Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:131b11a0342dff28e6e74fef93dbb9a8e50d798c2be2a309dac9af4ef3a53c03
+oid sha256:8bfd96b83bbfcae3f4c3acafc75648048e48c4eaf9440b83cf73ba9814998514
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4784acdcb95cbede9bafe690275629d739cc4f3e6e3d5a2f1536a647150eebe
+oid sha256:e0bb2f977833271a38fea94597b96b3ec7b580801e4e4e80a1329dfe1dc5e767
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7f5bbfaaf7697d119d5bdf432f060cbe4ef6ecbca8897a175e3f929cece8c35
+oid sha256:d02832e007bdf624c2cd616b1f730061daaf174a56276b15049a86c6d19ea189
 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": 0.7086,
       "step": 25
+    },
+    {
+      "epoch": 0.03936411809235428,
+      "grad_norm": 0.9445357918739319,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.7351,
+      "step": 26
+    },
+    {
+      "epoch": 0.0408781226343679,
+      "grad_norm": 0.7903055548667908,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 0.6486,
+      "step": 27
+    },
+    {
+      "epoch": 0.0408781226343679,
+      "eval_loss": 0.6585749387741089,
+      "eval_runtime": 112.3863,
+      "eval_samples_per_second": 4.947,
+      "eval_steps_per_second": 0.623,
+      "step": 27
+    },
+    {
+      "epoch": 0.04239212717638153,
+      "grad_norm": 0.7344522476196289,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.6864,
+      "step": 28
+    },
+    {
+      "epoch": 0.04390613171839516,
+      "grad_norm": 0.7938252091407776,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 0.5384,
+      "step": 29
+    },
+    {
+      "epoch": 0.045420136260408785,
+      "grad_norm": 0.8089536428451538,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.6791,
+      "step": 30
+    },
+    {
+      "epoch": 0.046934140802422405,
+      "grad_norm": 0.6889751553535461,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 0.6777,
+      "step": 31
+    },
+    {
+      "epoch": 0.04844814534443603,
+      "grad_norm": 0.9178895354270935,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.6124,
+      "step": 32
+    },
+    {
+      "epoch": 0.04996214988644966,
+      "grad_norm": 0.790649950504303,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.6654,
+      "step": 33
+    },
+    {
+      "epoch": 0.05147615442846329,
+      "grad_norm": 0.7298893928527832,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.6839,
+      "step": 34
+    },
+    {
+      "epoch": 0.05299015897047691,
+      "grad_norm": 0.7058828473091125,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 0.6835,
+      "step": 35
+    },
+    {
+      "epoch": 0.05450416351249054,
+      "grad_norm": 0.7319390773773193,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.6597,
+      "step": 36
+    },
+    {
+      "epoch": 0.05450416351249054,
+      "eval_loss": 0.6305856108665466,
+      "eval_runtime": 112.421,
+      "eval_samples_per_second": 4.946,
+      "eval_steps_per_second": 0.623,
+      "step": 36
+    },
+    {
+      "epoch": 0.056018168054504165,
+      "grad_norm": 0.8053693175315857,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.7052,
+      "step": 37
+    },
+    {
+      "epoch": 0.05753217259651779,
+      "grad_norm": 0.8908604979515076,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.6315,
+      "step": 38
+    },
+    {
+      "epoch": 0.059046177138531414,
+      "grad_norm": 0.8547291159629822,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.55,
+      "step": 39
+    },
+    {
+      "epoch": 0.06056018168054504,
+      "grad_norm": 0.6951102614402771,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.6597,
+      "step": 40
+    },
+    {
+      "epoch": 0.06207418622255867,
+      "grad_norm": 0.8669103384017944,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 0.5783,
+      "step": 41
+    },
+    {
+      "epoch": 0.0635881907645723,
+      "grad_norm": 0.7219836115837097,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.7272,
+      "step": 42
+    },
+    {
+      "epoch": 0.06510219530658592,
+      "grad_norm": 0.9448738694190979,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.5859,
+      "step": 43
+    },
+    {
+      "epoch": 0.06661619984859955,
+      "grad_norm": 0.8073548674583435,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 0.6732,
+      "step": 44
+    },
+    {
+      "epoch": 0.06813020439061317,
+      "grad_norm": 0.7021400332450867,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.5786,
+      "step": 45
+    },
+    {
+      "epoch": 0.06813020439061317,
+      "eval_loss": 0.617196261882782,
+      "eval_runtime": 112.3955,
+      "eval_samples_per_second": 4.947,
+      "eval_steps_per_second": 0.623,
+      "step": 45
+    },
+    {
+      "epoch": 0.0696442089326268,
+      "grad_norm": 0.7012249827384949,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.7483,
+      "step": 46
+    },
+    {
+      "epoch": 0.07115821347464042,
+      "grad_norm": 0.7140128016471863,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 0.6484,
+      "step": 47
+    },
+    {
+      "epoch": 0.07267221801665405,
+      "grad_norm": 0.7511979341506958,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.5084,
+      "step": 48
+    },
+    {
+      "epoch": 0.07418622255866768,
+      "grad_norm": 0.9730421900749207,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.5932,
+      "step": 49
+    },
+    {
+      "epoch": 0.0757002271006813,
+      "grad_norm": 0.7117515206336975,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.3311,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.523964596912128e+16,
+  "total_flos": 6.899551737112166e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null