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:d8be482ca9f3ae4727232b6a5e40dc957e96ec3c3776de78d512fe65cef17567
+oid sha256:a4cf68ce1914731bf96616d872334d2cd38592198cb74ce32d05a2e0c9762456
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a73e8bcd13a359fb722ca88bf833834c75a1e0f6dbcf406cfa68d7933dc6d39
+oid sha256:7c5fe18352f8b3e5449e7e26a82e7908777de81afea653e379313e57c9a3eaf8
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9d8089d024ad79e3de1f48930b296c1210bcbde5032c19b971ff3470c299c24
+oid sha256:7c346df5b4b53ec580b3f72c8716c89357d7cb6ad6e4c4d8d524ee44930414ca
 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": 0.002052629418284823,
+  "epoch": 0.004105258836569646,
   "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": 1.194,
       "step": 25
+    },
+    {
+      "epoch": 0.0021347345950162157,
+      "grad_norm": 0.6608679294586182,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 1.8281,
+      "step": 26
+    },
+    {
+      "epoch": 0.0022168397717476085,
+      "grad_norm": 0.868128776550293,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 1.7768,
+      "step": 27
+    },
+    {
+      "epoch": 0.0022168397717476085,
+      "eval_loss": 1.5856971740722656,
+      "eval_runtime": 1412.7068,
+      "eval_samples_per_second": 7.261,
+      "eval_steps_per_second": 0.908,
+      "step": 27
+    },
+    {
+      "epoch": 0.0022989449484790017,
+      "grad_norm": 0.7959260940551758,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.8639,
+      "step": 28
+    },
+    {
+      "epoch": 0.0023810501252103946,
+      "grad_norm": 0.8122575879096985,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 1.7216,
+      "step": 29
+    },
+    {
+      "epoch": 0.0024631553019417874,
+      "grad_norm": 0.9101079106330872,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 1.57,
+      "step": 30
+    },
+    {
+      "epoch": 0.0025452604786731802,
+      "grad_norm": 0.9344307780265808,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 1.5108,
+      "step": 31
+    },
+    {
+      "epoch": 0.002627365655404573,
+      "grad_norm": 0.6139394044876099,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 1.5798,
+      "step": 32
+    },
+    {
+      "epoch": 0.0027094708321359663,
+      "grad_norm": 0.7699390053749084,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 1.7372,
+      "step": 33
+    },
+    {
+      "epoch": 0.002791576008867359,
+      "grad_norm": 0.7680745720863342,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 1.7336,
+      "step": 34
+    },
+    {
+      "epoch": 0.002873681185598752,
+      "grad_norm": 0.7378080487251282,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 1.8474,
+      "step": 35
+    },
+    {
+      "epoch": 0.002955786362330145,
+      "grad_norm": 0.9059414863586426,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 1.4418,
+      "step": 36
+    },
+    {
+      "epoch": 0.002955786362330145,
+      "eval_loss": 1.5442832708358765,
+      "eval_runtime": 1413.5895,
+      "eval_samples_per_second": 7.256,
+      "eval_steps_per_second": 0.908,
+      "step": 36
+    },
+    {
+      "epoch": 0.0030378915390615376,
+      "grad_norm": 0.8282952904701233,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 1.503,
+      "step": 37
+    },
+    {
+      "epoch": 0.003119996715792931,
+      "grad_norm": 0.8562686443328857,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 1.5108,
+      "step": 38
+    },
+    {
+      "epoch": 0.0032021018925243237,
+      "grad_norm": 0.8166694641113281,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 1.2283,
+      "step": 39
+    },
+    {
+      "epoch": 0.0032842070692557165,
+      "grad_norm": 0.5978056788444519,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.4893,
+      "step": 40
+    },
+    {
+      "epoch": 0.0033663122459871094,
+      "grad_norm": 1.075669765472412,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 1.3745,
+      "step": 41
+    },
+    {
+      "epoch": 0.003448417422718502,
+      "grad_norm": 0.6868987679481506,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 1.4326,
+      "step": 42
+    },
+    {
+      "epoch": 0.0035305225994498955,
+      "grad_norm": 0.67482990026474,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 1.6454,
+      "step": 43
+    },
+    {
+      "epoch": 0.0036126277761812883,
+      "grad_norm": 0.5418546795845032,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 1.7307,
+      "step": 44
+    },
+    {
+      "epoch": 0.003694732952912681,
+      "grad_norm": 0.8468795418739319,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 1.5811,
+      "step": 45
+    },
+    {
+      "epoch": 0.003694732952912681,
+      "eval_loss": 1.5238127708435059,
+      "eval_runtime": 1414.3795,
+      "eval_samples_per_second": 7.252,
+      "eval_steps_per_second": 0.907,
+      "step": 45
+    },
+    {
+      "epoch": 0.003776838129644074,
+      "grad_norm": 0.5245246291160583,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.6244,
+      "step": 46
+    },
+    {
+      "epoch": 0.0038589433063754668,
+      "grad_norm": 0.934582531452179,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 1.2247,
+      "step": 47
+    },
+    {
+      "epoch": 0.00394104848310686,
+      "grad_norm": 0.669644296169281,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 1.6391,
+      "step": 48
+    },
+    {
+      "epoch": 0.004023153659838252,
+      "grad_norm": 0.6915856003761292,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 1.3849,
+      "step": 49
+    },
+    {
+      "epoch": 0.004105258836569646,
+      "grad_norm": 0.5015689730644226,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 1.54,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.299850579037389e+16,
+  "total_flos": 4.896456071498957e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null