Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:292cc69d8d37aa56ab0a7df4a77276443f48f4edc58181d10158fcd8776bc3e3
+oid sha256:2cc1a1217204e52fdad0e5f7e6d91124a346c39f556163756c296d1f2751a608
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0509590c5abafc4abcf6dac2cb90d0d84a601f5bfb08c5034aff2f51c5a88775
+oid sha256:96c6285fd972f63e6d1f9c9f03f912ba05da0e1233b2a10636760d6c23fe25d5
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25371f2e7128c95880901f05b110872026ee73ab8099b739fc1804690b170c47
+oid sha256:392d94d3acb0b66fb1c3dab39d3e9e44137c67f588e6391c4cd8effb0aa77252
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c931ece4da598a541d357f6c98f67481603252e193960022d37ddd49c584b1f
+oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002523722996163941,
+  "epoch": 0.005047445992327882,
   "eval_steps": 9,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -206,6 +206,205 @@
       "learning_rate": 9.330127018922194e-05,
       "loss": 2.1961,
       "step": 25
+    },
+    {
+      "epoch": 0.0026246719160104987,
+      "grad_norm": 0.279491662979126,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 2.1918,
+      "step": 26
+    },
+    {
+      "epoch": 0.0027256208358570565,
+      "grad_norm": 0.4121980369091034,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 2.1888,
+      "step": 27
+    },
+    {
+      "epoch": 0.0027256208358570565,
+      "eval_loss": 2.1801180839538574,
+      "eval_runtime": 837.0562,
+      "eval_samples_per_second": 9.966,
+      "eval_steps_per_second": 1.246,
+      "step": 27
+    },
+    {
+      "epoch": 0.002826569755703614,
+      "grad_norm": 0.2528911828994751,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 2.1625,
+      "step": 28
+    },
+    {
+      "epoch": 0.0029275186755501714,
+      "grad_norm": 0.30560562014579773,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 2.1744,
+      "step": 29
+    },
+    {
+      "epoch": 0.0030284675953967293,
+      "grad_norm": 0.5374148488044739,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 2.212,
+      "step": 30
+    },
+    {
+      "epoch": 0.0031294165152432867,
+      "grad_norm": 0.2979753911495209,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 2.161,
+      "step": 31
+    },
+    {
+      "epoch": 0.0032303654350898446,
+      "grad_norm": 0.23406262695789337,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 2.149,
+      "step": 32
+    },
+    {
+      "epoch": 0.003331314354936402,
+      "grad_norm": 0.28936153650283813,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 2.1734,
+      "step": 33
+    },
+    {
+      "epoch": 0.00343226327478296,
+      "grad_norm": 0.3578174412250519,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 2.193,
+      "step": 34
+    },
+    {
+      "epoch": 0.0035332121946295173,
+      "grad_norm": 0.33021020889282227,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 2.1804,
+      "step": 35
+    },
+    {
+      "epoch": 0.0036341611144760752,
+      "grad_norm": 0.2678793966770172,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 2.2016,
+      "step": 36
+    },
+    {
+      "epoch": 0.0036341611144760752,
+      "eval_loss": 2.1783008575439453,
+      "eval_runtime": 836.5111,
+      "eval_samples_per_second": 9.972,
+      "eval_steps_per_second": 1.247,
+      "step": 36
+    },
+    {
+      "epoch": 0.0037351100343226327,
+      "grad_norm": 0.285946249961853,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 2.1862,
+      "step": 37
+    },
+    {
+      "epoch": 0.0038360589541691905,
+      "grad_norm": 0.32445332407951355,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 2.1826,
+      "step": 38
+    },
+    {
+      "epoch": 0.003937007874015748,
+      "grad_norm": 0.33953049778938293,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 2.1831,
+      "step": 39
+    },
+    {
+      "epoch": 0.004037956793862305,
+      "grad_norm": 0.22985900938510895,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 2.1897,
+      "step": 40
+    },
+    {
+      "epoch": 0.004138905713708864,
+      "grad_norm": 0.22906559705734253,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 2.1724,
+      "step": 41
+    },
+    {
+      "epoch": 0.004239854633555421,
+      "grad_norm": 0.23222745954990387,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 2.1808,
+      "step": 42
+    },
+    {
+      "epoch": 0.004340803553401979,
+      "grad_norm": 0.2707752585411072,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 2.1431,
+      "step": 43
+    },
+    {
+      "epoch": 0.004441752473248536,
+      "grad_norm": 0.4225059449672699,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 2.1715,
+      "step": 44
+    },
+    {
+      "epoch": 0.0045427013930950935,
+      "grad_norm": 0.2372809201478958,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 2.159,
+      "step": 45
+    },
+    {
+      "epoch": 0.0045427013930950935,
+      "eval_loss": 2.1703410148620605,
+      "eval_runtime": 836.4728,
+      "eval_samples_per_second": 9.973,
+      "eval_steps_per_second": 1.247,
+      "step": 45
+    },
+    {
+      "epoch": 0.004643650312941652,
+      "grad_norm": 0.2771320641040802,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.1876,
+      "step": 46
+    },
+    {
+      "epoch": 0.004744599232788209,
+      "grad_norm": 0.25997450947761536,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 2.1687,
+      "step": 47
+    },
+    {
+      "epoch": 0.004845548152634767,
+      "grad_norm": 0.23976390063762665,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 2.1836,
+      "step": 48
+    },
+    {
+      "epoch": 0.004946497072481324,
+      "grad_norm": 0.23776023089885712,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 2.168,
+      "step": 49
+    },
+    {
+      "epoch": 0.005047445992327882,
+      "grad_norm": 0.2904040813446045,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 2.1617,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.561120808619213e+16,
+  "total_flos": 7.048051600392192e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null