Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bbd20d01f1ae750ec62973dfc211e97fa351555ba83196874f6da3a28b84958
+oid sha256:60eadddc9cdc6c3d34399c3aee0728f71486796d5fa497f2b2ec773220eb94d2
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9704f7ecd49aadfb985aa2827216054a474b15d283c8599f307bb782b1e45631
+oid sha256:424eec27786b4ccf5c884b553f5900543a0ba5a7d42c33b972de41605732cfa1
 size 148053627

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:718a0f3db00824213036a2c0441849791319b7d9cf189065873bb26a7020738e
+oid sha256:363c5df1543d2c82b2f13164f35bdd0367ceb32e7fa1b2f67c19df073a08b17b
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d058f6eb40c5a033dfcf02497fe0985a6e27999364c25714f6c2b2d7a336dc21
+oid sha256:9aee271141ab610b95fde470ef517f2ca73982be844feca339433f8632bdc1ef
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4884004884004884,
+  "epoch": 0.9768009768009768,
   "eval_steps": 50,
-  "global_step": 200,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -180,6 +180,178 @@
       "eval_samples_per_second": 1.171,
       "eval_steps_per_second": 1.171,
       "step": 200
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 0.8788589239120483,
+      "learning_rate": 5.700080724843147e-05,
+      "loss": 0.5496622562408447,
+      "step": 210
+    },
+    {
+      "epoch": 0.5372405372405372,
+      "grad_norm": 1.0257195234298706,
+      "learning_rate": 5.2765573307992036e-05,
+      "loss": 0.7461658000946045,
+      "step": 220
+    },
+    {
+      "epoch": 0.5616605616605617,
+      "grad_norm": 1.6746125221252441,
+      "learning_rate": 4.851030526738321e-05,
+      "loss": 0.5698539733886718,
+      "step": 230
+    },
+    {
+      "epoch": 0.5860805860805861,
+      "grad_norm": 0.8949107527732849,
+      "learning_rate": 4.4265828730079987e-05,
+      "loss": 0.5721668243408203,
+      "step": 240
+    },
+    {
+      "epoch": 0.6105006105006106,
+      "grad_norm": 2.384493350982666,
+      "learning_rate": 4.0062891124787e-05,
+      "loss": 0.7134846687316895,
+      "step": 250
+    },
+    {
+      "epoch": 0.6105006105006106,
+      "eval_loss": 0.36719319224357605,
+      "eval_runtime": 155.0828,
+      "eval_samples_per_second": 1.174,
+      "eval_steps_per_second": 1.174,
+      "step": 250
+    },
+    {
+      "epoch": 0.6349206349206349,
+      "grad_norm": 1.2632209062576294,
+      "learning_rate": 3.5931938967872766e-05,
+      "loss": 0.7118762969970703,
+      "step": 260
+    },
+    {
+      "epoch": 0.6593406593406593,
+      "grad_norm": 1.3680095672607422,
+      "learning_rate": 3.1902897305644095e-05,
+      "loss": 0.8658300399780273,
+      "step": 270
+    },
+    {
+      "epoch": 0.6837606837606838,
+      "grad_norm": 1.2788431644439697,
+      "learning_rate": 2.8004952934203838e-05,
+      "loss": 0.7101179122924804,
+      "step": 280
+    },
+    {
+      "epoch": 0.7081807081807082,
+      "grad_norm": 1.044674277305603,
+      "learning_rate": 2.4266342967269552e-05,
+      "loss": 0.5662980079650879,
+      "step": 290
+    },
+    {
+      "epoch": 0.7326007326007326,
+      "grad_norm": 1.589475154876709,
+      "learning_rate": 2.071415028359026e-05,
+      "loss": 0.5755983352661133,
+      "step": 300
+    },
+    {
+      "epoch": 0.7326007326007326,
+      "eval_loss": 0.355652779340744,
+      "eval_runtime": 155.57,
+      "eval_samples_per_second": 1.17,
+      "eval_steps_per_second": 1.17,
+      "step": 300
+    },
+    {
+      "epoch": 0.757020757020757,
+      "grad_norm": 1.370431900024414,
+      "learning_rate": 1.7374107335760936e-05,
+      "loss": 0.539859390258789,
+      "step": 310
+    },
+    {
+      "epoch": 0.7814407814407814,
+      "grad_norm": 0.995492160320282,
+      "learning_rate": 1.427040974166427e-05,
+      "loss": 0.2917079210281372,
+      "step": 320
+    },
+    {
+      "epoch": 0.8058608058608059,
+      "grad_norm": 1.1896394491195679,
+      "learning_rate": 1.1425541008902851e-05,
+      "loss": 0.7617981433868408,
+      "step": 330
+    },
+    {
+      "epoch": 0.8302808302808303,
+      "grad_norm": 2.3315072059631348,
+      "learning_rate": 8.860109661935674e-06,
+      "loss": 0.6248091697692871,
+      "step": 340
+    },
+    {
+      "epoch": 0.8547008547008547,
+      "grad_norm": 0.6425564885139465,
+      "learning_rate": 6.592699951787362e-06,
+      "loss": 0.4457353115081787,
+      "step": 350
+    },
+    {
+      "epoch": 0.8547008547008547,
+      "eval_loss": 0.35156095027923584,
+      "eval_runtime": 155.323,
+      "eval_samples_per_second": 1.172,
+      "eval_steps_per_second": 1.172,
+      "step": 350
+    },
+    {
+      "epoch": 0.8791208791208791,
+      "grad_norm": 1.164421796798706,
+      "learning_rate": 4.639737229804403e-06,
+      "loss": 0.36368584632873535,
+      "step": 360
+    },
+    {
+      "epoch": 0.9035409035409036,
+      "grad_norm": 1.071614146232605,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.5256676197052002,
+      "step": 370
+    },
+    {
+      "epoch": 0.927960927960928,
+      "grad_norm": 0.6991368532180786,
+      "learning_rate": 1.7313622368738014e-06,
+      "loss": 0.5124877452850342,
+      "step": 380
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 1.053227186203003,
+      "learning_rate": 7.970185363271431e-07,
+      "loss": 0.444692325592041,
+      "step": 390
+    },
+    {
+      "epoch": 0.9768009768009768,
+      "grad_norm": 1.5848822593688965,
+      "learning_rate": 2.1910634183644474e-07,
+      "loss": 0.5859388828277587,
+      "step": 400
+    },
+    {
+      "epoch": 0.9768009768009768,
+      "eval_loss": 0.3502028286457062,
+      "eval_runtime": 155.3968,
+      "eval_samples_per_second": 1.171,
+      "eval_steps_per_second": 1.171,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -199,7 +371,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3031079475757056.0,
+  "total_flos": 6159172374405120.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null