Training in progress, step 140000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b61f0fcd50875833fb0e1f9ce51cdf7d430e60b619e76669b19c533bc334c88
+oid sha256:e1a663fa8a1428dfd0e1ea579f8f1884a2fe84a94e67275218c60462158fe8aa
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39c23cb20328d6cd580ce88942d789c9a02552a95a268d89326d508421abbe4a
+oid sha256:a40275396ce53417c9c00526c28902e900eee7fe8a1176e3b167b8fa880709f1
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8e29d5733f7ec570f71140fb29faf2306a82ee45c27c9eb9c785e5d73fa8382
+oid sha256:ff6473d36a3b0d61e638f6f7adf0e3c4e3a4c90311741bef45eedc8752b4abbb
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dabc5ed16f76e0d1a8c7f2b2c2a3619addb4d0c3eca0a88fa6e7b0ba2beea5dd
+oid sha256:abd20d5dfc80e3bb5cba79ef18d635e6b9d3fba3685d49236ba9bbfcbd245f3d
 size 14439

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7531b762a4f77385b5cf4054c1324ef1475bf3e0305baf6834591cd7a2e6b325
+oid sha256:2963be3c0faa28379747d9429ff572f2788db89f6185c9c53832cb9290c1c849
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95971fab031e1bc0e074238eeb9bb97d0dce735f44e80bc1ac009c7c3e11e0ef
+oid sha256:bc4f1c2a017f1ba8bd941830cb07d47e6bde89cb5e80ca0663de3f779aa3e16b
 size 14439

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b5759d26021494b175082e8aa472aecf989df6cf2e73cc13099dc5f04e8a3a7
-size 14503
+oid sha256:52188af98e11936af8bc69f5366b88b44cd6c73d9b1b37682a5e46e4706f5e3f
+size 14439

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:437af33cac768d06b94a7ff819e2415c2d01a6cb933eea2964edd87e0a74d2a3
+oid sha256:299331297e38ed6c53d0026997de39e06ade131719f6e2f227655bc716b72e7d
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f46bc5befc0dd2669aebf64aa0216b1a5da79235f03660685ed5378a375aacc
+oid sha256:d145aa3067eb9b9e66af4f261f18929e80b865f364d9ea9075acacb8581bccd8
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10d615ff7d950e30ec30974f2cf78479d745d92e39a0b3ba0bec5c1a7fb2cdeb
-size 14503
+oid sha256:e8dc2be3757aa011e41ae06df8c828d05d218a32a27ad90767a1b48fa565a909
+size 14439

