Training in progress, step 22000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73cb875f1568155797c9b13f85384966dd718f46953534c4b08f677ecf9a6a82
+oid sha256:da60d3804c57e29e90c568ae5208c61903451533ab428233f16399bcbfdc9166
 size 386379

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82e61a71536ab895c8bd16825f7157395f1f1e328b8bc9b70f310b0e401ae1c9
+oid sha256:ae80c44868efaca16e3497e99d1fc33821e44d73899ed13a47e498dc9e7e5f4f
 size 1540661735

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d96b0f1732638e94f0dd38858b482c7b94b7f3411e8a578ab9a90fdbb757ebb
+oid sha256:61863070aab8e3fd6186dff8c80983e46f5b6001d914499a18aecd5a02fce32e
 size 14469

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd4b6599a59298e453c4d085cd48234a781aec741f5259b079ae63537e07c1c7
+oid sha256:1c56eb422b2956686f9277e34bc8cc34789a6a9f96cf48c8d1b348ee4c2ad32c
 size 14469

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2e7187571674580cade9fd9dfacd95fa924ade19964d58e7bb3223bdcdbc044
+oid sha256:840cbc90b77dbf5757761c33cef483dae80038c8699a537b601bec429e4b01e9
 size 14469

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cd1fa900a34ad14997cdf150e9de3df071aa3fe4c05fe4db1c61b32b2a4740c
+oid sha256:5ff0e24afa3409357bf39531523e499a8986d839d13150d8699023666917a09d
 size 14469

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82990efadc5b10e2a504af1bdd4a3367edbdc97a4dc60703abf25017a2c875ac
+oid sha256:905af1194cdc14999c18dad2fabad60fafc93ae7a1c0e79c4823b9eb13773481
 size 14469

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c9abb1ba3e1b7ce8e555b49390f991a3b537fbfb6d6b26e1bd0c291d5a66e7a
+oid sha256:c67c497a04a0d73e36401384f5befb87de2150301460bc892a7b91a194cddf9c
 size 14469

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d0f333ee4fb3004963191fa2d8aad29bd882472216b178dad7bbc0e452c4074
+oid sha256:1005ca97ab493a99758751af1ed27f7d6861f63a7b13198af207a82d4466553b
 size 14469

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc906b60e410824a7dd383e3b2d2e5d2a4a21124b5941e8d66cd1dff093e4f33
+oid sha256:35f85e297907fbcb53b678fa9ba91187159d898c1cb97d3c43297e528ef7f91d
 size 14469

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aab6b99bf19a139d59a98baf0538093fa1ac1d789fb675ce2d1672f97dd7cb0e
+oid sha256:c4367024a5082b707bb4697c2bda35f75c55af7bbf7b2a4d5e72a490087ab5da
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8,
+  "epoch": 0.88,
   "eval_steps": 1000,
-  "global_step": 20000,
+  "global_step": 22000,
   "is_hyper_param_search": false,
   "is_local_process_zero": false,
   "is_world_process_zero": true,
@@ -1588,6 +1588,164 @@
       "eval_samples_per_second": 18.231,
       "eval_steps_per_second": 0.583,
       "step": 20000
+    },
+    {
+      "epoch": 0.804,
+      "grad_norm": 1.055684208869934,
+      "learning_rate": 0.00036775145669569497,
+      "loss": 42.2956591796875,
+      "step": 20100
+    },
+    {
+      "epoch": 0.808,
+      "grad_norm": 1.0924086570739746,
+      "learning_rate": 0.0003533513873867442,
+      "loss": 42.5350732421875,
+      "step": 20200
+    },
+    {
+      "epoch": 0.812,
+      "grad_norm": 1.0316708087921143,
+      "learning_rate": 0.0003392115511243421,
+      "loss": 42.4560107421875,
+      "step": 20300
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 1.1133615970611572,
+      "learning_rate": 0.00032533418253987323,
+      "loss": 42.3101513671875,
+      "step": 20400
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.103115200996399,
+      "learning_rate": 0.00031172147478485514,
+      "loss": 42.077275390625,
+      "step": 20500
+    },
+    {
+      "epoch": 0.824,
+      "grad_norm": 1.1964024305343628,
+      "learning_rate": 0.00029837557918433946,
+      "loss": 42.031953125,
+      "step": 20600
+    },
+    {
+      "epoch": 0.828,
+      "grad_norm": 1.4636120796203613,
+      "learning_rate": 0.00028529860489691903,
+      "loss": 42.072587890625,
+      "step": 20700
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 1.1224356889724731,
+      "learning_rate": 0.00027249261858140186,
+      "loss": 42.538427734375,
+      "step": 20800
+    },
+    {
+      "epoch": 0.836,
+      "grad_norm": 0.7813518643379211,
+      "learning_rate": 0.00025995964407019923,
+      "loss": 42.4304736328125,
+      "step": 20900
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.8456737399101257,
+      "learning_rate": 0.0002477016620494856,
+      "loss": 42.2731982421875,
+      "step": 21000
+    },
+    {
+      "epoch": 0.84,
+      "eval_accuracy": 0.22656598240469208,
+      "eval_loss": 42.09526824951172,
+      "eval_runtime": 7.2222,
+      "eval_samples_per_second": 17.308,
+      "eval_steps_per_second": 0.554,
+      "step": 21000
+    },
+    {
+      "epoch": 0.844,
+      "grad_norm": 1.4627004861831665,
+      "learning_rate": 0.00023572060974617082,
+      "loss": 42.2644970703125,
+      "step": 21100
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 1.2561938762664795,
+      "learning_rate": 0.0002240183806217493,
+      "loss": 42.0703955078125,
+      "step": 21200
+    },
+    {
+      "epoch": 0.852,
+      "grad_norm": 1.2216907739639282,
+      "learning_rate": 0.00021259682407305847,
+      "loss": 42.2020556640625,
+      "step": 21300
+    },
+    {
+      "epoch": 0.856,
+      "grad_norm": 0.8914040923118591,
+      "learning_rate": 0.00020145774514000438,
+      "loss": 42.357060546875,
+      "step": 21400
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.1476701498031616,
+      "learning_rate": 0.00019060290422029657,
+      "loss": 42.13251953125,
+      "step": 21500
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 1.119214653968811,
+      "learning_rate": 0.00018003401679123887,
+      "loss": 42.2200732421875,
+      "step": 21600
+    },
+    {
+      "epoch": 0.868,
+      "grad_norm": 0.9182925820350647,
+      "learning_rate": 0.0001697527531386196,
+      "loss": 42.22140625,
+      "step": 21700
+    },
+    {
+      "epoch": 0.872,
+      "grad_norm": 1.2138001918792725,
+      "learning_rate": 0.00015976073809273973,
+      "loss": 42.254619140625,
+      "step": 21800
+    },
+    {
+      "epoch": 0.876,
+      "grad_norm": 1.321160078048706,
+      "learning_rate": 0.00015005955077163137,
+      "loss": 42.439716796875,
+      "step": 21900
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.8333455920219421,
+      "learning_rate": 0.00014065072433149607,
+      "loss": 42.4203271484375,
+      "step": 22000
+    },
+    {
+      "epoch": 0.88,
+      "eval_accuracy": 0.2271329423264907,
+      "eval_loss": 42.06480407714844,
+      "eval_runtime": 6.8562,
+      "eval_samples_per_second": 18.232,
+      "eval_steps_per_second": 0.583,
+      "step": 22000
     }
   ],
   "logging_steps": 100,