Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57031e9ff8caf7c36e19cc63d80889954e3d549787916a61a34c1309c71f2291
+oid sha256:9135a5768c1ed5d7d1d04c0db3392c5c3e612ba98172748d1e48039acbb8fffb
 size 25192592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:336712cf58fd73ae147bfec827e8b7b058071623b9ab76d81b30247103c0c8fb
+oid sha256:6579645b2ece171482de6947dc1209c034cb858cf6315748d25361d17b11227d
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19a32067fb5f557237726e10d4e5248eee478b9f21bf82db1c657e481f64a127
+oid sha256:0a2ba38d61cd6275d77c5204447109dd9eddc38992e480ed671e0d925609356b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef527702b4e2147a500c0b29beb26751d245ebb60338b3910b449b6549ac4d59
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006963788300835654,
+  "epoch": 0.013927576601671309,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,65 @@
       "eval_samples_per_second": 77.602,
       "eval_steps_per_second": 38.844,
       "step": 15
+    },
+    {
+      "epoch": 0.008356545961002786,
+      "grad_norm": 35.8166618347168,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 8.8082,
+      "step": 18
+    },
+    {
+      "epoch": 0.009285051067780872,
+      "eval_loss": 2.1811230182647705,
+      "eval_runtime": 11.73,
+      "eval_samples_per_second": 77.323,
+      "eval_steps_per_second": 38.704,
+      "step": 20
+    },
+    {
+      "epoch": 0.009749303621169917,
+      "grad_norm": 36.95984649658203,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 8.5593,
+      "step": 21
+    },
+    {
+      "epoch": 0.011142061281337047,
+      "grad_norm": 59.03194808959961,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 9.4143,
+      "step": 24
+    },
+    {
+      "epoch": 0.01160631383472609,
+      "eval_loss": 2.1778345108032227,
+      "eval_runtime": 11.6534,
+      "eval_samples_per_second": 77.831,
+      "eval_steps_per_second": 38.958,
+      "step": 25
+    },
+    {
+      "epoch": 0.012534818941504178,
+      "grad_norm": 35.66450881958008,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 8.5712,
+      "step": 27
+    },
+    {
+      "epoch": 0.013927576601671309,
+      "grad_norm": 46.05991744995117,
+      "learning_rate": 0.0,
+      "loss": 8.6996,
+      "step": 30
+    },
+    {
+      "epoch": 0.013927576601671309,
+      "eval_loss": 2.1666736602783203,
+      "eval_runtime": 11.7607,
+      "eval_samples_per_second": 77.121,
+      "eval_steps_per_second": 38.603,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -88,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 265504979681280.0,
+  "total_flos": 531009959362560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null