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:bfe4fb35fcd5b3b7a8e2c25d8737d4d900793a1f44a936efe4a57a88421ffdee
+oid sha256:e16d10bf9a111161de20e15d969d0718256939f6c381d64394c50b2255908991
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf0f2d783aed1c0f73ebd2177e49ca8f15fe22070344707ae703d693193f4f09
+oid sha256:bddea746290e791019360e6635a4efd9a761a0c5be7fc82ebae738ac75ed8e49
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b3600f4f62c77cfb9f3f36d5a114f6f58022f220d20e149c85171731fd49eb1
+oid sha256:cb9517b7ce59c47365939baf2f50e6bfd58d4414b9c61ed194de990178b59d75
 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": 0.0008209102252577658,
+  "epoch": 0.0016418204505155316,
   "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": 10.3757,
       "step": 25
+    },
+    {
+      "epoch": 0.0008537466342680765,
+      "grad_norm": 0.04307650402188301,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 10.3715,
+      "step": 26
+    },
+    {
+      "epoch": 0.0008865830432783871,
+      "grad_norm": 0.041188716888427734,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 10.3712,
+      "step": 27
+    },
+    {
+      "epoch": 0.0008865830432783871,
+      "eval_loss": 10.375112533569336,
+      "eval_runtime": 170.1694,
+      "eval_samples_per_second": 150.709,
+      "eval_steps_per_second": 18.84,
+      "step": 27
+    },
+    {
+      "epoch": 0.0009194194522886977,
+      "grad_norm": 0.03614542633295059,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 10.3765,
+      "step": 28
+    },
+    {
+      "epoch": 0.0009522558612990083,
+      "grad_norm": 0.0354689322412014,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 10.3743,
+      "step": 29
+    },
+    {
+      "epoch": 0.000985092270309319,
+      "grad_norm": 0.0464780293405056,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 10.3809,
+      "step": 30
+    },
+    {
+      "epoch": 0.0010179286793196296,
+      "grad_norm": 0.05983458459377289,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 10.3758,
+      "step": 31
+    },
+    {
+      "epoch": 0.0010507650883299403,
+      "grad_norm": 0.04344520345330238,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 10.3735,
+      "step": 32
+    },
+    {
+      "epoch": 0.0010836014973402508,
+      "grad_norm": 0.041173264384269714,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 10.3722,
+      "step": 33
+    },
+    {
+      "epoch": 0.0011164379063505615,
+      "grad_norm": 0.041133031249046326,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 10.3769,
+      "step": 34
+    },
+    {
+      "epoch": 0.0011492743153608722,
+      "grad_norm": 0.06315415352582932,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 10.378,
+      "step": 35
+    },
+    {
+      "epoch": 0.0011821107243711827,
+      "grad_norm": 0.04024801030755043,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 10.373,
+      "step": 36
+    },
+    {
+      "epoch": 0.0011821107243711827,
+      "eval_loss": 10.374061584472656,
+      "eval_runtime": 170.5991,
+      "eval_samples_per_second": 150.329,
+      "eval_steps_per_second": 18.793,
+      "step": 36
+    },
+    {
+      "epoch": 0.0012149471333814934,
+      "grad_norm": 0.042859919369220734,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 10.3751,
+      "step": 37
+    },
+    {
+      "epoch": 0.0012477835423918041,
+      "grad_norm": 0.04361676052212715,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 10.3766,
+      "step": 38
+    },
+    {
+      "epoch": 0.0012806199514021146,
+      "grad_norm": 0.053741976618766785,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 10.3753,
+      "step": 39
+    },
+    {
+      "epoch": 0.0013134563604124253,
+      "grad_norm": 0.0702785924077034,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 10.3751,
+      "step": 40
+    },
+    {
+      "epoch": 0.0013462927694227358,
+      "grad_norm": 0.06600352376699448,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 10.3788,
+      "step": 41
+    },
+    {
+      "epoch": 0.0013791291784330465,
+      "grad_norm": 0.037580136209726334,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 10.3778,
+      "step": 42
+    },
+    {
+      "epoch": 0.0014119655874433572,
+      "grad_norm": 0.05780002847313881,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 10.375,
+      "step": 43
+    },
+    {
+      "epoch": 0.0014448019964536677,
+      "grad_norm": 0.04174739867448807,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 10.3758,
+      "step": 44
+    },
+    {
+      "epoch": 0.0014776384054639784,
+      "grad_norm": 0.053912002593278885,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 10.3738,
+      "step": 45
+    },
+    {
+      "epoch": 0.0014776384054639784,
+      "eval_loss": 10.373043060302734,
+      "eval_runtime": 170.5618,
+      "eval_samples_per_second": 150.362,
+      "eval_steps_per_second": 18.797,
+      "step": 45
+    },
+    {
+      "epoch": 0.0015104748144742892,
+      "grad_norm": 0.044272515922784805,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 10.3758,
+      "step": 46
+    },
+    {
+      "epoch": 0.0015433112234845997,
+      "grad_norm": 0.04709697142243385,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 10.3749,
+      "step": 47
+    },
+    {
+      "epoch": 0.0015761476324949104,
+      "grad_norm": 0.04305019602179527,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 10.364,
+      "step": 48
+    },
+    {
+      "epoch": 0.001608984041505221,
+      "grad_norm": 0.049739986658096313,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 10.3708,
+      "step": 49
+    },
+    {
+      "epoch": 0.0016418204505155316,
+      "grad_norm": 0.04268916696310043,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 10.3697,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1307561164800.0,
+  "total_flos": 2615122329600.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null