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:cc8f0c190e4a56bc322dc3399efcf62e0cbaf013e5291d2dc4749ee7fb6ad25c
+oid sha256:90b705367bba234bb5c75934f4b99bf161163d8280cfd590ce94d97b6d97c81f
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a67088a3e63a04b22420540d43c875cad6de2c0bda16803d205a6d06d9c0b37f
+oid sha256:0ee4e0e698b77fe5d6e411e20649bd406714ffffeee5c115e31c4dba5027a1df
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:117bcf297abcf03ea5cc0e187dccdcc9d88da67477eb38df2d3754b727a1e0d5
+oid sha256:3b4131a509b6b42b66684092460d46c4fc36a71b60f6f4d6445b1dba91068a01
 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": 0.04975124378109453,
+  "epoch": 0.09950248756218906,
   "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": 7.986,
       "eval_steps_per_second": 1.001,
       "step": 25
+    },
+    {
+      "epoch": 0.051741293532338306,
+      "grad_norm": 3.5864768028259277,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.7563,
+      "step": 26
+    },
+    {
+      "epoch": 0.05373134328358209,
+      "grad_norm": 3.2884480953216553,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 2.4898,
+      "step": 27
+    },
+    {
+      "epoch": 0.05572139303482587,
+      "grad_norm": 3.3325111865997314,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 2.7511,
+      "step": 28
+    },
+    {
+      "epoch": 0.05771144278606965,
+      "grad_norm": 3.520771026611328,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 2.5736,
+      "step": 29
+    },
+    {
+      "epoch": 0.05970149253731343,
+      "grad_norm": 3.5022075176239014,
+      "learning_rate": 5e-05,
+      "loss": 2.7136,
+      "step": 30
+    },
+    {
+      "epoch": 0.05970149253731343,
+      "eval_loss": 1.250102162361145,
+      "eval_runtime": 52.9746,
+      "eval_samples_per_second": 7.985,
+      "eval_steps_per_second": 1.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.061691542288557215,
+      "grad_norm": 3.329467296600342,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 2.3554,
+      "step": 31
+    },
+    {
+      "epoch": 0.06368159203980099,
+      "grad_norm": 2.840151071548462,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 2.4211,
+      "step": 32
+    },
+    {
+      "epoch": 0.06567164179104477,
+      "grad_norm": 3.219452381134033,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 2.6979,
+      "step": 33
+    },
+    {
+      "epoch": 0.06766169154228856,
+      "grad_norm": 3.7276501655578613,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.6547,
+      "step": 34
+    },
+    {
+      "epoch": 0.06965174129353234,
+      "grad_norm": 3.3804147243499756,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.525,
+      "step": 35
+    },
+    {
+      "epoch": 0.06965174129353234,
+      "eval_loss": 1.2339178323745728,
+      "eval_runtime": 52.9732,
+      "eval_samples_per_second": 7.985,
+      "eval_steps_per_second": 1.001,
+      "step": 35
+    },
+    {
+      "epoch": 0.07164179104477612,
+      "grad_norm": 3.1214122772216797,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 2.5263,
+      "step": 36
+    },
+    {
+      "epoch": 0.0736318407960199,
+      "grad_norm": 3.337712049484253,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 2.6071,
+      "step": 37
+    },
+    {
+      "epoch": 0.07562189054726368,
+      "grad_norm": 3.190777540206909,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.2989,
+      "step": 38
+    },
+    {
+      "epoch": 0.07761194029850746,
+      "grad_norm": 3.186429977416992,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 2.39,
+      "step": 39
+    },
+    {
+      "epoch": 0.07960199004975124,
+      "grad_norm": 3.9558160305023193,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.7493,
+      "step": 40
+    },
+    {
+      "epoch": 0.07960199004975124,
+      "eval_loss": 1.2219856977462769,
+      "eval_runtime": 52.9723,
+      "eval_samples_per_second": 7.985,
+      "eval_steps_per_second": 1.001,
+      "step": 40
+    },
+    {
+      "epoch": 0.08159203980099503,
+      "grad_norm": 3.221808671951294,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 2.4962,
+      "step": 41
+    },
+    {
+      "epoch": 0.08358208955223881,
+      "grad_norm": 3.636087656021118,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.6025,
+      "step": 42
+    },
+    {
+      "epoch": 0.08557213930348259,
+      "grad_norm": 3.114062547683716,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 2.82,
+      "step": 43
+    },
+    {
+      "epoch": 0.08756218905472637,
+      "grad_norm": 3.6059587001800537,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 2.4225,
+      "step": 44
+    },
+    {
+      "epoch": 0.08955223880597014,
+      "grad_norm": 3.2046148777008057,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.2631,
+      "step": 45
+    },
+    {
+      "epoch": 0.08955223880597014,
+      "eval_loss": 1.216843605041504,
+      "eval_runtime": 52.9723,
+      "eval_samples_per_second": 7.985,
+      "eval_steps_per_second": 1.001,
+      "step": 45
+    },
+    {
+      "epoch": 0.09154228855721393,
+      "grad_norm": 3.014789342880249,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.2711,
+      "step": 46
+    },
+    {
+      "epoch": 0.09353233830845771,
+      "grad_norm": 3.0080182552337646,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 2.4075,
+      "step": 47
+    },
+    {
+      "epoch": 0.0955223880597015,
+      "grad_norm": 3.5312676429748535,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 2.5651,
+      "step": 48
+    },
+    {
+      "epoch": 0.09751243781094528,
+      "grad_norm": 3.9376723766326904,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 2.5869,
+      "step": 49
+    },
+    {
+      "epoch": 0.09950248756218906,
+      "grad_norm": 3.390911102294922,
+      "learning_rate": 0.0,
+      "loss": 2.4581,
+      "step": 50
+    },
+    {
+      "epoch": 0.09950248756218906,
+      "eval_loss": 1.215503454208374,
+      "eval_runtime": 52.9683,
+      "eval_samples_per_second": 7.986,
+      "eval_steps_per_second": 1.001,
+      "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": 1.75782374670336e+16,
+  "total_flos": 3.51564749340672e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null