Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a602d4b12efd8bac3490118b071b5fdd0461f5fc0764f19f4811bb62853b636
+oid sha256:275a0518b6369e85e4c585418cc6150fd4f36779420132d8a5f78eb4f9989267
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3934faacd6ff655818de8845912c82a474cb93a07f1d41b5894d2cb4ba049808
+oid sha256:67f954f26bbc7fa193ae4ab9c52b1b63a3f97c59bf2fd7544764169aba5152e9
 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": 0.0021284747350048955,
+  "epoch": 0.004256949470009791,
   "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": 10.3898,
       "step": 25
+    },
+    {
+      "epoch": 0.002213613724405091,
+      "grad_norm": 0.06255259364843369,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 10.3848,
+      "step": 26
+    },
+    {
+      "epoch": 0.0022987527138052873,
+      "grad_norm": 0.07093428820371628,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 10.3834,
+      "step": 27
+    },
+    {
+      "epoch": 0.0022987527138052873,
+      "eval_loss": 10.376791000366211,
+      "eval_runtime": 37.1822,
+      "eval_samples_per_second": 266.014,
+      "eval_steps_per_second": 33.269,
+      "step": 27
+    },
+    {
+      "epoch": 0.002383891703205483,
+      "grad_norm": 0.06431137025356293,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 10.3878,
+      "step": 28
+    },
+    {
+      "epoch": 0.0024690306926056786,
+      "grad_norm": 0.06749837845563889,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 10.3917,
+      "step": 29
+    },
+    {
+      "epoch": 0.0025541696820058747,
+      "grad_norm": 0.06856685876846313,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 10.3812,
+      "step": 30
+    },
+    {
+      "epoch": 0.0026393086714060704,
+      "grad_norm": 0.07790417969226837,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 10.3734,
+      "step": 31
+    },
+    {
+      "epoch": 0.002724447660806266,
+      "grad_norm": 0.06906121224164963,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 10.3667,
+      "step": 32
+    },
+    {
+      "epoch": 0.0028095866502064622,
+      "grad_norm": 0.07379811257123947,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 10.3681,
+      "step": 33
+    },
+    {
+      "epoch": 0.002894725639606658,
+      "grad_norm": 0.0777546837925911,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 10.3742,
+      "step": 34
+    },
+    {
+      "epoch": 0.0029798646290068536,
+      "grad_norm": 0.09084642678499222,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 10.3725,
+      "step": 35
+    },
+    {
+      "epoch": 0.0030650036184070497,
+      "grad_norm": 0.07533272355794907,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 10.3616,
+      "step": 36
+    },
+    {
+      "epoch": 0.0030650036184070497,
+      "eval_loss": 10.3751859664917,
+      "eval_runtime": 37.0132,
+      "eval_samples_per_second": 267.229,
+      "eval_steps_per_second": 33.42,
+      "step": 36
+    },
+    {
+      "epoch": 0.0031501426078072454,
+      "grad_norm": 0.09557131677865982,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 10.3627,
+      "step": 37
+    },
+    {
+      "epoch": 0.003235281597207441,
+      "grad_norm": 0.086721271276474,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 10.3797,
+      "step": 38
+    },
+    {
+      "epoch": 0.003320420586607637,
+      "grad_norm": 0.0951017513871193,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 10.3642,
+      "step": 39
+    },
+    {
+      "epoch": 0.003405559576007833,
+      "grad_norm": 0.08322468400001526,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 10.3718,
+      "step": 40
+    },
+    {
+      "epoch": 0.0034906985654080285,
+      "grad_norm": 0.08715411275625229,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 10.3912,
+      "step": 41
+    },
+    {
+      "epoch": 0.003575837554808224,
+      "grad_norm": 0.07306662946939468,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 10.3831,
+      "step": 42
+    },
+    {
+      "epoch": 0.0036609765442084203,
+      "grad_norm": 0.07265879958868027,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 10.3775,
+      "step": 43
+    },
+    {
+      "epoch": 0.003746115533608616,
+      "grad_norm": 0.07239469140768051,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 10.3708,
+      "step": 44
+    },
+    {
+      "epoch": 0.0038312545230088117,
+      "grad_norm": 0.06718676537275314,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 10.3772,
+      "step": 45
+    },
+    {
+      "epoch": 0.0038312545230088117,
+      "eval_loss": 10.373581886291504,
+      "eval_runtime": 36.9465,
+      "eval_samples_per_second": 267.712,
+      "eval_steps_per_second": 33.481,
+      "step": 45
+    },
+    {
+      "epoch": 0.003916393512409007,
+      "grad_norm": 0.1044333428144455,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 10.3736,
+      "step": 46
+    },
+    {
+      "epoch": 0.004001532501809204,
+      "grad_norm": 0.09110475331544876,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 10.3743,
+      "step": 47
+    },
+    {
+      "epoch": 0.0040866714912094,
+      "grad_norm": 0.08908325433731079,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 10.3715,
+      "step": 48
+    },
+    {
+      "epoch": 0.004171810480609595,
+      "grad_norm": 0.09201818704605103,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 10.3745,
+      "step": 49
+    },
+    {
+      "epoch": 0.004256949470009791,
+      "grad_norm": 0.08138486742973328,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 10.3831,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2484366213120.0,
+  "total_flos": 4864127533056.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null