Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:171b08a44be9c8ffee3ddb5426b4d7d238d5446ce5cb9262c971732ce3d5f2fd
+oid sha256:d74aebb169fae8510ce21a387ab39c367518d709ba4048f2e8663db59fc6b4f7
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2240cfbe4d3d3c5ea2a3a19d750bcaed7df019114ca26220b6062338b81ad86f
+oid sha256:52e2726de411488c312d7ffe2d4703268a662313baae462ba42a058534ae6e0f
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7b129ffce73c9907cc210368645c9a213a1d6ddd30ccdbc9e0f80ffaa10e696
+oid sha256:453c5000accfa50f72860edda190cbbb271eefba034f6186bba1a482bf7eb187
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65558e26afbfb87dd1928966282919939bdee4084add607d42e008ed52d680cd
+oid sha256:6088f970b1f0429ad85e576795204ef9269ce142d6ce9c2595b5649efde833b6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.026257293692692415,
+  "epoch": 0.03473186996387886,
   "eval_steps": 63,
-  "global_step": 189,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -165,6 +165,55 @@
       "eval_samples_per_second": 9.299,
       "eval_steps_per_second": 4.651,
       "step": 189
+    },
+    {
+      "epoch": 0.02639622117254793,
+      "grad_norm": 1.2719013690948486,
+      "learning_rate": 2.8165064990227252e-05,
+      "loss": 3.3775,
+      "step": 190
+    },
+    {
+      "epoch": 0.027785495971103084,
+      "grad_norm": 1.359384536743164,
+      "learning_rate": 1.985863781320435e-05,
+      "loss": 3.3751,
+      "step": 200
+    },
+    {
+      "epoch": 0.02917477076965824,
+      "grad_norm": 1.3881595134735107,
+      "learning_rate": 1.286812958766106e-05,
+      "loss": 3.7558,
+      "step": 210
+    },
+    {
+      "epoch": 0.03056404556821339,
+      "grad_norm": 1.2139527797698975,
+      "learning_rate": 7.308324265397836e-06,
+      "loss": 3.6978,
+      "step": 220
+    },
+    {
+      "epoch": 0.031953320366768546,
+      "grad_norm": 1.2041010856628418,
+      "learning_rate": 3.270513696097055e-06,
+      "loss": 3.7233,
+      "step": 230
+    },
+    {
+      "epoch": 0.0333425951653237,
+      "grad_norm": 3.732804536819458,
+      "learning_rate": 8.209986176753948e-07,
+      "loss": 3.6758,
+      "step": 240
+    },
+    {
+      "epoch": 0.03473186996387886,
+      "grad_norm": 1.107755422592163,
+      "learning_rate": 0.0,
+      "loss": 3.7334,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -179,12 +228,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.1485478667681792e+17,
+  "total_flos": 1.5182045544185856e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null