Training in progress, step 20000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5163584c22b230a285b507e8fe2e44bfe9c5791489c457ec3f5dae50ef6a9d4e
+oid sha256:73cb875f1568155797c9b13f85384966dd718f46953534c4b08f677ecf9a6a82
 size 386379

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea5c1de12275b49f3c217c8fb0f7b7f68cd81b837676a213fd5cbc5529e41d84
+oid sha256:82e61a71536ab895c8bd16825f7157395f1f1e328b8bc9b70f310b0e401ae1c9
 size 1540661735

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d32ac62864aa24d38961f967a353dbdc0c209a83a9a14bd5c6430acf5218f70
+oid sha256:8d96b0f1732638e94f0dd38858b482c7b94b7f3411e8a578ab9a90fdbb757ebb
 size 14469

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af8916051f16387fb69685f7e072b99274ccf08a163a3cca2253ee5f3a7d6975
+oid sha256:fd4b6599a59298e453c4d085cd48234a781aec741f5259b079ae63537e07c1c7
 size 14469

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:838f0bffb8a21a934a0dd82575abe5438ad86fa4e56f88f4502576bfc1452b15
+oid sha256:c2e7187571674580cade9fd9dfacd95fa924ade19964d58e7bb3223bdcdbc044
 size 14469

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4277fe562ff3ebc8bf0029b649400f1d520bbe1f14e9fb0ddeb5516160e4f1e
+oid sha256:2cd1fa900a34ad14997cdf150e9de3df071aa3fe4c05fe4db1c61b32b2a4740c
 size 14469

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2aca493fa7cb3a1e93f1a9b8b666fdc3f1dff09789426df3cc65d5126aa02b10
+oid sha256:82990efadc5b10e2a504af1bdd4a3367edbdc97a4dc60703abf25017a2c875ac
 size 14469

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:454e7b124610176fbeace81b35b4d3891f06294dd70b8c450a31971fb9d0f6e5
+oid sha256:6c9abb1ba3e1b7ce8e555b49390f991a3b537fbfb6d6b26e1bd0c291d5a66e7a
 size 14469

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a2463c5e875ad508adb42e7029d59e6e8bcbb4d858d11906a1c0881a41dee45
+oid sha256:9d0f333ee4fb3004963191fa2d8aad29bd882472216b178dad7bbc0e452c4074
 size 14469

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f3ee3875e552d5e8fd915d17b82bcf736028026d7ebd8fb029b832116243bc7
+oid sha256:fc906b60e410824a7dd383e3b2d2e5d2a4a21124b5941e8d66cd1dff093e4f33
 size 14469

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:218c7072bdbb7a0145270cf1a07d80a739b3014f750ae43e7b4b16e30b41a003
+oid sha256:aab6b99bf19a139d59a98baf0538093fa1ac1d789fb675ce2d1672f97dd7cb0e
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.72,
+  "epoch": 0.8,
   "eval_steps": 1000,
-  "global_step": 18000,
+  "global_step": 20000,
   "is_hyper_param_search": false,
   "is_local_process_zero": false,
   "is_world_process_zero": true,
@@ -1430,6 +1430,164 @@
       "eval_samples_per_second": 17.236,
       "eval_steps_per_second": 0.552,
       "step": 18000
+    },
+    {
+      "epoch": 0.724,
+      "grad_norm": 1.7778606414794922,
+      "learning_rate": 0.0007066090110867782,
+      "loss": 42.758095703125,
+      "step": 18100
+    },
+    {
+      "epoch": 0.728,
+      "grad_norm": 1.6367878913879395,
+      "learning_rate": 0.0006875340925068554,
+      "loss": 42.4748291015625,
+      "step": 18200
+    },
+    {
+      "epoch": 0.732,
+      "grad_norm": 1.4886348247528076,
+      "learning_rate": 0.0006686665934085281,
+      "loss": 42.22041015625,
+      "step": 18300
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 1.0366780757904053,
+      "learning_rate": 0.0006500094955735401,
+      "loss": 42.1452880859375,
+      "step": 18400
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.189237117767334,
+      "learning_rate": 0.0006315657475322411,
+      "loss": 42.422060546875,
+      "step": 18500
+    },
+    {
+      "epoch": 0.744,
+      "grad_norm": 1.5588538646697998,
+      "learning_rate": 0.0006133382640976061,
+      "loss": 42.59294921875,
+      "step": 18600
+    },
+    {
+      "epoch": 0.748,
+      "grad_norm": 1.2961610555648804,
+      "learning_rate": 0.0005953299259045865,
+      "loss": 42.5683740234375,
+      "step": 18700
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 1.513845682144165,
+      "learning_rate": 0.000577543578954858,
+      "loss": 42.31896484375,
+      "step": 18800
+    },
+    {
+      "epoch": 0.756,
+      "grad_norm": 1.0572335720062256,
+      "learning_rate": 0.0005599820341670454,
+      "loss": 42.3233642578125,
+      "step": 18900
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.4302053451538086,
+      "learning_rate": 0.0005426480669324906,
+      "loss": 42.2752880859375,
+      "step": 19000
+    },
+    {
+      "epoch": 0.76,
+      "eval_accuracy": 0.22522482893450635,
+      "eval_loss": 42.213226318359375,
+      "eval_runtime": 7.0911,
+      "eval_samples_per_second": 17.628,
+      "eval_steps_per_second": 0.564,
+      "step": 19000
+    },
+    {
+      "epoch": 0.764,
+      "grad_norm": 1.4170910120010376,
+      "learning_rate": 0.0005255444166766354,
+      "loss": 42.50333984375,
+      "step": 19100
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 1.3892245292663574,
+      "learning_rate": 0.0005086737864260862,
+      "loss": 42.474443359375,
+      "step": 19200
+    },
+    {
+      "epoch": 0.772,
+      "grad_norm": 1.5735739469528198,
+      "learning_rate": 0.0004920388423814364,
+      "loss": 42.25490234375,
+      "step": 19300
+    },
+    {
+      "epoch": 0.776,
+      "grad_norm": 1.2609901428222656,
+      "learning_rate": 0.0004756422134959031,
+      "loss": 42.3439208984375,
+      "step": 19400
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.1414227485656738,
+      "learning_rate": 0.00045948649105985397,
+      "loss": 42.31787109375,
+      "step": 19500
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 1.301095962524414,
+      "learning_rate": 0.0004435742282912836,
+      "loss": 42.43177734375,
+      "step": 19600
+    },
+    {
+      "epoch": 0.788,
+      "grad_norm": 1.1665655374526978,
+      "learning_rate": 0.0004279079399323087,
+      "loss": 42.386767578125,
+      "step": 19700
+    },
+    {
+      "epoch": 0.792,
+      "grad_norm": 1.5682238340377808,
+      "learning_rate": 0.0004124901018517433,
+      "loss": 42.2175439453125,
+      "step": 19800
+    },
+    {
+      "epoch": 0.796,
+      "grad_norm": 1.259811520576477,
+      "learning_rate": 0.00039732315065381754,
+      "loss": 42.252421875,
+      "step": 19900
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.8927878141403198,
+      "learning_rate": 0.00038240948329310156,
+      "loss": 42.2313232421875,
+      "step": 20000
+    },
+    {
+      "epoch": 0.8,
+      "eval_accuracy": 0.2259481915933529,
+      "eval_loss": 42.14704895019531,
+      "eval_runtime": 6.8564,
+      "eval_samples_per_second": 18.231,
+      "eval_steps_per_second": 0.583,
+      "step": 20000
     }
   ],
   "logging_steps": 100,