Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69aef81aaabffa269d26f1d64ad1472522d2932e949d8e56b55bbeb5aa5ad34f
+oid sha256:7ace869f31b8aa0c5784c63fc283848cda4e239fcfe4f704bce90f520273cc41
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:420111d5975146ac06e2ebe8a6135a4ab9a44ed1c054eb71d4dcab83be753847
+oid sha256:81f100c70461eeefe495b7614066ae51583e8337b4378f5fea447532a1e9407a
 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": 0.19455252918287938,
+  "epoch": 0.38910505836575876,
   "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": 10.3402,
       "step": 25
+    },
+    {
+      "epoch": 0.20233463035019456,
+      "grad_norm": 0.09935510903596878,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 10.367,
+      "step": 26
+    },
+    {
+      "epoch": 0.21011673151750973,
+      "grad_norm": 0.1893402338027954,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 10.343,
+      "step": 27
+    },
+    {
+      "epoch": 0.21011673151750973,
+      "eval_loss": NaN,
+      "eval_runtime": 0.396,
+      "eval_samples_per_second": 272.742,
+      "eval_steps_per_second": 35.355,
+      "step": 27
+    },
+    {
+      "epoch": 0.2178988326848249,
+      "grad_norm": 0.16203711926937103,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 10.3318,
+      "step": 28
+    },
+    {
+      "epoch": 0.22568093385214008,
+      "grad_norm": 0.19412550330162048,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 10.3913,
+      "step": 29
+    },
+    {
+      "epoch": 0.23346303501945526,
+      "grad_norm": 0.3511830270290375,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 10.2959,
+      "step": 30
+    },
+    {
+      "epoch": 0.24124513618677043,
+      "grad_norm": 0.2315189391374588,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 10.3486,
+      "step": 31
+    },
+    {
+      "epoch": 0.2490272373540856,
+      "grad_norm": 0.1658879965543747,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 10.3505,
+      "step": 32
+    },
+    {
+      "epoch": 0.25680933852140075,
+      "grad_norm": 0.1770622283220291,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 10.3333,
+      "step": 33
+    },
+    {
+      "epoch": 0.26459143968871596,
+      "grad_norm": 0.0,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.2723735408560311,
+      "grad_norm": 0.28501346707344055,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 10.2935,
+      "step": 35
+    },
+    {
+      "epoch": 0.2801556420233463,
+      "grad_norm": 0.2703624367713928,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 10.3251,
+      "step": 36
+    },
+    {
+      "epoch": 0.2801556420233463,
+      "eval_loss": NaN,
+      "eval_runtime": 0.3829,
+      "eval_samples_per_second": 282.076,
+      "eval_steps_per_second": 36.565,
+      "step": 36
+    },
+    {
+      "epoch": 0.28793774319066145,
+      "grad_norm": 0.16514138877391815,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 10.3588,
+      "step": 37
+    },
+    {
+      "epoch": 0.29571984435797666,
+      "grad_norm": 0.17835251986980438,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 10.3294,
+      "step": 38
+    },
+    {
+      "epoch": 0.3035019455252918,
+      "grad_norm": 0.0,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.311284046692607,
+      "grad_norm": 0.35127612948417664,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 10.3466,
+      "step": 40
+    },
+    {
+      "epoch": 0.31906614785992216,
+      "grad_norm": 0.23155651986598969,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 10.3373,
+      "step": 41
+    },
+    {
+      "epoch": 0.32684824902723736,
+      "grad_norm": 0.31581297516822815,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 10.3105,
+      "step": 42
+    },
+    {
+      "epoch": 0.3346303501945525,
+      "grad_norm": 0.0,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.3424124513618677,
+      "grad_norm": 0.1989944577217102,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 10.3353,
+      "step": 44
+    },
+    {
+      "epoch": 0.35019455252918286,
+      "grad_norm": 0.10988571494817734,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 10.3591,
+      "step": 45
+    },
+    {
+      "epoch": 0.35019455252918286,
+      "eval_loss": NaN,
+      "eval_runtime": 0.4084,
+      "eval_samples_per_second": 264.436,
+      "eval_steps_per_second": 34.279,
+      "step": 45
+    },
+    {
+      "epoch": 0.35797665369649806,
+      "grad_norm": 0.2702690362930298,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 10.3186,
+      "step": 46
+    },
+    {
+      "epoch": 0.3657587548638132,
+      "grad_norm": 0.2404761016368866,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 10.3323,
+      "step": 47
+    },
+    {
+      "epoch": 0.3735408560311284,
+      "grad_norm": 0.24785469472408295,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 10.2847,
+      "step": 48
+    },
+    {
+      "epoch": 0.38132295719844356,
+      "grad_norm": 0.17176614701747894,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 10.3431,
+      "step": 49
+    },
+    {
+      "epoch": 0.38910505836575876,
+      "grad_norm": 0.2749108672142029,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 10.3002,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1909039300608.0,
+  "total_flos": 3687322484736.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null