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:b88af1d1af8f514a4ab5429fe1d7808f698704ace1aff64fb37eb0a4973773af
+oid sha256:37163875ed1986b916de49c04bcf8c2cc990826e0ff202d81589c10e20cc0f46
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:426fbdc0325bc1322509c03741570eb0b587b744468404811fb730c61fa8fd6e
+oid sha256:ea3f1d9719af2c2282229e3d50986e667dc36780b747b6ef8b553d7eb00fd518
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e4dee594575d9d29647a31877751cca61cb141c8edaa7181b92dbb7d6982030
+oid sha256:ab035f347a6570da46d155135020392bfdfe4de4249f6a928f2bffba87b2e43a
 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": 0.003016250047128907,
+  "epoch": 0.004524375070693361,
   "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": 1.2651,
       "step": 18
+    },
+    {
+      "epoch": 0.003167062549485352,
+      "grad_norm": 0.45209425687789917,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.0584,
+      "step": 21
+    },
+    {
+      "epoch": 0.0036195000565546883,
+      "grad_norm": 0.6036216616630554,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.1131,
+      "step": 24
+    },
+    {
+      "epoch": 0.0036195000565546883,
+      "eval_loss": 1.1596405506134033,
+      "eval_runtime": 166.0649,
+      "eval_samples_per_second": 16.813,
+      "eval_steps_per_second": 8.406,
+      "step": 24
+    },
+    {
+      "epoch": 0.0040719375636240245,
+      "grad_norm": 0.45558610558509827,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.0708,
+      "step": 27
+    },
+    {
+      "epoch": 0.004524375070693361,
+      "grad_norm": 0.5339828133583069,
+      "learning_rate": 0.0,
+      "loss": 1.0913,
+      "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": 6941488227287040.0,
+  "total_flos": 1.032959557632e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null