Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99d74bb1fbb17031b35623731de0a0934c646d3320ce13014e16f7fc7a3236e8
+oid sha256:bb4d00d3244fb53b7bed60bed31993422c378ab54bc8c8cb435149e1da7f6d25
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0159db15e3ebf5c8ea267dfcf9bb0e08171c9fa6704e56c7592b237bc11ed23
+oid sha256:b41af6b3b404b086e4053cfe2dd8df3293781080e77fbcc527f8bb8f324fb744
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70c8b97d8faf0007ec0b1ef24927ee6f5878bdf1348cf23ccc1f71d991209619
+oid sha256:e7aa0d0e67365fdc49701f7b2fac3d548c531ebecfe193942b41511ef17685b5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f7e91af1a79d7676619e959cc4b5dde54a9e2ec825d24c1c34fe5387a27894f
+oid sha256:d914dc409ae93ac75985631a9974025ebaa397f621307eef226e7d6e1076a1f6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0036999352511331053,
+  "epoch": 0.007399870502266211,
   "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": 21.689,
       "eval_steps_per_second": 10.845,
       "step": 25
+    },
+    {
+      "epoch": 0.0038479326611784294,
+      "grad_norm": 6.708371639251709,
+      "learning_rate": 0.0001537299608346824,
+      "loss": 2.0388,
+      "step": 26
+    },
+    {
+      "epoch": 0.003995930071223753,
+      "grad_norm": 5.384842395782471,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.7815,
+      "step": 27
+    },
+    {
+      "epoch": 0.004143927481269078,
+      "grad_norm": 5.319408416748047,
+      "learning_rate": 0.00014617486132350343,
+      "loss": 1.769,
+      "step": 28
+    },
+    {
+      "epoch": 0.004291924891314402,
+      "grad_norm": 5.727357387542725,
+      "learning_rate": 0.00014226182617406996,
+      "loss": 2.3294,
+      "step": 29
+    },
+    {
+      "epoch": 0.004439922301359726,
+      "grad_norm": 4.128015518188477,
+      "learning_rate": 0.000138268343236509,
+      "loss": 2.114,
+      "step": 30
+    },
+    {
+      "epoch": 0.0045879197114050505,
+      "grad_norm": 4.526007175445557,
+      "learning_rate": 0.00013420201433256689,
+      "loss": 1.9098,
+      "step": 31
+    },
+    {
+      "epoch": 0.004735917121450375,
+      "grad_norm": 4.137485504150391,
+      "learning_rate": 0.00013007057995042732,
+      "loss": 1.9011,
+      "step": 32
+    },
+    {
+      "epoch": 0.004883914531495699,
+      "grad_norm": 3.771566390991211,
+      "learning_rate": 0.00012588190451025207,
+      "loss": 1.6609,
+      "step": 33
+    },
+    {
+      "epoch": 0.005031911941541023,
+      "grad_norm": 3.3007614612579346,
+      "learning_rate": 0.00012164396139381029,
+      "loss": 1.6353,
+      "step": 34
+    },
+    {
+      "epoch": 0.005179909351586348,
+      "grad_norm": 4.597551345825195,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 2.11,
+      "step": 35
+    },
+    {
+      "epoch": 0.005327906761631671,
+      "grad_norm": 3.7648379802703857,
+      "learning_rate": 0.00011305261922200519,
+      "loss": 1.7404,
+      "step": 36
+    },
+    {
+      "epoch": 0.005475904171676996,
+      "grad_norm": 5.169516086578369,
+      "learning_rate": 0.00010871557427476583,
+      "loss": 1.9993,
+      "step": 37
+    },
+    {
+      "epoch": 0.00562390158172232,
+      "grad_norm": 3.914263963699341,
+      "learning_rate": 0.00010436193873653361,
+      "loss": 1.9136,
+      "step": 38
+    },
+    {
+      "epoch": 0.005771898991767644,
+      "grad_norm": 3.3549132347106934,
+      "learning_rate": 0.0001,
+      "loss": 1.9494,
+      "step": 39
+    },
+    {
+      "epoch": 0.005919896401812968,
+      "grad_norm": 3.380098342895508,
+      "learning_rate": 9.563806126346642e-05,
+      "loss": 1.4687,
+      "step": 40
+    },
+    {
+      "epoch": 0.006067893811858293,
+      "grad_norm": 3.6071436405181885,
+      "learning_rate": 9.128442572523417e-05,
+      "loss": 1.7524,
+      "step": 41
+    },
+    {
+      "epoch": 0.0062158912219036164,
+      "grad_norm": 3.8395206928253174,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 1.7826,
+      "step": 42
+    },
+    {
+      "epoch": 0.006363888631948941,
+      "grad_norm": 3.7298543453216553,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 1.5537,
+      "step": 43
+    },
+    {
+      "epoch": 0.006511886041994265,
+      "grad_norm": 2.709172248840332,
+      "learning_rate": 7.835603860618972e-05,
+      "loss": 1.4122,
+      "step": 44
+    },
+    {
+      "epoch": 0.006659883452039589,
+      "grad_norm": 3.5382652282714844,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 1.849,
+      "step": 45
+    },
+    {
+      "epoch": 0.0068078808620849135,
+      "grad_norm": 3.254901170730591,
+      "learning_rate": 6.992942004957271e-05,
+      "loss": 1.6019,
+      "step": 46
+    },
+    {
+      "epoch": 0.006955878272130238,
+      "grad_norm": 5.000037670135498,
+      "learning_rate": 6.579798566743314e-05,
+      "loss": 1.996,
+      "step": 47
+    },
+    {
+      "epoch": 0.007103875682175562,
+      "grad_norm": 4.309709548950195,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 1.955,
+      "step": 48
+    },
+    {
+      "epoch": 0.007251873092220886,
+      "grad_norm": 4.277580261230469,
+      "learning_rate": 5.773817382593008e-05,
+      "loss": 1.7035,
+      "step": 49
+    },
+    {
+      "epoch": 0.007399870502266211,
+      "grad_norm": 2.9081766605377197,
+      "learning_rate": 5.382513867649663e-05,
+      "loss": 1.6438,
+      "step": 50
+    },
+    {
+      "epoch": 0.007399870502266211,
+      "eval_loss": 1.7859166860580444,
+      "eval_runtime": 262.3802,
+      "eval_samples_per_second": 21.686,
+      "eval_steps_per_second": 10.843,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5146843860172800.0,
+  "total_flos": 1.02936877203456e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null