Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:937c4bbae14e6955faa1efdb9ebf8fa8cc87fb502dc83cf7e99ee6b6b125dbd1
+oid sha256:1246faa961795035a9204657d541b49a7d51132e86cfa5118d22bf001e51d9b5
 size 247944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af8666bd9f13b067bad5fd22296fcbf6d474c694bc52cfdb2eee93d950e44962
+oid sha256:1c1de1e31a4a8b3820d2b3904da2b95e0876506f6c4a320c5a4ee5864f766b07
 size 501438

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0c59790f2e3ba0a4714a087914c6124ed7398fe25ca94de6ab9e0301a8e585f
+oid sha256:7f53083d6bf416fa674a4d7654c4dc44772d047f9fd45a1c2d70bd5cf789eb73
 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": 0.0016389748212493086,
+  "epoch": 0.002458462231873963,
   "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": 44.4028,
       "step": 18
+    },
+    {
+      "epoch": 0.001720923562311774,
+      "grad_norm": 1.2452588081359863,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 44.4156,
+      "step": 21
+    },
+    {
+      "epoch": 0.00196676978549917,
+      "grad_norm": 1.3686741590499878,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 44.3663,
+      "step": 24
+    },
+    {
+      "epoch": 0.00196676978549917,
+      "eval_loss": 11.100367546081543,
+      "eval_runtime": 25.1832,
+      "eval_samples_per_second": 204.025,
+      "eval_steps_per_second": 102.012,
+      "step": 24
+    },
+    {
+      "epoch": 0.0022126160086865664,
+      "grad_norm": 1.308458924293518,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 44.3951,
+      "step": 27
+    },
+    {
+      "epoch": 0.002458462231873963,
+      "grad_norm": 1.25251042842865,
+      "learning_rate": 0.0,
+      "loss": 44.399,
+      "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": 415991070720.0,
+  "total_flos": 623986606080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null