Training in progress, step 16000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75ba0b7a63e25df56e29b8b1f4ae481007e80d1cbde28fce2cb4ed43b8b03d7f
+oid sha256:47d722dd48084253e30edcdf2b9c7c11a74b1b8db5e9fdd03e44b6b8722f9fe4
 size 386379

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbeaa2e3e7f8d9416a2aff04c3f41cb4a4fbb000165b5f4b0f96556dc4f75345
+oid sha256:0cc6390d79743c341e54409953964ed7435ac3ae79f72a9c0b2a61d5bfa4014e
 size 1540661735

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9fd33b0410b29f1c36e49a77f8193ae40be73acb6bc07f4d04bbf2f5a48485d
+oid sha256:0dcdb042e82db2feeaf162fa2c2cb05728354faf3a44aadef50aea6b23b1d50f
 size 14469

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b178b887d0edcf498486b28f0a4fa9660c9ddb3e2c9439c66b45fe0ea200cf9
+oid sha256:d2e4e7d621db7965ac0d0149ed05a3a6f4a8f4d9ee38752c9f0d6d1b7c145e73
 size 14469

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ffac77d94e352efd69a7a08457843666ef6e11840940a75b79aa309c60b093e
+oid sha256:508d87a75853c2525702937f0b29e20460fd10ed4559a13863d962226c0b64f6
 size 14469

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4793c6e47d0cc17f59428134402f504910de29559f3b25e714f01f8e2a921fa
+oid sha256:e58646a1d294f0200655cb40f9e0932383e71653f6e1881d789b0865a448d379
 size 14469

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9efd33673a3b22874e09faf8887dab4cf78fa75d3ae16ca5b96616a9ee4f34e
+oid sha256:12049670dc229efa48859b2adaa7bab30026005b65de953934912e8618042ff1
 size 14469

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b9d2fad89c5a6f1c349b9744f74a33ddbea84929474a3b07af7854b2cb5b948
+oid sha256:73cb0f9f2044cff462979fc73428559a94af22b0f0ccb7178a43a2c54c6bd489
 size 14469

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:366d6a2b5441cba1b4e3c949688263d18faed9ec24ff34e65646b84a37cd876f
+oid sha256:5d5d3e29a67a07d0732605625beeef4e37c068d24accf9b8ee268df48cbfb581
 size 14469

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:398af4c0b1b16509a9dc98b6f538417e0edc1b874f91676dd82e779576f34c02
+oid sha256:a884f7fff4609aa43572eb70b86f31ae319b33f5de3caf0a4442a33602de76c4
 size 14469

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e95cc046a3497bc828055e3c8ba24ab45d17dc68b972f4cff7ec411d034a7f1e
+oid sha256:5763ed75e068d243df01e54fda7497cd86e57ed3e9ed4dadca20a2d87ccb859e
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.56,
+  "epoch": 0.64,
   "eval_steps": 1000,
-  "global_step": 14000,
+  "global_step": 16000,
   "is_hyper_param_search": false,
   "is_local_process_zero": false,
   "is_world_process_zero": true,
@@ -1114,6 +1114,164 @@
       "eval_samples_per_second": 17.636,
       "eval_steps_per_second": 0.564,
       "step": 14000
+    },
+    {
+      "epoch": 0.564,
+      "grad_norm": 2.029331684112549,
+      "learning_rate": 0.0016019006351205318,
+      "loss": 43.2043701171875,
+      "step": 14100
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 2.470975399017334,
+      "learning_rate": 0.0015772930656726884,
+      "loss": 43.1994921875,
+      "step": 14200
+    },
+    {
+      "epoch": 0.572,
+      "grad_norm": 1.9896589517593384,
+      "learning_rate": 0.0015527522999815634,
+      "loss": 42.8731396484375,
+      "step": 14300
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 2.9005286693573,
+      "learning_rate": 0.001528282216420582,
+      "loss": 42.8190380859375,
+      "step": 14400
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 2.300215244293213,
+      "learning_rate": 0.0015038866821927073,
+      "loss": 42.9506982421875,
+      "step": 14500
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 1.927196979522705,
+      "learning_rate": 0.0014795695527192762,
+      "loss": 42.97125,
+      "step": 14600
+    },
+    {
+      "epoch": 0.588,
+      "grad_norm": 1.9869160652160645,
+      "learning_rate": 0.001455334671030695,
+      "loss": 43.0368505859375,
+      "step": 14700
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 2.05895733833313,
+      "learning_rate": 0.0014311858671590934,
+      "loss": 42.886181640625,
+      "step": 14800
+    },
+    {
+      "epoch": 0.596,
+      "grad_norm": 2.5150656700134277,
+      "learning_rate": 0.0014071269575330373,
+      "loss": 42.9019677734375,
+      "step": 14900
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.3601467609405518,
+      "learning_rate": 0.0013831617443743852,
+      "loss": 42.6784130859375,
+      "step": 15000
+    },
+    {
+      "epoch": 0.6,
+      "eval_accuracy": 0.22081524926686216,
+      "eval_loss": 42.696502685546875,
+      "eval_runtime": 7.2547,
+      "eval_samples_per_second": 17.23,
+      "eval_steps_per_second": 0.551,
+      "step": 15000
+    },
+    {
+      "epoch": 0.604,
+      "grad_norm": 2.1606075763702393,
+      "learning_rate": 0.0013592940150973943,
+      "loss": 42.9130859375,
+      "step": 15100
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 2.021022319793701,
+      "learning_rate": 0.0013355275417101637,
+      "loss": 42.95048828125,
+      "step": 15200
+    },
+    {
+      "epoch": 0.612,
+      "grad_norm": 2.6041364669799805,
+      "learning_rate": 0.0013118660802185161,
+      "loss": 42.6790380859375,
+      "step": 15300
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 2.121518135070801,
+      "learning_rate": 0.0012883133700324026,
+      "loss": 42.72169921875,
+      "step": 15400
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.0749258995056152,
+      "learning_rate": 0.0012648731333749373,
+      "loss": 42.6244970703125,
+      "step": 15500
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 2.3933210372924805,
+      "learning_rate": 0.0012415490746941434,
+      "loss": 42.629208984375,
+      "step": 15600
+    },
+    {
+      "epoch": 0.628,
+      "grad_norm": 2.163004159927368,
+      "learning_rate": 0.0012183448800775084,
+      "loss": 42.9462548828125,
+      "step": 15700
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 1.9806509017944336,
+      "learning_rate": 0.0011952642166694445,
+      "loss": 42.9928662109375,
+      "step": 15800
+    },
+    {
+      "epoch": 0.636,
+      "grad_norm": 2.2631726264953613,
+      "learning_rate": 0.0011723107320917396,
+      "loss": 42.7688671875,
+      "step": 15900
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.2971158027648926,
+      "learning_rate": 0.0011494880538670915,
+      "loss": 42.37572265625,
+      "step": 16000
+    },
+    {
+      "epoch": 0.64,
+      "eval_accuracy": 0.2221368523949169,
+      "eval_loss": 42.538299560546875,
+      "eval_runtime": 7.2739,
+      "eval_samples_per_second": 17.185,
+      "eval_steps_per_second": 0.55,
+      "step": 16000
     }
   ],
   "logging_steps": 100,