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:ff3baa51f8808e76f5241ad19a67795e180ec1f8a290aa3b1541922bd2327a5e
+oid sha256:9d22f95e3cd88edc3757d7ca1c31409faf9f62a8e6ae82974371ae975ea0e92c
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8212e96422f95e6c2906e96211f4e5cfde0bdcbe2d576d1c47fe529a40a109e8
+oid sha256:f65f1dec5036641ecea6416b3ad62e338983a52ac5cdc65c7d2bec893cc4b579
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:590761e6940b8a5f51a47f69d09c8ece26c1a0fc061d07ca27ebdc6e6a55b220
+oid sha256:5c15ee7e64adbbed173bd6a1ced0d959828c8fd99015a2fee41e29d011347912
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0032665060634518802,
+  "epoch": 0.0048997590951778205,
   "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": 0.00013090169943749476,
       "loss": 1.3165,
       "step": 18
+    },
+    {
+      "epoch": 0.003429831366624474,
+      "grad_norm": 0.9563743472099304,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.3355,
+      "step": 21
+    },
+    {
+      "epoch": 0.003919807276142257,
+      "grad_norm": 0.9076368808746338,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.3107,
+      "step": 24
+    },
+    {
+      "epoch": 0.003919807276142257,
+      "eval_loss": 1.3322792053222656,
+      "eval_runtime": 151.5342,
+      "eval_samples_per_second": 17.013,
+      "eval_steps_per_second": 8.506,
+      "step": 24
+    },
+    {
+      "epoch": 0.004409783185660038,
+      "grad_norm": 0.8078122735023499,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.2538,
+      "step": 27
+    },
+    {
+      "epoch": 0.0048997590951778205,
+      "grad_norm": 0.8908748626708984,
+      "learning_rate": 0.0,
+      "loss": 1.2256,
+      "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": 7604344656494592.0,
+  "total_flos": 1.1406516984741888e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null