Training in progress, step 170000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce756be38c7d806962a75c4ecd24790cdff6367292efa2cdf7ed0fff4145bbe4
+oid sha256:957a0b613730bb1f7e18c8182652c293421c706a14fa7ef89a59100dcf03486e
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac08afb5aa40873b91a011a4ac3e7ff40a672e324d1988d9844c7b8fb857f575
+oid sha256:a436af1cb440949a8156a3e0bac95099a250179167b60f6ba2300e45f023d5ef
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e3deb747f474d2d0563b125ac601cf8de26ef8f9fd17f727b1a014aa5e2d9d4
+oid sha256:8d68f14caf8efc58720b158ce68c4b79c768a79abd691f1fedf44aea3a645296
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e3deb747f474d2d0563b125ac601cf8de26ef8f9fd17f727b1a014aa5e2d9d4
+oid sha256:8d68f14caf8efc58720b158ce68c4b79c768a79abd691f1fedf44aea3a645296
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e3deb747f474d2d0563b125ac601cf8de26ef8f9fd17f727b1a014aa5e2d9d4
+oid sha256:8d68f14caf8efc58720b158ce68c4b79c768a79abd691f1fedf44aea3a645296
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e3deb747f474d2d0563b125ac601cf8de26ef8f9fd17f727b1a014aa5e2d9d4
+oid sha256:8d68f14caf8efc58720b158ce68c4b79c768a79abd691f1fedf44aea3a645296
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e3deb747f474d2d0563b125ac601cf8de26ef8f9fd17f727b1a014aa5e2d9d4
+oid sha256:8d68f14caf8efc58720b158ce68c4b79c768a79abd691f1fedf44aea3a645296
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e3deb747f474d2d0563b125ac601cf8de26ef8f9fd17f727b1a014aa5e2d9d4
+oid sha256:8d68f14caf8efc58720b158ce68c4b79c768a79abd691f1fedf44aea3a645296
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e3deb747f474d2d0563b125ac601cf8de26ef8f9fd17f727b1a014aa5e2d9d4
+oid sha256:8d68f14caf8efc58720b158ce68c4b79c768a79abd691f1fedf44aea3a645296
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e3deb747f474d2d0563b125ac601cf8de26ef8f9fd17f727b1a014aa5e2d9d4
+oid sha256:8d68f14caf8efc58720b158ce68c4b79c768a79abd691f1fedf44aea3a645296
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bc0c53c979a7805930dacd44e26c88894a437860c12a8b9fd2b0695ce7c583e
+oid sha256:fd2861f0d820018c213fdc57cc6eebc5c8df9d5485c4072b9ac9a4ac6f902e69
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.07767980019369,
-  "global_step": 160000,
+  "epoch": 4.332534787705796,
+  "global_step": 170000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3206,11 +3206,211 @@
       "eval_samples_per_second": 789.172,
       "eval_steps_per_second": 12.627,
       "step": 160000
+    },
+    {
+      "epoch": 4.09,
+      "learning_rate": 0.0002455665988827021,
+      "loss": 0.2998,
+      "step": 160500
+    },
+    {
+      "epoch": 4.1,
+      "learning_rate": 0.0002451916353649261,
+      "loss": 0.2996,
+      "step": 161000
+    },
+    {
+      "epoch": 4.1,
+      "eval_loss": 0.8267243504524231,
+      "eval_runtime": 1.2949,
+      "eval_samples_per_second": 772.28,
+      "eval_steps_per_second": 12.356,
+      "step": 161000
+    },
+    {
+      "epoch": 4.12,
+      "learning_rate": 0.00024481568552587566,
+      "loss": 0.2999,
+      "step": 161500
+    },
+    {
+      "epoch": 4.13,
+      "learning_rate": 0.0002444387534768781,
+      "loss": 0.301,
+      "step": 162000
+    },
+    {
+      "epoch": 4.13,
+      "eval_loss": 0.8215921521186829,
+      "eval_runtime": 1.2633,
+      "eval_samples_per_second": 791.589,
+      "eval_steps_per_second": 12.665,
+      "step": 162000
+    },
+    {
+      "epoch": 4.14,
+      "learning_rate": 0.0002440608433400018,
+      "loss": 0.2995,
+      "step": 162500
+    },
+    {
+      "epoch": 4.15,
+      "learning_rate": 0.00024368195924801158,
+      "loss": 0.2987,
+      "step": 163000
+    },
+    {
+      "epoch": 4.15,
+      "eval_loss": 0.8304322957992554,
