Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:168f9e26cab3560df5e151718dbe310dc4b0fb9724a790bfeec287a1730c788e
+oid sha256:7bfb0681cf264d0d6828df272d9cfd1dbd06f5e0bc775c0d17ff8a5b3706ce03
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bd410d19429c7de65f4f848e60d10a7e206e0ff7f2562dda5f2ac51d2c2df72
+oid sha256:71f46414575b6d899f6936e64c869f64493ad98aeec78f3bdb0211772ed0f522
 size 166439638

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:359faa112250855040038f51482d8548da67710f542988377b4353399b7e2fd2
+oid sha256:43800b050359a981bd6e05898b883373851a14e947762809d83209bbb5d177c2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99fc9c0ec571f76cf9b6d1229601c5173899cd18104e487c5627f5f4c56c6e8a
+oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0031795491399319578,
+  "epoch": 0.0063590982798639156,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 6.515,
       "eval_steps_per_second": 3.258,
       "step": 25
+    },
+    {
+      "epoch": 0.0033067311055292358,
+      "grad_norm": 2.405796766281128,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 1.6712,
+      "step": 26
+    },
+    {
+      "epoch": 0.003433913071126514,
+      "grad_norm": 2.1344990730285645,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.657,
+      "step": 27
+    },
+    {
+      "epoch": 0.0035610950367237926,
+      "grad_norm": 3.931316375732422,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 1.7584,
+      "step": 28
+    },
+    {
+      "epoch": 0.003688277002321071,
+      "grad_norm": 2.662752628326416,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 1.605,
+      "step": 29
+    },
+    {
+      "epoch": 0.003815458967918349,
+      "grad_norm": 3.1903748512268066,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.6863,
+      "step": 30
+    },
+    {
+      "epoch": 0.0039426409335156275,
+      "grad_norm": 2.342129945755005,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 1.5341,
+      "step": 31
+    },
+    {
+      "epoch": 0.0040698228991129055,
+      "grad_norm": 2.9486243724823,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 1.6403,
+      "step": 32
+    },
+    {
+      "epoch": 0.004197004864710184,
+      "grad_norm": 2.807129383087158,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 1.6695,
+      "step": 33
+    },
+    {
+      "epoch": 0.004324186830307462,
+      "grad_norm": 2.300341844558716,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 1.5375,
+      "step": 34
+    },
+    {
+      "epoch": 0.00445136879590474,
+      "grad_norm": 5.008623123168945,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 1.7217,
+      "step": 35
+    },
+    {
+      "epoch": 0.004578550761502019,
+      "grad_norm": 3.538121461868286,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 1.6573,
+      "step": 36
+    },
+    {
+      "epoch": 0.004705732727099297,
+      "grad_norm": 2.3192837238311768,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 1.4853,
+      "step": 37
+    },
+    {
+      "epoch": 0.004832914692696575,
+      "grad_norm": 2.5325701236724854,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 1.5451,
+      "step": 38
+    },
+    {
+      "epoch": 0.004960096658293854,
+      "grad_norm": 2.0213067531585693,
+      "learning_rate": 5e-05,
+      "loss": 1.6081,
+      "step": 39
+    },
+    {
+      "epoch": 0.005087278623891132,
+      "grad_norm": 3.6637330055236816,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 1.7933,
+      "step": 40
+    },
+    {
+      "epoch": 0.005214460589488411,
+      "grad_norm": 2.7776637077331543,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 1.4603,
+      "step": 41
+    },
+    {
+      "epoch": 0.005341642555085689,
+      "grad_norm": 3.7768895626068115,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.6809,
+      "step": 42
+    },
+    {
+      "epoch": 0.005468824520682967,
+      "grad_norm": 3.5375547409057617,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.6731,
+      "step": 43
+    },
+    {
+      "epoch": 0.005596006486280246,
+      "grad_norm": 2.548534393310547,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 1.6962,
+      "step": 44
+    },
+    {
+      "epoch": 0.005723188451877524,
+      "grad_norm": 1.7797907590866089,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.6327,
+      "step": 45
+    },
+    {
+      "epoch": 0.005850370417474802,
+      "grad_norm": 1.6917822360992432,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 1.543,
+      "step": 46
+    },
+    {
+      "epoch": 0.005977552383072081,
+      "grad_norm": 2.2675538063049316,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 1.6209,
+      "step": 47
+    },
+    {
+      "epoch": 0.006104734348669359,
+      "grad_norm": 1.9940866231918335,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.5505,
+      "step": 48
+    },
+    {
+      "epoch": 0.006231916314266637,
+      "grad_norm": 1.4850102663040161,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 1.6082,
+      "step": 49
+    },
+    {
+      "epoch": 0.0063590982798639156,
+      "grad_norm": 1.984756350517273,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 1.6368,
+      "step": 50
+    },
+    {
+      "epoch": 0.0063590982798639156,
+      "eval_loss": 1.5464518070220947,
+      "eval_runtime": 1017.6554,
+      "eval_samples_per_second": 6.507,
+      "eval_steps_per_second": 3.254,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.00529829052416e+16,
+  "total_flos": 2.01059658104832e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null