Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:241e36aa4e2b4e65686d74de6cb59e577a2314b034679fb2dd07aa0082ca4494
+oid sha256:44ac7708c2f713ea6a2c9493841a362d0001ab982b6d778d424e3f994eddc4eb
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbdba28c2035ed9ecdaa1ee131176f190f907bfa69509de83346bdc186b21df9
+oid sha256:1cffc8f8ab2b83373137831c79ae5a4625811838d82d22c3f068b0bc56fbeee8
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c32871ed367fbfce842fc140e0a7e8cd760b068dd07514dcbc3cbab9304e7efd
+oid sha256:02a02c6e1e5039e685015f9532b801dd762ac99b4c55df43aefb88cfdbccca3e
 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": 0.0003900517306107723,
+  "epoch": 0.0005850775959161584,
   "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": 10.7769,
       "step": 18
+    },
+    {
+      "epoch": 0.00040955431714131084,
+      "grad_norm": 16.416988372802734,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 10.6507,
+      "step": 21
+    },
+    {
+      "epoch": 0.0004680620767329267,
+      "grad_norm": 13.546721458435059,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 11.2692,
+      "step": 24
+    },
+    {
+      "epoch": 0.0004680620767329267,
+      "eval_loss": 2.682469129562378,
+      "eval_runtime": 1467.7144,
+      "eval_samples_per_second": 14.71,
+      "eval_steps_per_second": 7.355,
+      "step": 24
+    },
+    {
+      "epoch": 0.0005265698363245426,
+      "grad_norm": 16.323583602905273,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 10.9527,
+      "step": 27
+    },
+    {
+      "epoch": 0.0005850775959161584,
+      "grad_norm": 13.710123062133789,
+      "learning_rate": 0.0,
+      "loss": 11.1326,
+      "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": 7031294986813440.0,
+  "total_flos": 1.054694248022016e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null