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:b52befc52d8cdb9d6e78ea4e7562650ebba56cbd30825ce3ffe8da7595284643
+oid sha256:36a75c95b5aa5cbd938d68b35da3fcd50cc4a17e9a3a1a3b5b722b9c0dd47fe3
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d1766b3c7ba1f66470dd9ac918cc6384031db9779170a8b1113a605c3efa20a
+oid sha256:9f375b4408b6af3d228fa080ea22911a918cc4147b4e684b0dc75a73f51b3576
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0160325f3cfb2789544f924daf3b9721842346abd05e8dbfa142d277b468e99a
+oid sha256:ff117b2b37bde812847adc6eed8bdc759c3c07f5d1cbee1f5506533e03306f92
 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": 0.002891844997108155,
+  "epoch": 0.00578368999421631,
   "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": 1.3508,
       "step": 25
+    },
+    {
+      "epoch": 0.0030075187969924814,
+      "grad_norm": 0.6465054154396057,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 1.2657,
+      "step": 26
+    },
+    {
+      "epoch": 0.0031231925968768074,
+      "grad_norm": 0.6023719906806946,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 1.4483,
+      "step": 27
+    },
+    {
+      "epoch": 0.0031231925968768074,
+      "eval_loss": 1.3892802000045776,
+      "eval_runtime": 740.4541,
+      "eval_samples_per_second": 9.832,
+      "eval_steps_per_second": 1.229,
+      "step": 27
+    },
+    {
+      "epoch": 0.0032388663967611335,
+      "grad_norm": 0.46956098079681396,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.2895,
+      "step": 28
+    },
+    {
+      "epoch": 0.00335454019664546,
+      "grad_norm": 0.5599877834320068,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 1.3907,
+      "step": 29
+    },
+    {
+      "epoch": 0.003470213996529786,
+      "grad_norm": 0.6060083508491516,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 1.398,
+      "step": 30
+    },
+    {
+      "epoch": 0.003585887796414112,
+      "grad_norm": 0.9557406902313232,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 1.4978,
+      "step": 31
+    },
+    {
+      "epoch": 0.0037015615962984385,
+      "grad_norm": 0.575370728969574,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 1.4165,
+      "step": 32
+    },
+    {
+      "epoch": 0.0038172353961827645,
+      "grad_norm": 0.7410251498222351,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 1.3919,
+      "step": 33
+    },
+    {
+      "epoch": 0.003932909196067091,
+      "grad_norm": 0.5126181244850159,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 1.3076,
+      "step": 34
+    },
+    {
+      "epoch": 0.004048582995951417,
+      "grad_norm": 0.5956414937973022,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 1.3227,
+      "step": 35
+    },
+    {
+      "epoch": 0.0041642567958357435,
+      "grad_norm": 0.6212967038154602,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 1.2832,
+      "step": 36
+    },
+    {
+      "epoch": 0.0041642567958357435,
+      "eval_loss": 1.3439499139785767,
+      "eval_runtime": 744.255,
+      "eval_samples_per_second": 9.782,
+      "eval_steps_per_second": 1.223,
+      "step": 36
+    },
+    {
+      "epoch": 0.004279930595720069,
+      "grad_norm": 0.5324627757072449,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 1.318,
+      "step": 37
+    },
+    {
+      "epoch": 0.004395604395604396,
+      "grad_norm": 0.5703225135803223,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 1.5839,
+      "step": 38
+    },
+    {
+      "epoch": 0.004511278195488722,
+      "grad_norm": 0.7628889679908752,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 1.517,
+      "step": 39
+    },
+    {
+      "epoch": 0.004626951995373048,
+      "grad_norm": 1.1482807397842407,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.7088,
+      "step": 40
+    },
+    {
+      "epoch": 0.004742625795257374,
+      "grad_norm": 0.4733085036277771,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 1.3973,
+      "step": 41
+    },
+    {
+      "epoch": 0.004858299595141701,
+      "grad_norm": 0.7030467391014099,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 1.3371,
+      "step": 42
+    },
+    {
+      "epoch": 0.004973973395026026,
+      "grad_norm": 0.46287447214126587,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 1.2644,
+      "step": 43
+    },
+    {
+      "epoch": 0.005089647194910353,
+      "grad_norm": 0.482746958732605,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 1.3177,
+      "step": 44
+    },
+    {
+      "epoch": 0.005205320994794679,
+      "grad_norm": 0.4805569350719452,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 1.4233,
+      "step": 45
+    },
+    {
+      "epoch": 0.005205320994794679,
+      "eval_loss": 1.320542812347412,
+      "eval_runtime": 742.5308,
+      "eval_samples_per_second": 9.804,
+      "eval_steps_per_second": 1.226,
+      "step": 45
+    },
+    {
+      "epoch": 0.005320994794679005,
+      "grad_norm": 0.6398974657058716,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.3809,
+      "step": 46
+    },
+    {
+      "epoch": 0.005436668594563331,
+      "grad_norm": 0.7115899920463562,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 1.4922,
+      "step": 47
+    },
+    {
+      "epoch": 0.005552342394447658,
+      "grad_norm": 0.539852499961853,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 1.1924,
+      "step": 48
+    },
+    {
+      "epoch": 0.005668016194331984,
+      "grad_norm": 0.47398844361305237,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 1.2039,
+      "step": 49
+    },
+    {
+      "epoch": 0.00578368999421631,
+      "grad_norm": 0.6044884324073792,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 1.3744,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6527352922112e+16,
+  "total_flos": 3.3054705844224e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null