+      "eval_runtime": 1.2627,
+      "eval_samples_per_second": 791.952,
+      "eval_steps_per_second": 12.671,
+      "step": 163000
+    },
+    {
+      "epoch": 4.17,
+      "learning_rate": 0.00024330210534432314,
+      "loss": 0.2989,
+      "step": 163500
+    },
+    {
+      "epoch": 4.18,
+      "learning_rate": 0.0002429212857829579,
+      "loss": 0.2989,
+      "step": 164000
+    },
+    {
+      "epoch": 4.18,
+      "eval_loss": 0.8384572863578796,
+      "eval_runtime": 1.2927,
+      "eval_samples_per_second": 773.554,
+      "eval_steps_per_second": 12.377,
+      "step": 164000
+    },
+    {
+      "epoch": 4.19,
+      "learning_rate": 0.00024253950472849758,
+      "loss": 0.2995,
+      "step": 164500
+    },
+    {
+      "epoch": 4.21,
+      "learning_rate": 0.0002421567663560386,
+      "loss": 0.2995,
+      "step": 165000
+    },
+    {
+      "epoch": 4.21,
+      "eval_loss": 0.8305343985557556,
+      "eval_runtime": 1.3381,
+      "eval_samples_per_second": 747.307,
+      "eval_steps_per_second": 11.957,
+      "step": 165000
+    },
+    {
+      "epoch": 4.22,
+      "learning_rate": 0.00024177307485114653,
+      "loss": 0.2996,
+      "step": 165500
+    },
+    {
+      "epoch": 4.23,
+      "learning_rate": 0.0002413884344098101,
+      "loss": 0.2998,
+      "step": 166000
+    },
+    {
+      "epoch": 4.23,
+      "eval_loss": 0.8391353487968445,
+      "eval_runtime": 1.2414,
+      "eval_samples_per_second": 805.533,
+      "eval_steps_per_second": 12.889,
+      "step": 166000
+    },
+    {
+      "epoch": 4.24,
+      "learning_rate": 0.00024100284923839568,
+      "loss": 0.2996,
+      "step": 166500
+    },
+    {
+      "epoch": 4.26,
+      "learning_rate": 0.0002406163235536008,
+      "loss": 0.2991,
+      "step": 167000
+    },
+    {
+      "epoch": 4.26,
+      "eval_loss": 0.8364063501358032,
+      "eval_runtime": 1.2744,
+      "eval_samples_per_second": 784.671,
+      "eval_steps_per_second": 12.555,
+      "step": 167000
+    },
+    {
+      "epoch": 4.27,
+      "learning_rate": 0.00024022886158240857,
+      "loss": 0.2985,
+      "step": 167500
+    },
+    {
+      "epoch": 4.28,
+      "learning_rate": 0.0002398404675620409,
+      "loss": 0.2994,
+      "step": 168000
+    },
+    {
+      "epoch": 4.28,
+      "eval_loss": 0.8259013891220093,
+      "eval_runtime": 1.2581,
+      "eval_samples_per_second": 794.863,
+      "eval_steps_per_second": 12.718,
+      "step": 168000
+    },
+    {
+      "epoch": 4.29,
+      "learning_rate": 0.0002394511457399126,
+      "loss": 0.2983,
+      "step": 168500
+    },
+    {
+      "epoch": 4.31,
+      "learning_rate": 0.00023906090037358478,
+      "loss": 0.2977,
+      "step": 169000
+    },
+    {
+      "epoch": 4.31,
+      "eval_loss": 0.8347362875938416,
+      "eval_runtime": 1.2843,
+      "eval_samples_per_second": 778.639,
+      "eval_steps_per_second": 12.458,
+      "step": 169000
+    },
+    {
+      "epoch": 4.32,
+      "learning_rate": 0.0002386697357307182,
+      "loss": 0.2979,
+      "step": 169500
+    },
+    {
+      "epoch": 4.33,
+      "learning_rate": 0.00023827765608902676,
+      "loss": 0.2989,
+      "step": 170000
+    },
+    {
+      "epoch": 4.33,
+      "eval_loss": 0.8345726728439331,
+      "eval_runtime": 1.268,
+      "eval_samples_per_second": 788.617,
+      "eval_steps_per_second": 12.618,
+      "step": 170000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 5.11174030473982e+21,
+  "total_flos": 5.43122744351432e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac08afb5aa40873b91a011a4ac3e7ff40a672e324d1988d9844c7b8fb857f575
+oid sha256:a436af1cb440949a8156a3e0bac95099a250179167b60f6ba2300e45f023d5ef
 size 102501541