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:fa657dd5df7b5aea8a8ea71a2c4db77b2a2238203f10eff4f53d8a84dfb63529
+oid sha256:2fe232f15466d8eb910696b917297fa04ab5c65962446a41bc2b817887d5e4f1
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f01f5b64a7cc9d77d0803208e3aaeb7b4add9e15d53a519b3c60efc20b1b40fa
+oid sha256:e124e65fce3a65bf9e6a76362dd830a0678915906a77bd02c2b03850498b7236
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3e5dbc325562c890f65b04c44ff9ae3a4aaec245e3f64053f21254bb31be760
+oid sha256:8cda808a715e27e97306871d579469317867df663ceae9d24e156e477a5af537
 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": 0.00047469293300895983,
+  "epoch": 0.0007120393995134397,
   "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": 1.8599,
       "step": 18
+    },
+    {
+      "epoch": 0.0004984275796594078,
+      "grad_norm": 1.9304282665252686,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.9402,
+      "step": 21
+    },
+    {
+      "epoch": 0.0005696315196107518,
+      "grad_norm": 1.97409987449646,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.0165,
+      "step": 24
+    },
+    {
+      "epoch": 0.0005696315196107518,
+      "eval_loss": 0.4720425009727478,
+      "eval_runtime": 1873.0838,
+      "eval_samples_per_second": 9.471,
+      "eval_steps_per_second": 4.736,
+      "step": 24
+    },
+    {
+      "epoch": 0.0006408354595620958,
+      "grad_norm": 2.031785726547241,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.8595,
+      "step": 27
+    },
+    {
+      "epoch": 0.0007120393995134397,
+      "grad_norm": 1.998368740081787,
+      "learning_rate": 0.0,
+      "loss": 2.1204,
+      "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": 1.3007903174688768e+16,
+  "total_flos": 1.9863419712700416e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null