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:d999dd4148687ca52dc136e9ffa5fe7dcf8f64ba15b666393a0aa825fdfe996f
+oid sha256:a5e0ef393b8ccf1f759942c74b8c7230f1f670c710b6794576cf6c7e9d15bcfc
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a39bb09a478e5946a479ea1f0c8a7159de7fe5a435b4a7b9341d29317af410d
+oid sha256:dee3359f0506728cd7d60cd8281e1b01aecf08b672da3154daa77c6065df26c0
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72e4872822d2d93a87125714a96799dd0dc0b91855c62fd49037073db7b6a96b
+oid sha256:157c88691792471b33282b60fcf3705aa24d5b1b292e459ec02f49d68ccb111f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007172084042113006,
+  "epoch": 0.00919497954117052,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 0.403,
       "step": 35
+    },
+    {
+      "epoch": 0.007355983632936417,
+      "grad_norm": 0.5382698178291321,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.3619,
+      "step": 40
+    },
+    {
+      "epoch": 0.007355983632936417,
+      "eval_loss": 0.34493008255958557,
+      "eval_runtime": 135.733,
+      "eval_samples_per_second": 16.871,
+      "eval_steps_per_second": 8.436,
+      "step": 40
+    },
+    {
+      "epoch": 0.00827548158705347,
+      "grad_norm": 0.4202958643436432,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.3533,
+      "step": 45
+    },
+    {
+      "epoch": 0.00919497954117052,
+      "grad_norm": 0.41728895902633667,
+      "learning_rate": 0.0,
+      "loss": 0.3192,
+      "step": 50
+    },
+    {
+      "epoch": 0.00919497954117052,
+      "eval_loss": 0.332812637090683,
+      "eval_runtime": 135.7386,
+      "eval_samples_per_second": 16.871,
+      "eval_steps_per_second": 8.435,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5412321188904960.0,
+  "total_flos": 6929411219128320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null