Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e9461f145c4a7fc1ed9ac5d93fce0db5ed6267d4805fc04d67c8d16a395963b
+oid sha256:d361f722689a6c0f347aeb5f528f3d441589056395c0d91f0fd78f22a7aa84e5
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c0505071d3eef5486e0adb7de4bc50e2ded3ef8408f98b10e2409b231b7402a
+oid sha256:09f3f7f407e922bb7bbb38827750059f8eb3e41224c40787be68796549935b7e
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6d6eaf276fdf021006f90bf821ce46a64808e39f4e0c975649dc880600155fc
+oid sha256:cad57760029cf28563e59df0d6afdcc3b95ff86cb77fe0cab8e460b3d873d363
 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": 0.015206812652068127,
+  "epoch": 0.030413625304136254,
   "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": 1.5088,
       "step": 25
+    },
+    {
+      "epoch": 0.015815085158150853,
+      "grad_norm": 5.111483573913574,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 1.0722,
+      "step": 26
+    },
+    {
+      "epoch": 0.016423357664233577,
+      "grad_norm": 6.778738498687744,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 1.4215,
+      "step": 27
+    },
+    {
+      "epoch": 0.016423357664233577,
+      "eval_loss": 0.6313769221305847,
+      "eval_runtime": 251.1945,
+      "eval_samples_per_second": 5.514,
+      "eval_steps_per_second": 0.693,
+      "step": 27
+    },
+    {
+      "epoch": 0.0170316301703163,
+      "grad_norm": 5.726966381072998,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.2793,
+      "step": 28
+    },
+    {
+      "epoch": 0.017639902676399026,
+      "grad_norm": 9.59007453918457,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 1.0635,
+      "step": 29
+    },
+    {
+      "epoch": 0.01824817518248175,
+      "grad_norm": 7.323919296264648,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 1.2779,
+      "step": 30
+    },
+    {
+      "epoch": 0.018856447688564478,
+      "grad_norm": 9.515922546386719,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 2.2738,
+      "step": 31
+    },
+    {
+      "epoch": 0.019464720194647202,
+      "grad_norm": 6.336705207824707,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.897,
+      "step": 32
+    },
+    {
+      "epoch": 0.020072992700729927,
+      "grad_norm": 4.728940963745117,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.9216,
+      "step": 33
+    },
+    {
+      "epoch": 0.02068126520681265,
+      "grad_norm": 5.460188865661621,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 1.0803,
+      "step": 34
+    },
+    {
+      "epoch": 0.021289537712895375,
+      "grad_norm": 5.335496425628662,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 1.2525,
+      "step": 35
+    },
+    {
+      "epoch": 0.021897810218978103,
+      "grad_norm": 7.545004844665527,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.9629,
+      "step": 36
+    },
+    {
+      "epoch": 0.021897810218978103,
+      "eval_loss": 0.5044350624084473,
+      "eval_runtime": 251.2533,
+      "eval_samples_per_second": 5.512,
+      "eval_steps_per_second": 0.693,
+      "step": 36
+    },
+    {
+      "epoch": 0.022506082725060828,
+      "grad_norm": 8.623957633972168,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 1.3611,
+      "step": 37
+    },
+    {
+      "epoch": 0.023114355231143552,
+      "grad_norm": 4.0373735427856445,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.5133,
+      "step": 38
+    },
+    {
+      "epoch": 0.023722627737226276,
+      "grad_norm": 5.937623500823975,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 1.0959,
+      "step": 39
+    },
+    {
+      "epoch": 0.024330900243309004,
+      "grad_norm": 4.628834247589111,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.612,
+      "step": 40
+    },
+    {
+      "epoch": 0.024939172749391728,
+      "grad_norm": 4.886986255645752,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 1.1789,
+      "step": 41
+    },
+    {
+      "epoch": 0.025547445255474453,
+      "grad_norm": 6.197083950042725,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 1.2511,
+      "step": 42
+    },
+    {
+      "epoch": 0.026155717761557177,
+      "grad_norm": 4.846970558166504,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.7351,
+      "step": 43
+    },
+    {
+      "epoch": 0.0267639902676399,
+      "grad_norm": 19.016860961914062,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 1.2659,
+      "step": 44
+    },
+    {
+      "epoch": 0.02737226277372263,
+      "grad_norm": 5.002533435821533,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.974,
+      "step": 45
+    },
+    {
+      "epoch": 0.02737226277372263,
+      "eval_loss": 0.501889705657959,
+      "eval_runtime": 251.1579,
+      "eval_samples_per_second": 5.514,
+      "eval_steps_per_second": 0.693,
+      "step": 45
+    },
+    {
+      "epoch": 0.027980535279805353,
+      "grad_norm": 16.9000301361084,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.1102,
+      "step": 46
+    },
+    {
+      "epoch": 0.028588807785888078,
+      "grad_norm": 4.386449813842773,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 0.7829,
+      "step": 47
+    },
+    {
+      "epoch": 0.029197080291970802,
+      "grad_norm": 3.59611177444458,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.7655,
+      "step": 48
+    },
+    {
+      "epoch": 0.029805352798053526,
+      "grad_norm": 4.8466668128967285,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.9544,
+      "step": 49
+    },
+    {
+      "epoch": 0.030413625304136254,
+      "grad_norm": 4.518596649169922,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.6498,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.26729100951552e+16,
+  "total_flos": 6.53458201903104e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null