Training in progress, step 18000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bef8568f96238a5b06f1b8201e0457a70533d075df2bb2744dfc21292e3ccee
+oid sha256:6a028a1582a4cdcab16eaa810c62dd5a92cfee0e12fcbc95547030d75ad6054d
 size 529337896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae466236a6b73341348524a8c14751f290085bd91d0879fd65d99038fe1a8df2
+oid sha256:b858949970024f5c82faf265e8d537dcfb88c2afcfff507a59916042fcf45114
 size 871247243

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3094f03eb1b7ca78cd75cfac64b3e97454e2450697d516b4311c6fe7ecad5494
+oid sha256:68fb3c6eb1526b3dbce1657a61fe1a7b19cc45a43a389d7261b3c6e19d29ffb1
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:262c03618811dd08c5542ed422cb02749751837f2f34131505a0ce5eebb179de
+oid sha256:b1ec2a8f346b82ffd82d9deb224e5a88186c4ed8b6b71f4b78140ea3176eb4f4
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.32,
+  "epoch": 0.36,
   "eval_steps": 1000,
-  "global_step": 16000,
+  "global_step": 18000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1272,6 +1272,164 @@
       "eval_samples_per_second": 80.808,
       "eval_steps_per_second": 0.646,
       "step": 16000
+    },
+    {
+      "epoch": 0.322,
+      "grad_norm": 0.207662433385849,
+      "learning_rate": 0.001622063064240765,
+      "loss": 3.4661,
+      "step": 16100
+    },
+    {
+      "epoch": 0.324,
+      "grad_norm": 0.14697088301181793,
+      "learning_rate": 0.001616871046323253,
+      "loss": 3.4735,
+      "step": 16200
+    },
+    {
+      "epoch": 0.326,
+      "grad_norm": 0.16137182712554932,
+      "learning_rate": 0.0016116520444677894,
+      "loss": 3.451,
+      "step": 16300
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 0.1839095950126648,
+      "learning_rate": 0.001606406286970423,
+      "loss": 3.4646,
+      "step": 16400
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.1534615308046341,
+      "learning_rate": 0.0016011340032975805,
+      "loss": 3.4666,
+      "step": 16500
+    },
+    {
+      "epoch": 0.332,
+      "grad_norm": 0.15798258781433105,
+      "learning_rate": 0.00159583542407603,
+      "loss": 3.4418,
+      "step": 16600
+    },
+    {
+      "epoch": 0.334,
+      "grad_norm": 0.13258863985538483,
+      "learning_rate": 0.001590510781082791,
+      "loss": 3.4641,
+      "step": 16700
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 0.14669552445411682,
+      "learning_rate": 0.001585160307234998,
+      "loss": 3.4667,
+      "step": 16800
+    },
+    {
+      "epoch": 0.338,
+      "grad_norm": 0.15622150897979736,
+      "learning_rate": 0.00157978423657971,
+      "loss": 3.439,
+      "step": 16900
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.18012835085391998,
+      "learning_rate": 0.0015743828042836733,
+      "loss": 3.4512,
+      "step": 17000
+    },
+    {
+      "epoch": 0.34,
+      "eval_accuracy": 0.3706555772994129,
+      "eval_loss": 3.4220447540283203,
+      "eval_runtime": 21.6548,
+      "eval_samples_per_second": 46.179,
+      "eval_steps_per_second": 0.369,
+      "step": 17000
+    },
+    {
+      "epoch": 0.342,
+      "grad_norm": 0.143183171749115,
+      "learning_rate": 0.0015689562466230352,
+      "loss": 3.4531,
+      "step": 17100
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 0.15830625593662262,
+      "learning_rate": 0.0015635048009730072,
+      "loss": 3.4425,
+      "step": 17200
+    },
+    {
+      "epoch": 0.346,
+      "grad_norm": 0.1351785659790039,
+      "learning_rate": 0.0015580287057974822,
+      "loss": 3.4491,
+      "step": 17300
+    },
+    {
+      "epoch": 0.348,
+      "grad_norm": 0.1572723239660263,
+      "learning_rate": 0.0015525282006386032,
+      "loss": 3.4329,
+      "step": 17400
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.16905032098293304,
+      "learning_rate": 0.0015470035261062852,
+      "loss": 3.4457,
+      "step": 17500
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.1542733907699585,
+      "learning_rate": 0.0015414549238676899,
+      "loss": 3.4466,
+      "step": 17600
+    },
+    {
+      "epoch": 0.354,
+      "grad_norm": 0.17319922149181366,
+      "learning_rate": 0.0015358826366366532,
+      "loss": 3.4311,
+      "step": 17700
+    },
+    {
+      "epoch": 0.356,
+      "grad_norm": 0.17198143899440765,
+      "learning_rate": 0.0015302869081630717,
+      "loss": 3.4453,
+      "step": 17800
+    },
+    {
+      "epoch": 0.358,
+      "grad_norm": 0.15461337566375732,
+      "learning_rate": 0.0015246679832222353,
+      "loss": 3.4539,
+      "step": 17900
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.15917198359966278,
+      "learning_rate": 0.0015190261076041245,
+      "loss": 3.4188,
+      "step": 18000
+    },
+    {
+      "epoch": 0.36,
+      "eval_accuracy": 0.3723365949119374,
+      "eval_loss": 3.4081637859344482,
+      "eval_runtime": 12.6994,
+      "eval_samples_per_second": 78.744,
+      "eval_steps_per_second": 0.63,
+      "step": 18000
     }
   ],
   "logging_steps": 100,