Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00398b3cfc2f8ee7eee3da92e818f8a3dc7b7c49543d91e2b92837b9480338ff
+oid sha256:17b58096e2b0042e90ac4c77902d6b61832d448e4ac593854b9541f5e18ec13a
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26b221c6b7e90e21506ebc5d21b7902b0727348329251398b6f839b20d5e4287
+oid sha256:fddbb383e22119aec0c66f14edad7e5c6874a90b85c5f6cd76f15a54446ded64
 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": 0.0027162103433289874,
+  "epoch": 0.005432420686657975,
   "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": 10.3411,
       "step": 25
+    },
+    {
+      "epoch": 0.002824858757062147,
+      "grad_norm": 1.67805016040802,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 10.3366,
+      "step": 26
+    },
+    {
+      "epoch": 0.0029335071707953064,
+      "grad_norm": 1.5231330394744873,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 10.3398,
+      "step": 27
+    },
+    {
+      "epoch": 0.0029335071707953064,
+      "eval_loss": 10.332958221435547,
+      "eval_runtime": 50.6164,
+      "eval_samples_per_second": 153.132,
+      "eval_steps_per_second": 19.144,
+      "step": 27
+    },
+    {
+      "epoch": 0.003042155584528466,
+      "grad_norm": 1.7659465074539185,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 10.331,
+      "step": 28
+    },
+    {
+      "epoch": 0.0031508039982616255,
+      "grad_norm": 1.6914821863174438,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 10.3354,
+      "step": 29
+    },
+    {
+      "epoch": 0.003259452411994785,
+      "grad_norm": 1.7179479598999023,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 10.3135,
+      "step": 30
+    },
+    {
+      "epoch": 0.0033681008257279445,
+      "grad_norm": 1.6100873947143555,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 10.3158,
+      "step": 31
+    },
+    {
+      "epoch": 0.003476749239461104,
+      "grad_norm": 1.5977933406829834,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 10.3014,
+      "step": 32
+    },
+    {
+      "epoch": 0.003585397653194263,
+      "grad_norm": 1.5835942029953003,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 10.3178,
+      "step": 33
+    },
+    {
+      "epoch": 0.0036940460669274227,
+      "grad_norm": 1.5189638137817383,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 10.317,
+      "step": 34
+    },
+    {
+      "epoch": 0.003802694480660582,
+      "grad_norm": 1.5402252674102783,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 10.3151,
+      "step": 35
+    },
+    {
+      "epoch": 0.003911342894393742,
+      "grad_norm": 1.6104727983474731,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 10.2874,
+      "step": 36
+    },
+    {
+      "epoch": 0.003911342894393742,
+      "eval_loss": 10.299212455749512,
+      "eval_runtime": 50.866,
+      "eval_samples_per_second": 152.381,
+      "eval_steps_per_second": 19.05,
+      "step": 36
+    },
+    {
+      "epoch": 0.004019991308126901,
+      "grad_norm": 1.610350251197815,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 10.3047,
+      "step": 37
+    },
+    {
+      "epoch": 0.004128639721860061,
+      "grad_norm": 1.5481282472610474,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 10.2996,
+      "step": 38
+    },
+    {
+      "epoch": 0.00423728813559322,
+      "grad_norm": 1.247719168663025,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 10.3214,
+      "step": 39
+    },
+    {
+      "epoch": 0.004345936549326379,
+      "grad_norm": 1.5715504884719849,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 10.3132,
+      "step": 40
+    },
+    {
+      "epoch": 0.004454584963059539,
+      "grad_norm": 1.5834615230560303,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 10.2998,
+      "step": 41
+    },
+    {
+      "epoch": 0.0045632333767926985,
+      "grad_norm": 1.3792880773544312,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 10.3017,
+      "step": 42
+    },
+    {
+      "epoch": 0.0046718817905258584,
+      "grad_norm": 1.5816736221313477,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 10.2933,
+      "step": 43
+    },
+    {
+      "epoch": 0.0047805302042590175,
+      "grad_norm": 1.5913182497024536,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 10.2781,
+      "step": 44
+    },
+    {
+      "epoch": 0.0048891786179921775,
+      "grad_norm": 1.6335688829421997,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 10.2657,
+      "step": 45
+    },
+    {
+      "epoch": 0.0048891786179921775,
+      "eval_loss": 10.27038288116455,
+      "eval_runtime": 50.9692,
+      "eval_samples_per_second": 152.072,
+      "eval_steps_per_second": 19.011,
+      "step": 45
+    },
+    {
+      "epoch": 0.004997827031725337,
+      "grad_norm": 1.475588321685791,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 10.2898,
+      "step": 46
+    },
+    {
+      "epoch": 0.0051064754454584966,
+      "grad_norm": 1.5345820188522339,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 10.2616,
+      "step": 47
+    },
+    {
+      "epoch": 0.005215123859191656,
+      "grad_norm": 1.508804440498352,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 10.2893,
+      "step": 48
+    },
+    {
+      "epoch": 0.005323772272924816,
+      "grad_norm": 1.4398443698883057,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 10.2821,
+      "step": 49
+    },
+    {
+      "epoch": 0.005432420686657975,
+      "grad_norm": 1.4615792036056519,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 10.2633,
+      "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