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:a8a710dec7bb4127ecf3e75819b8cd7d7be4b8bb683d05adcc348a70e18325c0
+oid sha256:da4360ccad2121ce7d6aeedcae6f6ee3af4f0499001f38d3645cb17acedf8b6b
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fa2f5523ffee4a7acf3911995b80882e0f34149ec984d19ab1166f5f57e31d6
+oid sha256:b4dfaa852d8c0a619895fe0ebdad36344a03e49caeec16ae44db1c598447d6e5
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ab2abce808460fbf09200dc73542ef2b7fb79ad65ba37f1046d1d341f927df4
+oid sha256:c33feb238edb291cd05db2a1f78c61ea97195145e02e941fc757930ac6bc0675
 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": 0.03785011355034065,
+  "epoch": 0.0757002271006813,
   "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": 0.674,
       "step": 25
+    },
+    {
+      "epoch": 0.03936411809235428,
+      "grad_norm": 0.5442315340042114,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.542,
+      "step": 26
+    },
+    {
+      "epoch": 0.0408781226343679,
+      "grad_norm": 0.49935996532440186,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 0.5723,
+      "step": 27
+    },
+    {
+      "epoch": 0.0408781226343679,
+      "eval_loss": 0.5580048561096191,
+      "eval_runtime": 127.335,
+      "eval_samples_per_second": 4.366,
+      "eval_steps_per_second": 0.55,
+      "step": 27
+    },
+    {
+      "epoch": 0.04239212717638153,
+      "grad_norm": 0.43072766065597534,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.6508,
+      "step": 28
+    },
+    {
+      "epoch": 0.04390613171839516,
+      "grad_norm": 0.559459388256073,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 0.5142,
+      "step": 29
+    },
+    {
+      "epoch": 0.045420136260408785,
+      "grad_norm": 0.5589441061019897,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.5605,
+      "step": 30
+    },
+    {
+      "epoch": 0.046934140802422405,
+      "grad_norm": 0.46951043605804443,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 0.6581,
+      "step": 31
+    },
+    {
+      "epoch": 0.04844814534443603,
+      "grad_norm": 0.5119128227233887,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.5879,
+      "step": 32
+    },
+    {
+      "epoch": 0.04996214988644966,
+      "grad_norm": 0.680155873298645,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.5249,
+      "step": 33
+    },
+    {
+      "epoch": 0.05147615442846329,
+      "grad_norm": 0.5114449858665466,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.5143,
+      "step": 34
+    },
+    {
+      "epoch": 0.05299015897047691,
+      "grad_norm": 0.43590912222862244,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 0.5876,
+      "step": 35
+    },
+    {
+      "epoch": 0.05450416351249054,
+      "grad_norm": 0.4947156310081482,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.6025,
+      "step": 36
+    },
+    {
+      "epoch": 0.05450416351249054,
+      "eval_loss": 0.5477901697158813,
+      "eval_runtime": 127.3887,
+      "eval_samples_per_second": 4.365,
+      "eval_steps_per_second": 0.549,
+      "step": 36
+    },
+    {
+      "epoch": 0.056018168054504165,
+      "grad_norm": 0.5622116923332214,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.5587,
+      "step": 37
+    },
+    {
+      "epoch": 0.05753217259651779,
+      "grad_norm": 0.442304790019989,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.6293,
+      "step": 38
+    },
+    {
+      "epoch": 0.059046177138531414,
+      "grad_norm": 0.5162755846977234,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.6347,
+      "step": 39
+    },
+    {
+      "epoch": 0.06056018168054504,
+      "grad_norm": 0.4614929258823395,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.5356,
+      "step": 40
+    },
+    {
+      "epoch": 0.06207418622255867,
+      "grad_norm": 0.4985050559043884,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 0.5409,
+      "step": 41
+    },
+    {
+      "epoch": 0.0635881907645723,
+      "grad_norm": 0.5837581753730774,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.4478,
+      "step": 42
+    },
+    {
+      "epoch": 0.06510219530658592,
+      "grad_norm": 0.4671187996864319,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.6622,
+      "step": 43
+    },
+    {
+      "epoch": 0.06661619984859955,
+      "grad_norm": 0.5558192729949951,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 0.6513,
+      "step": 44
+    },
+    {
+      "epoch": 0.06813020439061317,
+      "grad_norm": 0.5534436106681824,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.649,
+      "step": 45
+    },
+    {
+      "epoch": 0.06813020439061317,
+      "eval_loss": 0.5416960716247559,
+      "eval_runtime": 127.3858,
+      "eval_samples_per_second": 4.365,
+      "eval_steps_per_second": 0.55,
+      "step": 45
+    },
+    {
+      "epoch": 0.0696442089326268,
+      "grad_norm": 0.5023759603500366,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.6837,
+      "step": 46
+    },
+    {
+      "epoch": 0.07115821347464042,
+      "grad_norm": 0.4820226728916168,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 0.6636,
+      "step": 47
+    },
+    {
+      "epoch": 0.07267221801665405,
+      "grad_norm": 0.5207632184028625,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.5335,
+      "step": 48
+    },
+    {
+      "epoch": 0.07418622255866768,
+      "grad_norm": 0.45377227663993835,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.6229,
+      "step": 49
+    },
+    {
+      "epoch": 0.0757002271006813,
+      "grad_norm": 0.46908336877822876,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.699,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.4868702327341056e+16,
+  "total_flos": 7.085023558002278e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null