Training in progress, step 480000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5de66d4a93d929dbf59bf082b441005c55284067d059fcb692905debf93d43ec
+oid sha256:b4060e633dae015e5639b74a57f1603654125aa36a5a7f3f6681895bc39045ec
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b866106aa5570064c241431938c823c9b3d9c0359a68aaf12dac64797d2c681f
+oid sha256:f459617feff07cc080660c37736876af343cf74d6054e3f49e34fa66dc0e7730
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0939dfbb6ece3c207cb8da7c45398fb3890f9eac2a2a8a7c463fa15eb93581f8
+oid sha256:999632cad034f4eed7b42df53c59662bbc3b13bc2d63a7da3c114bc461d69692
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0939dfbb6ece3c207cb8da7c45398fb3890f9eac2a2a8a7c463fa15eb93581f8
+oid sha256:999632cad034f4eed7b42df53c59662bbc3b13bc2d63a7da3c114bc461d69692
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0939dfbb6ece3c207cb8da7c45398fb3890f9eac2a2a8a7c463fa15eb93581f8
+oid sha256:999632cad034f4eed7b42df53c59662bbc3b13bc2d63a7da3c114bc461d69692
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0939dfbb6ece3c207cb8da7c45398fb3890f9eac2a2a8a7c463fa15eb93581f8
+oid sha256:999632cad034f4eed7b42df53c59662bbc3b13bc2d63a7da3c114bc461d69692
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0939dfbb6ece3c207cb8da7c45398fb3890f9eac2a2a8a7c463fa15eb93581f8
+oid sha256:999632cad034f4eed7b42df53c59662bbc3b13bc2d63a7da3c114bc461d69692
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0939dfbb6ece3c207cb8da7c45398fb3890f9eac2a2a8a7c463fa15eb93581f8
+oid sha256:999632cad034f4eed7b42df53c59662bbc3b13bc2d63a7da3c114bc461d69692
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0939dfbb6ece3c207cb8da7c45398fb3890f9eac2a2a8a7c463fa15eb93581f8
+oid sha256:999632cad034f4eed7b42df53c59662bbc3b13bc2d63a7da3c114bc461d69692
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0939dfbb6ece3c207cb8da7c45398fb3890f9eac2a2a8a7c463fa15eb93581f8
+oid sha256:999632cad034f4eed7b42df53c59662bbc3b13bc2d63a7da3c114bc461d69692
 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": 10.483583154889365,
-  "global_step": 470000,
+  "epoch": 10.70663811563169,
+  "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": 1202.649,
       "eval_steps_per_second": 18.849,
       "step": 470000
+    },
+    {
+      "epoch": 10.49,
+      "learning_rate": 1.2751163567020592e-05,
+      "loss": 0.2544,
+      "step": 470500
+    },
+    {
+      "epoch": 10.51,
+      "learning_rate": 1.2658977796373478e-05,
+      "loss": 0.2546,
+      "step": 471000
+    },
+    {
+      "epoch": 10.51,
+      "eval_loss": 0.23835012316703796,
+      "eval_runtime": 2.0021,
+      "eval_samples_per_second": 1147.276,
+      "eval_steps_per_second": 17.981,
+      "step": 471000
+    },
+    {
+      "epoch": 10.52,
+      "learning_rate": 1.2568348644340153e-05,
+      "loss": 0.2545,
+      "step": 471500
+    },
+    {
+      "epoch": 10.53,
+      "learning_rate": 1.2479277102026465e-05,
+      "loss": 0.2544,
+      "step": 472000
+    },
+    {
+      "epoch": 10.53,
+      "eval_loss": 0.23700165748596191,
+      "eval_runtime": 2.0158,
+      "eval_samples_per_second": 1139.473,
+      "eval_steps_per_second": 17.859,
+      "step": 472000
+    },
+    {
+      "epoch": 10.54,
+      "learning_rate": 1.2391764143504556e-05,
+      "loss": 0.2542,
+      "step": 472500
+    },
+    {
+      "epoch": 10.55,
+      "learning_rate": 1.2305810725802118e-05,
+      "loss": 0.254,
+      "step": 473000
+    },
+    {
+      "epoch": 10.55,
+      "eval_loss": 0.23847134411334991,
+      "eval_runtime": 1.9758,
+      "eval_samples_per_second": 1162.557,
+      "eval_steps_per_second": 18.22,
