d0
+oid sha256:53b80add2f721b313442c1bb213a82292246deee0ccb0a8adb5825cf71645364
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:241694889d5343c5f04a75e7c4db1bba90bea2ebc6296d61306df81c3305c3d0
+oid sha256:53b80add2f721b313442c1bb213a82292246deee0ccb0a8adb5825cf71645364
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d15e11a6de6abd55121a73bc214cc950fb971f927ae2b1d5067145da50de5d0
+oid sha256:ebbfa680b1187d22cc7371654116ef29dab3c85749ad34b845956736ad3b3612
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.950860924066264,
-  "global_step": 470000,
+  "epoch": 11.183857965003844,
+  "global_step": 480000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -9406,11 +9406,211 @@
       "eval_samples_per_second": 1509.326,
       "eval_steps_per_second": 24.034,
       "step": 470000
+    },
+    {
+      "epoch": 10.96,
+      "learning_rate": 1.2751163567020592e-05,
+      "loss": 0.251,
+      "step": 470500
+    },
+    {
+      "epoch": 10.97,
+      "learning_rate": 1.2658977796373478e-05,
+      "loss": 0.2508,
+      "step": 471000
+    },
+    {
+      "epoch": 10.97,
+      "eval_loss": 0.2342199683189392,
+      "eval_runtime": 1.4356,
+      "eval_samples_per_second": 1531.079,
+      "eval_steps_per_second": 24.38,
+      "step": 471000
+    },
+    {
+      "epoch": 10.99,
+      "learning_rate": 1.2568348644340153e-05,
+      "loss": 0.2509,
+      "step": 471500
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 1.2479277102026465e-05,
+      "loss": 0.2508,
+      "step": 472000
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 0.23464734852313995,
+      "eval_runtime": 1.4438,
+      "eval_samples_per_second": 1522.38,
+      "eval_steps_per_second": 24.242,
+      "step": 472000
+    },
+    {
+      "epoch": 11.01,
+      "learning_rate": 1.2391764143504556e-05,
+      "loss": 0.2504,
+      "step": 472500
+    },
+    {
+      "epoch": 11.02,
+      "learning_rate": 1.2305810725802118e-05,
+      "loss": 0.2509,
+      "step": 473000
+    },
+    {
+      "epoch": 11.02,
+      "eval_loss": 0.23320455849170685,
+      "eval_runtime": 1.4791,
+      "eval_samples_per_second": 1486.056,
+      "eval_steps_per_second": 23.663,
+      "step": 473000
+    },
+    {
+      "epoch": 11.03,
+      "learning_rate": 1.222141778889195e-05,
+      "loss": 0.2508,
+      "step": 473500
+    },
+    {
+      "epoch": 11.04,
+      "learning_rate": 1.2138586255681707e-05,
+      "loss": 0.2506,
+      "step": 474000
+    },
+    {
+      "epoch": 11.04,
+      "eval_loss": 0.23511675000190735,
+      "eval_runtime": 1.4624,
+      "eval_samples_per_second": 1503.027,
+      "eval_steps_per_second": 23.934,
+      "step": 474000
+    },
+    {
+      "epoch": 11.06,
+      "learning_rate": 1.2057317032003731e-05,
+      "loss": 0.2508,
+      "step": 474500
+    },
+    {
+      "epoch": 11.07,
+      "learning_rate": 1.1977611006605263e-05,
+      "loss": 0.2506,
+      "step": 475000
+    },
+    {
+      "epoch": 11.07,
+      "eval_loss": 0.23173680901527405,
+      "eval_runtime": 1.4544,
+      "eval_samples_per_second": 1511.25,
+      "eval_steps_per_second": 24.064,
+      "step": 475000
+    },
+    {
+      "epoch": 11.08,
+      "learning_rate": 1.1899469051138602e-05,
+      "loss": 0.2507,
+      "step": 475500
+    },
+    {
+      "epoch": 11.09,
+      "learning_rate": 1.1822892020151667e-05,
+      "loss": 0.2508,
+      "step": 476000
+    },
+    {
+      "epoch": 11.09,
+      "eval_loss": 0.23393820226192474,
+      "eval_runtime": 1.4377,
+      "eval_samples_per_second": 1528.825,
+      "eval_steps_per_second": 24.344,
+      "step": 476000
+    },
+    {
+      "epoch": 11.1,
+      "learning_rate": 1.1747880751078614e-05,
+      "loss": 0.2506,
+      "step": 476500
+    },
+    {
+      "epoch": 11.11,
+      "learning_rate": 1.1674436064230637e-05,
+      "loss": 0.2506,
+      "step": 477000
+    },
+    {
+      "epoch": 11.11,
+      "eval_loss": 0.2342890352010727,
+      "eval_runtime": 1.4636,
+      "eval_samples_per_second": 1501.77,
+      "eval_steps_per_second": 23.914,
+      "step": 477000
+    },
+    {
+      "epoch": 11.13,
+      "learning_rate": 1.1602558762787069e-05,
+      "loss": 0.2507,
+      "step": 477500
+    },
+    {
+      "epoch": 11.14,
+      "learning_rate": 1.1532249632786582e-05,
+      "loss": 0.2506,
+      "step": 478000
+    },
+    {
+      "epoch": 11.14,
+      "eval_loss": 0.23357579112052917,
+      "eval_runtime": 1.4711,
+      "eval_samples_per_second": 1494.153,
+      "eval_steps_per_second": 23.792,
+      "step": 478000
+    },
+    {
+      "epoch": 11.15,
+      "learning_rate": 1.1463509443118552e-05,
+      "loss": 0.2506,
+      "step": 478500
+    },
+    {
+      "epoch": 11.16,
+      "learning_rate": 1.1396338945514663e-05,
+      "loss": 0.2508,
+      "step": 479000
+    },
+    {
+      "epoch": 11.16,
+      "eval_loss": 0.23314166069030762,
+      "eval_runtime": 1.4516,
+      "eval_samples_per_second": 1514.175,
+      "eval_steps_per_second": 24.111,
+      "step": 479000
+    },
+    {
+      "epoch": 11.17,
+      "learning_rate": 1.133073887454072e-05,
+      "loss": 0.2505,
+      "step": 479500
+    },
+    {
+      "epoch": 11.18,
+      "learning_rate": 1.1266709947588599e-05,
+      "loss": 0.2507,
+      "step": 480000
+    },
+    {
+      "epoch": 11.18,
+      "eval_loss": 0.2337002009153366,
+      "eval_runtime": 1.4605,
+      "eval_samples_per_second": 1504.998,
+      "eval_steps_per_second": 23.965,
+      "step": 480000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 1.5015870552492432e+22,
+  "total_flos": 1.5335355194276026e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f2373aeb4dd8a73f874cd12197ac54e4d9ac9c719856821eb66aa7befcac8c3
+oid sha256:ee18b8656f6a0b3440508e619212cead3b138d9483fe935cb4bd5e4c76ccfc89
 size 102501541