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:e4919cab1163c0b14520b45e76e8337d677fdeec660326b6c741d3f6551cebd4
+oid sha256:544289615aa5c2e3973ab4cf89ac12752a7cc261af22cd1e7adb31aa43236371
 size 217931936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5046390c8d63d352059611096f340583f2738a385d59b6a584fb264d1a0e1f63
+oid sha256:5b749b6eb802a6b78ff62a49631e3bc469ed7a907d879b4f0f2a2fba6c406c0c
 size 436083346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f36f41fda655962bf032d9412b700b60ae7f10561821fe4555d168e69146d408
+oid sha256:3110dd384a1eab915ce374d836b351e17ed65eb43c290bc69a5726b557515a33
 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": 0.0007298071484610192,
+  "epoch": 0.0010947107226915288,
   "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": 1.6203,
       "step": 18
+    },
+    {
+      "epoch": 0.0007662975058840702,
+      "grad_norm": 1.0494722127914429,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.5117,
+      "step": 21
+    },
+    {
+      "epoch": 0.000875768578153223,
+      "grad_norm": 1.0654144287109375,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.516,
+      "step": 24
+    },
+    {
+      "epoch": 0.000875768578153223,
+      "eval_loss": 1.512626051902771,
+      "eval_runtime": 1856.5611,
+      "eval_samples_per_second": 6.215,
+      "eval_steps_per_second": 3.108,
+      "step": 24
+    },
+    {
+      "epoch": 0.0009852396504223758,
+      "grad_norm": 1.169287085533142,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.5039,
+      "step": 27
+    },
+    {
+      "epoch": 0.0010947107226915288,
+      "grad_norm": 1.247051477432251,
+      "learning_rate": 0.0,
+      "loss": 1.5193,
+      "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": 8475499214929920.0,
+  "total_flos": 1.2819192562581504e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null