Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70755a26ce2f813457fb5ce83c2413e83c5a526ee2dc3bb26c0732e26034b407
+oid sha256:ed4ba09f3d935f5f87daf7a56ad9a3a13365be013f8d543b47843ffa86ba3e8f
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de79212b1d977ccfbd456ba74db5d98833bc44779f0d28d59d7aa1b24d55b557
+oid sha256:ba3b44f5320f25e7e50e70b22ea6ea52a9c73b6ea0958d78595aa00d18a24e50
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d1b8821978c7450bd2cb49e068182933549eb330933b29022697a95533c47a4
+oid sha256:8dd60e9ba809120cc78feb8bd27109edcdf93018d99882fdeecb2257ff3c3de7
 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": 0.0007979413114165454,
+  "epoch": 0.0011969119671248179,
   "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": 0.1223,
       "step": 18
+    },
+    {
+      "epoch": 0.0008378383769873726,
+      "grad_norm": 0.03902443125844002,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.0669,
+      "step": 21
+    },
+    {
+      "epoch": 0.0009575295736998544,
+      "grad_norm": 6.657548427581787,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.16,
+      "step": 24
+    },
+    {
+      "epoch": 0.0009575295736998544,
+      "eval_loss": 0.04156876355409622,
+      "eval_runtime": 1363.9818,
+      "eval_samples_per_second": 7.738,
+      "eval_steps_per_second": 3.869,
+      "step": 24
+    },
+    {
+      "epoch": 0.0010772207704123362,
+      "grad_norm": 0.0965176597237587,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.1114,
+      "step": 27
+    },
+    {
+      "epoch": 0.0011969119671248179,
+      "grad_norm": 0.16754962503910065,
+      "learning_rate": 0.0,
+      "loss": 0.0055,
+      "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": 7418872835604480.0,
+  "total_flos": 1.112830925340672e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null