Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:953912d5fd6b4b31ddb26bbd91b4d05ae1e7aaf8369f551cedcb06aaa495ee38
+oid sha256:cb02220735713899e4500445a3b40bb7a049308f30dd104e335cb93abb6a75f9
 size 767856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dad0fb4993c8ae07276a867e76f5d28df4eafbcabacf57e4be7408e24737a3ac
+oid sha256:a5d38d812841627e967b1f485c5092add15f1ffaca3e7e17b8da2405ac7ddaae
 size 1601338

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d93b33273c9b3125ec5a88273d23398e57bd0888aa6d11d2e60da98e429ff6ae
+oid sha256:80546a3f69a81bba48ed69e31ba9b51f3877d5e68b87beb3fea8356bf7cbceff
 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": 0.0009580195819202544,
+  "epoch": 0.001916039163840509,
   "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": 9.5802,
       "step": 25
+    },
+    {
+      "epoch": 0.0009963403651970647,
+      "grad_norm": 3.075852155685425,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 9.5869,
+      "step": 26
+    },
+    {
+      "epoch": 0.0010346611484738748,
+      "grad_norm": 3.107454776763916,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 9.2758,
+      "step": 27
+    },
+    {
+      "epoch": 0.0010346611484738748,
+      "eval_loss": 9.356222152709961,
+      "eval_runtime": 196.8567,
+      "eval_samples_per_second": 111.635,
+      "eval_steps_per_second": 13.954,
+      "step": 27
+    },
+    {
+      "epoch": 0.001072981931750685,
+      "grad_norm": 3.239929437637329,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 9.3093,
+      "step": 28
+    },
+    {
+      "epoch": 0.001111302715027495,
+      "grad_norm": 3.1697399616241455,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 9.4413,
+      "step": 29
+    },
+    {
+      "epoch": 0.0011496234983043054,
+      "grad_norm": 2.983443260192871,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 9.2819,
+      "step": 30
+    },
+    {
+      "epoch": 0.0011879442815811154,
+      "grad_norm": 2.9809553623199463,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 9.2256,
+      "step": 31
+    },
+    {
+      "epoch": 0.0012262650648579257,
+      "grad_norm": 2.92080020904541,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 9.0488,
+      "step": 32
+    },
+    {
+      "epoch": 0.001264585848134736,
+      "grad_norm": 2.7908945083618164,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 9.1336,
+      "step": 33
+    },
+    {
+      "epoch": 0.001302906631411546,
+      "grad_norm": 2.688901662826538,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 9.0057,
+      "step": 34
+    },
+    {
+      "epoch": 0.0013412274146883563,
+      "grad_norm": 2.6229913234710693,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 8.8516,
+      "step": 35
+    },
+    {
+      "epoch": 0.0013795481979651664,
+      "grad_norm": 2.903886556625366,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 9.1772,
+      "step": 36
+    },
+    {
+      "epoch": 0.0013795481979651664,
+      "eval_loss": 9.0332670211792,
+      "eval_runtime": 200.6695,
+      "eval_samples_per_second": 109.513,
+      "eval_steps_per_second": 13.689,
+      "step": 36
+    },
+    {
+      "epoch": 0.0014178689812419766,
+      "grad_norm": 2.304446220397949,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 9.0422,
+      "step": 37
+    },
+    {
+      "epoch": 0.0014561897645187867,
+      "grad_norm": 2.6148622035980225,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 8.9424,
+      "step": 38
+    },
+    {
+      "epoch": 0.001494510547795597,
+      "grad_norm": 2.5895235538482666,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 8.9902,
+      "step": 39
+    },
+    {
+      "epoch": 0.001532831331072407,
+      "grad_norm": 2.4067177772521973,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 8.9559,
+      "step": 40
+    },
+    {
+      "epoch": 0.0015711521143492173,
+      "grad_norm": 2.6639695167541504,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 8.8575,
+      "step": 41
+    },
+    {
+      "epoch": 0.0016094728976260276,
+      "grad_norm": 2.2785677909851074,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 9.0544,
+      "step": 42
+    },
+    {
+      "epoch": 0.0016477936809028376,
+      "grad_norm": 2.155168294906616,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 8.7763,
+      "step": 43
+    },
+    {
+      "epoch": 0.001686114464179648,
+      "grad_norm": 2.451356887817383,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 8.9635,
+      "step": 44
+    },
+    {
+      "epoch": 0.001724435247456458,
+      "grad_norm": 2.1244118213653564,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 8.7786,
+      "step": 45
+    },
+    {
+      "epoch": 0.001724435247456458,
+      "eval_loss": 8.795065879821777,
+      "eval_runtime": 198.6273,
+      "eval_samples_per_second": 110.639,
+      "eval_steps_per_second": 13.83,
+      "step": 45
+    },
+    {
+      "epoch": 0.0017627560307332682,
+      "grad_norm": 2.1409757137298584,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 8.843,
+      "step": 46
+    },
+    {
+      "epoch": 0.0018010768140100783,
+      "grad_norm": 2.1220507621765137,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 8.8037,
+      "step": 47
+    },
+    {
+      "epoch": 0.0018393975972868886,
+      "grad_norm": 1.9951223134994507,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 8.7091,
+      "step": 48
+    },
+    {
+      "epoch": 0.0018777183805636986,
+      "grad_norm": 2.0571706295013428,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 8.624,
+      "step": 49
+    },
+    {
+      "epoch": 0.001916039163840509,
+      "grad_norm": 2.1683812141418457,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 8.7798,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6787380019200.0,
+  "total_flos": 13574760038400.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null