Training in progress, step 14000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b8e8d3ec310b587a737b2ff1479785c95b383b0103a20c2616bcaa1b70cedfd
+oid sha256:75ba0b7a63e25df56e29b8b1f4ae481007e80d1cbde28fce2cb4ed43b8b03d7f
 size 386379

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af1c4c4789099e3f06b7040705745688787a84de28b3c92b707a08bf66acedd5
+oid sha256:bbeaa2e3e7f8d9416a2aff04c3f41cb4a4fbb000165b5f4b0f96556dc4f75345
 size 1540661735

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de97c976c1994a7f2b52cd661dd45e50f8c59ea7f29046e2b153d031a5329003
+oid sha256:b9fd33b0410b29f1c36e49a77f8193ae40be73acb6bc07f4d04bbf2f5a48485d
 size 14469

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:945dfe762c470357f0955a0e4fddcfadf68d636dfea2666def3fd34df1ab5189
+oid sha256:3b178b887d0edcf498486b28f0a4fa9660c9ddb3e2c9439c66b45fe0ea200cf9
 size 14469

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3883b9681a4e564010f0c080b9a5c164f6cfc69d29380b6cdfc7bd14e3061a6c
+oid sha256:3ffac77d94e352efd69a7a08457843666ef6e11840940a75b79aa309c60b093e
 size 14469

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bfa4cd8ff4ea106b4895cc38559e225da4381a514e25136b0ad798f67a76ec0
+oid sha256:a4793c6e47d0cc17f59428134402f504910de29559f3b25e714f01f8e2a921fa
 size 14469

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bd3539150b8b4416c1ef3e8435df0b2b18db72a3b53e80a325b1d948246653b
+oid sha256:b9efd33673a3b22874e09faf8887dab4cf78fa75d3ae16ca5b96616a9ee4f34e
 size 14469

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:414056302bb2c51030907ea288f267bbdafb5b349fed9bbe5df32046e41df462
+oid sha256:7b9d2fad89c5a6f1c349b9744f74a33ddbea84929474a3b07af7854b2cb5b948
 size 14469

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:217d507942f28f310e4eeed6bfba8d07fd2bb6dc167c4c4f66eda1c08b6318d6
+oid sha256:366d6a2b5441cba1b4e3c949688263d18faed9ec24ff34e65646b84a37cd876f
 size 14469

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06b43a58b72baf558b7e5624a89206c612752404e0e3755fa74aff6a8a856fea
+oid sha256:398af4c0b1b16509a9dc98b6f538417e0edc1b874f91676dd82e779576f34c02
 size 14469

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef456277f681db2c07f1ff63be489edd84235ae448b25e8872b7c6ddb3f68afb
+oid sha256:e95cc046a3497bc828055e3c8ba24ab45d17dc68b972f4cff7ec411d034a7f1e
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.48,
+  "epoch": 0.56,
   "eval_steps": 1000,
-  "global_step": 12000,
+  "global_step": 14000,
   "is_hyper_param_search": false,
   "is_local_process_zero": false,
   "is_world_process_zero": true,
@@ -956,6 +956,164 @@
       "eval_samples_per_second": 16.508,
       "eval_steps_per_second": 0.528,
       "step": 12000
+    },
+    {
+      "epoch": 0.484,
+      "grad_norm": 3.012925148010254,
+      "learning_rate": 0.0021020354462549986,
+      "loss": 43.3377099609375,
+      "step": 12100
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 3.428558826446533,
+      "learning_rate": 0.0020769179888207967,
+      "loss": 43.5579638671875,
+      "step": 12200
+    },
+    {
+      "epoch": 0.492,
+      "grad_norm": 3.1122782230377197,
+      "learning_rate": 0.0020517883754218,
+      "loss": 43.4773828125,
+      "step": 12300
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 2.5048506259918213,
+      "learning_rate": 0.0020266505774917446,
+      "loss": 43.3037744140625,
+      "step": 12400
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.638044595718384,
+      "learning_rate": 0.0020015085677578355,
+      "loss": 43.562880859375,
+      "step": 12500
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 2.780961036682129,
+      "learning_rate": 0.0019763663196129006,
+      "loss": 43.3517138671875,
+      "step": 12600
+    },
+    {
+      "epoch": 0.508,
+      "grad_norm": 1.9473482370376587,
+      "learning_rate": 0.0019512278064874483,
+      "loss": 43.109091796875,
+      "step": 12700
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 3.174790143966675,
+      "learning_rate": 0.0019260970012217105,
+      "loss": 43.475107421875,
+      "step": 12800
+    },
+    {
+      "epoch": 0.516,
+      "grad_norm": 2.280482769012451,
+      "learning_rate": 0.001900977875437784,
+      "loss": 43.4238671875,
+      "step": 12900
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 3.096158266067505,
+      "learning_rate": 0.0018758743989119647,
+      "loss": 43.194453125,
+      "step": 13000
+    },
+    {
+      "epoch": 0.52,
+      "eval_accuracy": 0.21564809384164224,
+      "eval_loss": 43.14116668701172,
+      "eval_runtime": 6.8523,
+      "eval_samples_per_second": 18.242,
+      "eval_steps_per_second": 0.584,
+      "step": 13000
+    },
+    {
+      "epoch": 0.524,
+      "grad_norm": 2.7369933128356934,
+      "learning_rate": 0.0018507905389473706,
+      "loss": 43.233857421875,
+      "step": 13100
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 2.2296907901763916,
+      "learning_rate": 0.001825730259746958,
+      "loss": 43.15728515625,
+      "step": 13200
+    },
+    {
+      "epoch": 0.532,
+      "grad_norm": 3.018181324005127,
+      "learning_rate": 0.0018006975217870259,
+      "loss": 43.116005859375,
+      "step": 13300
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 2.055466890335083,
+      "learning_rate": 0.0017756962811913122,
+      "loss": 43.1440869140625,
+      "step": 13400
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 2.277271032333374,
+      "learning_rate": 0.0017507304891057722,
+      "loss": 43.4723193359375,
+      "step": 13500
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 2.3194973468780518,
+      "learning_rate": 0.001725804091074152,
+      "loss": 43.233828125,
+      "step": 13600
+    },
+    {
+      "epoch": 0.548,
+      "grad_norm": 2.0250515937805176,
+      "learning_rate": 0.0017009210264144388,
+      "loss": 43.008115234375,
+      "step": 13700
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 2.4250712394714355,
+      "learning_rate": 0.0016760852275963015,
+      "loss": 42.6800048828125,
+      "step": 13800
+    },
+    {
+      "epoch": 0.556,
+      "grad_norm": 1.7238541841506958,
+      "learning_rate": 0.0016513006196196098,
+      "loss": 42.93923828125,
+      "step": 13900
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.7167351245880127,
+      "learning_rate": 0.0016265711193941361,
+      "loss": 43.267294921875,
+      "step": 14000
+    },
+    {
+      "epoch": 0.56,
+      "eval_accuracy": 0.2188279569892473,
+      "eval_loss": 42.8851318359375,
+      "eval_runtime": 7.0878,
+      "eval_samples_per_second": 17.636,
+      "eval_steps_per_second": 0.564,
+      "step": 14000
     }
   ],
   "logging_steps": 100,