Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ef0d92a9d9cc6333f0de2ee09c73fda4362739b96219ea37dad5f061ab3fa0a
+oid sha256:e85439816c13f82136da2e9aef77896e40fa719796866d1858673100928b8def
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81d564364eb846e4c5cf03b42b4356c598872e84266894a76c497e20c8f558ef
+oid sha256:840b3da3a1ba26088d1a4a2c871c6a5ec9c1620a5f85487868fbf29818572f2c
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:100a98efda01deac0d9d0ec043e13e0ceab192c7fc1329dd719aa17191cede2e
+oid sha256:197f791b66ede35de0172ab30f4461f6ed1a4b36c3f6ac0e248c3af1e5aa1c2d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0009367133071834201,
+  "epoch": 0.0014050699607751304,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 6.545084971874738e-05,
       "loss": 1.012,
       "step": 18
+    },
+    {
+      "epoch": 0.0009835489725425913,
+      "grad_norm": 0.5412721633911133,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.929,
+      "step": 21
+    },
+    {
+      "epoch": 0.0011240559686201042,
+      "grad_norm": 0.6460533142089844,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.9141,
+      "step": 24
+    },
+    {
+      "epoch": 0.0011240559686201042,
+      "eval_loss": 0.9949507713317871,
+      "eval_runtime": 1197.3016,
+      "eval_samples_per_second": 7.509,
+      "eval_steps_per_second": 3.754,
+      "step": 24
+    },
+    {
+      "epoch": 0.0012645629646976173,
+      "grad_norm": 0.49220025539398193,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.9051,
+      "step": 27
+    },
+    {
+      "epoch": 0.0014050699607751304,
+      "grad_norm": 0.7920961380004883,
+      "learning_rate": 0.0,
+      "loss": 0.937,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7697080566939648.0,
+  "total_flos": 1.1499252895186944e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null