+      "step": 473000
+    },
+    {
+      "epoch": 10.56,
+      "learning_rate": 1.222141778889195e-05,
+      "loss": 0.2538,
+      "step": 473500
+    },
+    {
+      "epoch": 10.57,
+      "learning_rate": 1.2138586255681707e-05,
+      "loss": 0.2539,
+      "step": 474000
+    },
+    {
+      "epoch": 10.57,
+      "eval_loss": 0.23491570353507996,
+      "eval_runtime": 1.99,
+      "eval_samples_per_second": 1154.271,
+      "eval_steps_per_second": 18.09,
+      "step": 474000
+    },
+    {
+      "epoch": 10.58,
+      "learning_rate": 1.2057317032003731e-05,
+      "loss": 0.2542,
+      "step": 474500
+    },
+    {
+      "epoch": 10.6,
+      "learning_rate": 1.1977611006605263e-05,
+      "loss": 0.2549,
+      "step": 475000
+    },
+    {
+      "epoch": 10.6,
+      "eval_loss": 0.2358667552471161,
+      "eval_runtime": 2.0083,
+      "eval_samples_per_second": 1143.743,
+      "eval_steps_per_second": 17.925,
+      "step": 475000
+    },
+    {
+      "epoch": 10.61,
+      "learning_rate": 1.1899469051138602e-05,
+      "loss": 0.2543,
+      "step": 475500
+    },
+    {
+      "epoch": 10.62,
+      "learning_rate": 1.1822892020151667e-05,
+      "loss": 0.2549,
+      "step": 476000
+    },
+    {
+      "epoch": 10.62,
+      "eval_loss": 0.2398059368133545,
+      "eval_runtime": 2.007,
+      "eval_samples_per_second": 1144.474,
+      "eval_steps_per_second": 17.937,
+      "step": 476000
+    },
+    {
+      "epoch": 10.63,
+      "learning_rate": 1.1747880751078614e-05,
+      "loss": 0.2554,
+      "step": 476500
+    },
+    {
+      "epoch": 10.64,
+      "learning_rate": 1.1674436064230637e-05,
+      "loss": 0.2548,
+      "step": 477000
+    },
+    {
+      "epoch": 10.64,
+      "eval_loss": 0.23931536078453064,
+      "eval_runtime": 1.9895,
+      "eval_samples_per_second": 1154.534,
+      "eval_steps_per_second": 18.095,
+      "step": 477000
+    },
+    {
+      "epoch": 10.65,
+      "learning_rate": 1.1602558762787069e-05,
+      "loss": 0.2547,
+      "step": 477500
+    },
+    {
+      "epoch": 10.66,
+      "learning_rate": 1.1532249632786582e-05,
+      "loss": 0.2542,
+      "step": 478000
+    },
+    {
+      "epoch": 10.66,
+      "eval_loss": 0.237422376871109,
+      "eval_runtime": 2.0815,
+      "eval_samples_per_second": 1103.524,
+      "eval_steps_per_second": 17.295,
+      "step": 478000
+    },
+    {
+      "epoch": 10.67,
+      "learning_rate": 1.1463509443118552e-05,
+      "loss": 0.2541,
+      "step": 478500
+    },
+    {
+      "epoch": 10.68,
+      "learning_rate": 1.1396338945514663e-05,
+      "loss": 0.2543,
+      "step": 479000
+    },
+    {
+      "epoch": 10.68,
+      "eval_loss": 0.2378796935081482,
+      "eval_runtime": 2.0025,
+      "eval_samples_per_second": 1147.061,
+      "eval_steps_per_second": 17.977,
+      "step": 479000
+    },
+    {
+      "epoch": 10.7,
+      "learning_rate": 1.133073887454072e-05,
+      "loss": 0.2538,
+      "step": 479500
+    },
+    {
+      "epoch": 10.71,
+      "learning_rate": 1.1266709947588599e-05,
+      "loss": 0.2539,
+      "step": 480000
+    },
+    {
+      "epoch": 10.71,
+      "eval_loss": 0.2366316020488739,
+      "eval_runtime": 1.9626,
+      "eval_samples_per_second": 1170.393,
+      "eval_steps_per_second": 18.343,
+      "step": 480000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 1.5015610979787347e+22,
+  "total_flos": 1.5335098118561847e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b866106aa5570064c241431938c823c9b3d9c0359a68aaf12dac64797d2c681f
+oid sha256:f459617feff07cc080660c37736876af343cf74d6054e3f49e34fa66dc0e7730
 size 102501541