Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01895cd3af32b85dabcf86952f1f5df9d1157b9a9d974b2fed676dafc696c263
+oid sha256:1e4a964f31dd0a8dd5f1cbfa36c04b66c899e2ddf60b4412ae882c81f3e50580
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cab15cf8d7f98b6fe61f231a3484a0893ae0fc0c503ac87f3d53ef178c407e0
+oid sha256:b1ddb04398fa4312eac567eaeeb7b06131658bcad362ffe49a8d216090472ce4
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f8e5ed923d081d691bbd914665583b8046f8946ab3842a1e06975493ff2a92b
+oid sha256:ea6542ea5e34bb1c1dcc0aa12c7426317df18665467f05291c0133229c6e57f4
 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": 0.2304147465437788,
+  "epoch": 0.4608294930875576,
   "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": 1.248,
       "step": 25
+    },
+    {
+      "epoch": 0.23963133640552994,
+      "grad_norm": 0.8940214514732361,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 1.1786,
+      "step": 26
+    },
+    {
+      "epoch": 0.2488479262672811,
+      "grad_norm": 0.7923563122749329,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 1.092,
+      "step": 27
+    },
+    {
+      "epoch": 0.2488479262672811,
+      "eval_loss": 1.0744620561599731,
+      "eval_runtime": 11.0513,
+      "eval_samples_per_second": 8.325,
+      "eval_steps_per_second": 1.086,
+      "step": 27
+    },
+    {
+      "epoch": 0.25806451612903225,
+      "grad_norm": 0.7313264012336731,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.1987,
+      "step": 28
+    },
+    {
+      "epoch": 0.2672811059907834,
+      "grad_norm": 0.7360963225364685,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 1.0541,
+      "step": 29
+    },
+    {
+      "epoch": 0.2764976958525346,
+      "grad_norm": 0.8408584594726562,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 1.0301,
+      "step": 30
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.7449260354042053,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 1.1199,
+      "step": 31
+    },
+    {
+      "epoch": 0.29493087557603687,
+      "grad_norm": 0.7829388976097107,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 1.1198,
+      "step": 32
+    },
+    {
+      "epoch": 0.30414746543778803,
+      "grad_norm": 0.6732165217399597,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.9592,
+      "step": 33
+    },
+    {
+      "epoch": 0.31336405529953915,
+      "grad_norm": 0.8087509870529175,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 1.2257,
+      "step": 34
+    },
+    {
+      "epoch": 0.3225806451612903,
+      "grad_norm": 0.7753763794898987,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 1.1163,
+      "step": 35
+    },
+    {
+      "epoch": 0.3317972350230415,
+      "grad_norm": 0.896714448928833,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 1.1567,
+      "step": 36
+    },
+    {
+      "epoch": 0.3317972350230415,
+      "eval_loss": 1.049620270729065,
+      "eval_runtime": 11.0483,
+      "eval_samples_per_second": 8.327,
+      "eval_steps_per_second": 1.086,
+      "step": 36
+    },
+    {
+      "epoch": 0.34101382488479265,
+      "grad_norm": 0.9242726564407349,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 1.2014,
+      "step": 37
+    },
+    {
+      "epoch": 0.35023041474654376,
+      "grad_norm": 0.7677705883979797,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.9391,
+      "step": 38
+    },
+    {
+      "epoch": 0.35944700460829493,
+      "grad_norm": 1.0923584699630737,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 1.0083,
+      "step": 39
+    },
+    {
+      "epoch": 0.3686635944700461,
+      "grad_norm": 0.5865107178688049,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.0555,
+      "step": 40
+    },
+    {
+      "epoch": 0.3778801843317972,
+      "grad_norm": 0.8392916321754456,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 1.1126,
+      "step": 41
+    },
+    {
+      "epoch": 0.3870967741935484,
+      "grad_norm": 0.7484853863716125,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 1.1251,
+      "step": 42
+    },
+    {
+      "epoch": 0.39631336405529954,
+      "grad_norm": 0.9701381921768188,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 1.268,
+      "step": 43
+    },
+    {
+      "epoch": 0.4055299539170507,
+      "grad_norm": 0.901788055896759,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 1.1903,
+      "step": 44
+    },
+    {
+      "epoch": 0.4147465437788018,
+      "grad_norm": 0.516913890838623,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.9569,
+      "step": 45
+    },
+    {
+      "epoch": 0.4147465437788018,
+      "eval_loss": 1.0289723873138428,
+      "eval_runtime": 11.0778,
+      "eval_samples_per_second": 8.305,
+      "eval_steps_per_second": 1.083,
+      "step": 45
+    },
+    {
+      "epoch": 0.423963133640553,
+      "grad_norm": 0.6888841390609741,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.1008,
+      "step": 46
+    },
+    {
+      "epoch": 0.43317972350230416,
+      "grad_norm": 0.8466167449951172,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 1.1525,
+      "step": 47
+    },
+    {
+      "epoch": 0.4423963133640553,
+      "grad_norm": 0.7238967418670654,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.9355,
+      "step": 48
+    },
+    {
+      "epoch": 0.45161290322580644,
+      "grad_norm": 0.6457561254501343,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 1.0782,
+      "step": 49
+    },
+    {
+      "epoch": 0.4608294930875576,
+      "grad_norm": 0.6437515616416931,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.8966,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.966001301435187e+16,
+  "total_flos": 3.932002602870374e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null