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:e377e62bfc5d72d6a2cb9adba4ae2db11933dd1a211ea3e61240ec99a8d6e2cf
+oid sha256:b9f1c40a02ba6f085e8eea4e121ccd287988ba647a2dcdf957afd529aeff1c40
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c97379af7963bb24d8a5112d45a147aadfdb77ef54095d2d65d1c4cb8af7a8e0
+oid sha256:b35d35f9589f924f212e935c6a962a59a1bce0d69c4ca1a23f300d7e2f086c90
 size 27273018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:959575122cbd9df9f3bf8a9fdfccd607d62a5f6a9ddc76bc1bf0eb2ab60a02af
+oid sha256:19e09a843cff3edec57c07364eb7d61752970c6995726aee3f57c1f3e8305536
 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": 0.012391573729863693,
+  "epoch": 0.024783147459727387,
   "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": 98.361,
       "eval_steps_per_second": 12.331,
       "step": 25
+    },
+    {
+      "epoch": 0.01288723667905824,
+      "grad_norm": 0.7884762287139893,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.0006,
+      "step": 26
+    },
+    {
+      "epoch": 0.013382899628252789,
+      "grad_norm": 0.6535519957542419,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 1.6955,
+      "step": 27
+    },
+    {
+      "epoch": 0.013878562577447335,
+      "grad_norm": 0.6614362597465515,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 1.7235,
+      "step": 28
+    },
+    {
+      "epoch": 0.014374225526641884,
+      "grad_norm": 0.569136917591095,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 1.6187,
+      "step": 29
+    },
+    {
+      "epoch": 0.01486988847583643,
+      "grad_norm": 0.8128046989440918,
+      "learning_rate": 5e-05,
+      "loss": 1.8391,
+      "step": 30
+    },
+    {
+      "epoch": 0.01486988847583643,
+      "eval_loss": 1.7055069208145142,
+      "eval_runtime": 17.3629,
+      "eval_samples_per_second": 97.852,
+      "eval_steps_per_second": 12.268,
+      "step": 30
+    },
+    {
+      "epoch": 0.015365551425030979,
+      "grad_norm": 0.5898133516311646,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 1.4803,
+      "step": 31
+    },
+    {
+      "epoch": 0.015861214374225528,
+      "grad_norm": 0.8634248375892639,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 1.9185,
+      "step": 32
+    },
+    {
+      "epoch": 0.016356877323420074,
+      "grad_norm": 0.7606371641159058,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 1.7444,
+      "step": 33
+    },
+    {
+      "epoch": 0.01685254027261462,
+      "grad_norm": 0.827926516532898,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.5359,
+      "step": 34
+    },
+    {
+      "epoch": 0.01734820322180917,
+      "grad_norm": 0.6055005192756653,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.3024,
+      "step": 35
+    },
+    {
+      "epoch": 0.01734820322180917,
+      "eval_loss": 1.6104322671890259,
+      "eval_runtime": 17.2589,
+      "eval_samples_per_second": 98.442,
+      "eval_steps_per_second": 12.341,
+      "step": 35
+    },
+    {
+      "epoch": 0.017843866171003718,
+      "grad_norm": 0.8044369220733643,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 1.5692,
+      "step": 36
+    },
+    {
+      "epoch": 0.018339529120198265,
+      "grad_norm": 0.6717920303344727,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 1.6285,
+      "step": 37
+    },
+    {
+      "epoch": 0.01883519206939281,
+      "grad_norm": 0.7943913340568542,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.5588,
+      "step": 38
+    },
+    {
+      "epoch": 0.019330855018587362,
+      "grad_norm": 0.7974594235420227,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 1.4334,
+      "step": 39
+    },
+    {
+      "epoch": 0.01982651796778191,
+      "grad_norm": 0.7847771048545837,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.6791,
+      "step": 40
+    },
+    {
+      "epoch": 0.01982651796778191,
+      "eval_loss": 1.5548481941223145,
+      "eval_runtime": 17.2904,
+      "eval_samples_per_second": 98.263,
+      "eval_steps_per_second": 12.319,
+      "step": 40
+    },
+    {
+      "epoch": 0.020322180916976455,
+      "grad_norm": 0.6804707050323486,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 1.5037,
+      "step": 41
+    },
+    {
+      "epoch": 0.020817843866171002,
+      "grad_norm": 0.8448418378829956,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.6357,
+      "step": 42
+    },
+    {
+      "epoch": 0.021313506815365552,
+      "grad_norm": 0.8616818189620972,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 1.5866,
+      "step": 43
+    },
+    {
+      "epoch": 0.0218091697645601,
+      "grad_norm": 0.6975346803665161,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 1.4729,
+      "step": 44
+    },
+    {
+      "epoch": 0.022304832713754646,
+      "grad_norm": 0.6911585927009583,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.3803,
+      "step": 45
+    },
+    {
+      "epoch": 0.022304832713754646,
+      "eval_loss": 1.5319888591766357,
+      "eval_runtime": 17.2847,
+      "eval_samples_per_second": 98.295,
+      "eval_steps_per_second": 12.323,
+      "step": 45
+    },
+    {
+      "epoch": 0.022800495662949196,
+      "grad_norm": 0.6003568172454834,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.4585,
+      "step": 46
+    },
+    {
+      "epoch": 0.023296158612143743,
+      "grad_norm": 0.7089613676071167,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 1.4629,
+      "step": 47
+    },
+    {
+      "epoch": 0.02379182156133829,
+      "grad_norm": 0.7499310970306396,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 1.4805,
+      "step": 48
+    },
+    {
+      "epoch": 0.024287484510532836,
+      "grad_norm": 0.7139114141464233,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 1.5951,
+      "step": 49
+    },
+    {
+      "epoch": 0.024783147459727387,
+      "grad_norm": 0.7746477127075195,
+      "learning_rate": 0.0,
+      "loss": 1.6068,
+      "step": 50
+    },
+    {
+      "epoch": 0.024783147459727387,
+      "eval_loss": 1.527747392654419,
+      "eval_runtime": 17.2729,
+      "eval_samples_per_second": 98.362,
+      "eval_steps_per_second": 12.331,
+      "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": 395687120338944.0,
+  "total_flos": 763606723461120.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null