Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e82a9e0ac7252170256e34dec70937d19d19e24804a7cc96b0f317e43f7a22b
+oid sha256:573556e4158509af3b7fad601117af002f3b04b3c2d4588b9c06866c4f850882
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e533e070f8196d75fa4a15cccaa1551b99f6c43bdffa0f3ce96fe472fc0d2d67
+oid sha256:669f480eb165da0c7d70ee6c77e8535ea22418161fade0a197b84d1ad905d4a8
 size 400264058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e214e866b1d74f7e464cb6a2e678a00e1dfe391c9317136d872b47c2ee9a12a
+oid sha256:803988d8f78e28f0bbf5b0e853b0fea54bcf1036578f67b315e74390a29fb73f
 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": 0.019603038470963,
+  "epoch": 0.029404557706444498,
   "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": 1.202,
       "step": 18
+    },
+    {
+      "epoch": 0.02058319039451115,
+      "grad_norm": 1.691860556602478,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.2074,
+      "step": 21
+    },
+    {
+      "epoch": 0.0235236461651556,
+      "grad_norm": 1.7501243352890015,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.195,
+      "step": 24
+    },
+    {
+      "epoch": 0.0235236461651556,
+      "eval_loss": 1.148852825164795,
+      "eval_runtime": 120.4004,
+      "eval_samples_per_second": 3.571,
+      "eval_steps_per_second": 1.786,
+      "step": 24
+    },
+    {
+      "epoch": 0.02646410193580005,
+      "grad_norm": 1.4713298082351685,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.1689,
+      "step": 27
+    },
+    {
+      "epoch": 0.029404557706444498,
+      "grad_norm": 1.6153112649917603,
+      "learning_rate": 0.0,
+      "loss": 1.0901,
+      "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": 7668943615426560.0,
+  "total_flos": 1.150341542313984e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null