Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65936f8dc813f583517d6cf8914663de05d0313fba665db0793fe4dad59001d0
+oid sha256:b851e56fe1e20386cb6f188985747e344f534e5016134dacc6163f3300160c86
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0ff4751872c7ba8e162f8f9679c4f58bc1a992a8c9caa7863c8aae065809640
+oid sha256:8f78fc6e843842422938caa603e8f2e4bd002d610acbd7a33f8ce72652bf3a25
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad06d6575ee59e74108d9c4f8816f7974dab7778222a92e7eb26ff08be09916f
+oid sha256:906a9e6400187d6899fb20f1e1e70a8f191fa21191db7d4f21aaf6ccce3ae8ad
 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": 0.005622399640166423,
+  "epoch": 0.011244799280332845,
   "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": 0.0197,
       "step": 25
+    },
+    {
+      "epoch": 0.00584729562577308,
+      "grad_norm": 0.18810567259788513,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.0156,
+      "step": 26
+    },
+    {
+      "epoch": 0.006072191611379737,
+      "grad_norm": 0.3696419298648834,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 0.0168,
+      "step": 27
+    },
+    {
+      "epoch": 0.006072191611379737,
+      "eval_loss": 0.01646805927157402,
+      "eval_runtime": 821.6288,
+      "eval_samples_per_second": 4.558,
+      "eval_steps_per_second": 0.571,
+      "step": 27
+    },
+    {
+      "epoch": 0.006297087596986394,
+      "grad_norm": 0.25218066573143005,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.0093,
+      "step": 28
+    },
+    {
+      "epoch": 0.0065219835825930505,
+      "grad_norm": 0.34651580452919006,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 0.0176,
+      "step": 29
+    },
+    {
+      "epoch": 0.006746879568199708,
+      "grad_norm": 0.36292922496795654,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.0124,
+      "step": 30
+    },
+    {
+      "epoch": 0.006971775553806365,
+      "grad_norm": 0.19089706242084503,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 0.0203,
+      "step": 31
+    },
+    {
+      "epoch": 0.007196671539413021,
+      "grad_norm": 0.24353894591331482,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.0101,
+      "step": 32
+    },
+    {
+      "epoch": 0.007421567525019678,
+      "grad_norm": 0.23627233505249023,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.0179,
+      "step": 33
+    },
+    {
+      "epoch": 0.0076464635106263355,
+      "grad_norm": 0.4310121238231659,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.0214,
+      "step": 34
+    },
+    {
+      "epoch": 0.007871359496232992,
+      "grad_norm": 0.227275088429451,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 0.0098,
+      "step": 35
+    },
+    {
+      "epoch": 0.00809625548183965,
+      "grad_norm": 0.2399313896894455,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.0111,
+      "step": 36
+    },
+    {
+      "epoch": 0.00809625548183965,
+      "eval_loss": 0.011674784123897552,
+      "eval_runtime": 821.5999,
+      "eval_samples_per_second": 4.558,
+      "eval_steps_per_second": 0.571,
+      "step": 36
+    },
+    {
+      "epoch": 0.008321151467446306,
+      "grad_norm": 0.1582072526216507,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.0038,
+      "step": 37
+    },
+    {
+      "epoch": 0.008546047453052963,
+      "grad_norm": 0.24019911885261536,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.0069,
+      "step": 38
+    },
+    {
+      "epoch": 0.00877094343865962,
+      "grad_norm": 0.20569612085819244,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.0065,
+      "step": 39
+    },
+    {
+      "epoch": 0.008995839424266277,
+      "grad_norm": 0.30835479497909546,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0073,
+      "step": 40
+    },
+    {
+      "epoch": 0.009220735409872933,
+      "grad_norm": 0.25597208738327026,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 0.0127,
+      "step": 41
+    },
+    {
+      "epoch": 0.009445631395479591,
+      "grad_norm": 0.09658183157444,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.0047,
+      "step": 42
+    },
+    {
+      "epoch": 0.009670527381086248,
+      "grad_norm": 0.20138397812843323,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.0162,
+      "step": 43
+    },
+    {
+      "epoch": 0.009895423366692904,
+      "grad_norm": 0.2869853377342224,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 0.0074,
+      "step": 44
+    },
+    {
+      "epoch": 0.010120319352299562,
+      "grad_norm": 0.3238297700881958,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.022,
+      "step": 45
+    },
+    {
+      "epoch": 0.010120319352299562,
+      "eval_loss": 0.012101165018975735,
+      "eval_runtime": 821.4174,
+      "eval_samples_per_second": 4.559,
+      "eval_steps_per_second": 0.571,
+      "step": 45
+    },
+    {
+      "epoch": 0.010345215337906218,
+      "grad_norm": 0.1724397987127304,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0064,
+      "step": 46
+    },
+    {
+      "epoch": 0.010570111323512875,
+      "grad_norm": 0.3781624138355255,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 0.0113,
+      "step": 47
+    },
+    {
+      "epoch": 0.010795007309119533,
+      "grad_norm": 0.17849580943584442,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.0067,
+      "step": 48
+    },
+    {
+      "epoch": 0.011019903294726189,
+      "grad_norm": 0.19034115970134735,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.006,
+      "step": 49
+    },
+    {
+      "epoch": 0.011244799280332845,
+      "grad_norm": 0.5638530254364014,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.019,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.672342053624218e+16,
+  "total_flos": 7.344684107248435e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null