Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e57cfec7fa5b6dc86f84b7a747b908d5e0ccb5c9108674b236f4c0f27bf502d
+oid sha256:5fa9630f889fdb7864d9e5b6a22db9ee4d35d21e12cf87bca99fe9455dffb6d0
 size 247944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6aea4d13feb9a156fc9ee45bd2fc54fcb9cf562531e20a3a6a42ddfc17a68f72
+oid sha256:e578fbba6e1fbf99d150a81c197216e1097ad5d33fc89851b63167a4e31096f0
 size 505518

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:608488dcaf4515c2d3f93963e503554ea2e0ff15a5daf1091cffc2d71884636c
+oid sha256:d221886497b5a7a3e66091d1d23f488449308e75ebdbae8631c8d7478838679a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.018996960486322188,
+  "epoch": 0.037993920972644375,
   "eval_steps": 5,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,221 @@
       "eval_samples_per_second": 115.772,
       "eval_steps_per_second": 14.524,
       "step": 25
+    },
+    {
+      "epoch": 0.019756838905775075,
+      "grad_norm": 0.966887891292572,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 22.063,
+      "step": 26
+    },
+    {
+      "epoch": 0.020516717325227963,
+      "grad_norm": 1.0077238082885742,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 22.0584,
+      "step": 27
+    },
+    {
+      "epoch": 0.02127659574468085,
+      "grad_norm": 0.9766594171524048,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 22.0625,
+      "step": 28
+    },
+    {
+      "epoch": 0.022036474164133738,
+      "grad_norm": 0.9364005327224731,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 22.0474,
+      "step": 29
+    },
+    {
+      "epoch": 0.022796352583586626,
+      "grad_norm": 1.0432188510894775,
+      "learning_rate": 5e-05,
+      "loss": 22.0193,
+      "step": 30
+    },
+    {
+      "epoch": 0.022796352583586626,
+      "eval_loss": 11.019878387451172,
+      "eval_runtime": 9.1273,
+      "eval_samples_per_second": 121.394,
+      "eval_steps_per_second": 15.229,
+      "step": 30
+    },
+    {
+      "epoch": 0.023556231003039513,
+      "grad_norm": 0.990106463432312,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 22.0551,
+      "step": 31
+    },
+    {
+      "epoch": 0.0243161094224924,
+      "grad_norm": 0.9892701506614685,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 22.0255,
+      "step": 32
+    },
+    {
+      "epoch": 0.02507598784194529,
+      "grad_norm": 1.0256024599075317,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 22.0296,
+      "step": 33
+    },
+    {
+      "epoch": 0.025835866261398176,
+      "grad_norm": 0.9178345203399658,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 22.0515,
+      "step": 34
+    },
+    {
+      "epoch": 0.026595744680851064,
+      "grad_norm": 1.0213465690612793,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 22.046,
+      "step": 35
+    },
+    {
+      "epoch": 0.026595744680851064,
+      "eval_loss": 11.006331443786621,
+      "eval_runtime": 9.6408,
+      "eval_samples_per_second": 114.929,
+      "eval_steps_per_second": 14.418,
+      "step": 35
+    },
+    {
+      "epoch": 0.02735562310030395,
+      "grad_norm": 1.0454298257827759,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 22.0217,
+      "step": 36
+    },
+    {
+      "epoch": 0.02811550151975684,
+      "grad_norm": 1.0446940660476685,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 21.9847,
+      "step": 37
+    },
+    {
+      "epoch": 0.028875379939209727,
+      "grad_norm": 1.061407446861267,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 22.0118,
+      "step": 38
+    },
+    {
+      "epoch": 0.029635258358662615,
+      "grad_norm": 1.0344719886779785,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 21.9994,
+      "step": 39
+    },
+    {
+      "epoch": 0.030395136778115502,
+      "grad_norm": 1.0409643650054932,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 22.0019,
+      "step": 40
+    },
+    {
+      "epoch": 0.030395136778115502,
+      "eval_loss": 10.998189926147461,
+      "eval_runtime": 9.3925,
+      "eval_samples_per_second": 117.967,
+      "eval_steps_per_second": 14.799,
+      "step": 40
+    },
+    {
+      "epoch": 0.03115501519756839,
+      "grad_norm": 1.0946383476257324,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 21.9642,
+      "step": 41
+    },
+    {
+      "epoch": 0.031914893617021274,
+      "grad_norm": 1.0578166246414185,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 21.9906,
+      "step": 42
+    },
+    {
+      "epoch": 0.03267477203647416,
+      "grad_norm": 1.0239158868789673,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 21.9779,
+      "step": 43
+    },
+    {
+      "epoch": 0.03343465045592705,
+      "grad_norm": 1.0567377805709839,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 21.9981,
+      "step": 44
+    },
+    {
+      "epoch": 0.03419452887537994,
+      "grad_norm": 1.0055408477783203,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 22.0115,
+      "step": 45
+    },
+    {
+      "epoch": 0.03419452887537994,
+      "eval_loss": 10.994943618774414,
+      "eval_runtime": 9.5858,
+      "eval_samples_per_second": 115.587,
+      "eval_steps_per_second": 14.501,
+      "step": 45
+    },
+    {
+      "epoch": 0.034954407294832825,
+      "grad_norm": 1.1111423969268799,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 21.9687,
+      "step": 46
+    },
+    {
+      "epoch": 0.03571428571428571,
+      "grad_norm": 1.0502803325653076,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 21.985,
+      "step": 47
+    },
+    {
+      "epoch": 0.0364741641337386,
+      "grad_norm": 0.9838832020759583,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 21.9997,
+      "step": 48
+    },
+    {
+      "epoch": 0.03723404255319149,
+      "grad_norm": 1.068258285522461,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 21.9884,
+      "step": 49
+    },
+    {
+      "epoch": 0.037993920972644375,
+      "grad_norm": 1.0668437480926514,
+      "learning_rate": 0.0,
+      "loss": 21.9595,
+      "step": 50
+    },
+    {
+      "epoch": 0.037993920972644375,
+      "eval_loss": 10.994412422180176,
+      "eval_runtime": 9.4009,
+      "eval_samples_per_second": 117.861,
+      "eval_steps_per_second": 14.786,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -244,12 +459,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1081576783872.0,
+  "total_flos": 2121554460672.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null