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1c3de3c2d66025eca4b56b8d5efacb781ba1e9b4daae40acd9c92c0f7cbe98c
+oid sha256:f9522f343e5b1c37fe7e600f7b39d619e850350d8948dc240940a440582a0eb9
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.9829651643739084,
-  "global_step": 130000,
+  "epoch": 4.289347100094979,
+  "global_step": 140000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2606,11 +2606,211 @@
       "eval_samples_per_second": 1938.903,
       "eval_steps_per_second": 31.022,
       "step": 130000
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0002661106834948409,
+      "loss": 0.3626,
+      "step": 130500
+    },
+    {
+      "epoch": 4.01,
+      "learning_rate": 0.0002658019908268041,
+      "loss": 0.3625,
+      "step": 131000
+    },
+    {
+      "epoch": 4.01,
+      "eval_loss": 0.7918245792388916,
+      "eval_runtime": 0.521,
+      "eval_samples_per_second": 1919.333,
+      "eval_steps_per_second": 30.709,
+      "step": 131000
+    },
+    {
+      "epoch": 4.03,
+      "learning_rate": 0.00026549208644594766,
+      "loss": 0.3622,
+      "step": 131500
+    },
+    {
+      "epoch": 4.04,
+      "learning_rate": 0.00026518097374133627,
+      "loss": 0.3622,
+      "step": 132000
+    },
+    {
+      "epoch": 4.04,
+      "eval_loss": 0.7886719107627869,
+      "eval_runtime": 0.5166,
+      "eval_samples_per_second": 1935.893,
+      "eval_steps_per_second": 30.974,
+      "step": 132000
+    },
+    {
+      "epoch": 4.06,
+      "learning_rate": 0.00026486865611524853,
+      "loss": 0.3622,
+      "step": 132500
+    },
+    {
+      "epoch": 4.07,
+      "learning_rate": 0.00026455513698314003,
+      "loss": 0.3616,
+      "step": 133000
+    },
+    {
+      "epoch": 4.07,
+      "eval_loss": 0.7906731963157654,
+      "eval_runtime": 0.5202,
+      "eval_samples_per_second": 1922.502,
+      "eval_steps_per_second": 30.76,
+      "step": 133000
+    },
+    {
+      "epoch": 4.09,
+      "learning_rate": 0.0002642404197736058,
+      "loss": 0.3618,
+      "step": 133500
+    },
+    {
+      "epoch": 4.11,
+      "learning_rate": 0.0002639245079283428,
+      "loss": 0.3646,
+      "step": 134000
+    },
+    {
+      "epoch": 4.11,
+      "eval_loss": 0.7901037931442261,
+      "eval_runtime": 0.5304,
+      "eval_samples_per_second": 1885.342,
+      "eval_steps_per_second": 30.165,
+      "step": 134000
+    },
+    {
+      "epoch": 4.12,
+      "learning_rate": 0.00026360740490211234,
+      "loss": 0.3612,
+      "step": 134500
+    },
+    {
+      "epoch": 4.14,
+      "learning_rate": 0.0002632891141627023,
+      "loss": 0.3604,
+      "step": 135000
+    },
+    {
+      "epoch": 4.14,
+      "eval_loss": 0.7916610836982727,
+      "eval_runtime": 0.5131,
+      "eval_samples_per_second": 1948.858,
+      "eval_steps_per_second": 31.182,
+      "step": 135000
+    },
+    {
+      "epoch": 4.15,
+      "learning_rate": 0.00026296963919088923,
+      "loss": 0.3603,
+      "step": 135500
+    },
+    {
+      "epoch": 4.17,
+      "learning_rate": 0.00026264898348040024,
+      "loss": 0.3604,
+      "step": 136000
+    },
+    {
+      "epoch": 4.17,
+      "eval_loss": 0.7712200284004211,
+      "eval_runtime": 0.519,
+      "eval_samples_per_second": 1926.697,
+      "eval_steps_per_second": 30.827,
+      "step": 136000
+    },
+    {
+      "epoch": 4.18,
+      "learning_rate": 0.0002623271505378748,
+      "loss": 0.3608,
+      "step": 136500
+    },
+    {
+      "epoch": 4.2,
+      "learning_rate": 0.00026200414388282637,
+      "loss": 0.361,
+      "step": 137000
+    },
+    {
+      "epoch": 4.2,
+      "eval_loss": 0.7850333452224731,
+      "eval_runtime": 0.5415,
+      "eval_samples_per_second": 1846.815,
+      "eval_steps_per_second": 29.549,
+      "step": 137000
+    },
+    {
+      "epoch": 4.21,
+      "learning_rate": 0.00026167996704760406,
+      "loss": 0.3603,
+      "step": 137500
+    },
+    {
+      "epoch": 4.23,
+      "learning_rate": 0.00026135462357735375,
+      "loss": 0.3604,
+      "step": 138000
+    },
+    {
+      "epoch": 4.23,
+      "eval_loss": 0.7824327349662781,
+      "eval_runtime": 0.5307,
+      "eval_samples_per_second": 1884.218,
+      "eval_steps_per_second": 30.147,
+      "step": 138000
+    },
+    {
+      "epoch": 4.24,
+      "learning_rate": 0.0002610281170299795,
+      "loss": 0.3602,
+      "step": 138500
+    },
+    {
+      "epoch": 4.26,
+      "learning_rate": 0.00026070045097610465,
+      "loss": 0.36,
+      "step": 139000
+    },
+    {
+      "epoch": 4.26,
+      "eval_loss": 0.787578821182251,
+      "eval_runtime": 0.5306,
+      "eval_samples_per_second": 1884.712,
+      "eval_steps_per_second": 30.155,
+      "step": 139000
+    },
+    {
+      "epoch": 4.27,
+      "learning_rate": 0.0002603716289990326,
+      "loss": 0.3601,
+      "step": 139500
+    },
+    {
+      "epoch": 4.29,
+      "learning_rate": 0.00026004165469470787,
+      "loss": 0.3597,
+      "step": 140000
+    },
+    {
+      "epoch": 4.29,
+      "eval_loss": 0.7803857326507568,
+      "eval_runtime": 0.5242,
+      "eval_samples_per_second": 1907.849,
+      "eval_steps_per_second": 30.526,
+      "step": 140000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 16,
-  "total_flos": 4.1533088402125724e+21,
+  "total_flos": 4.4727879910350966e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39c23cb20328d6cd580ce88942d789c9a02552a95a268d89326d508421abbe4a
+oid sha256:a40275396ce53417c9c00526c28902e900eee7fe8a1176e3b167b8fa880709f1
 size 102501541