Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecbad17c8c36f699ef2e60e8575a07017c945d8e8a66afc7e979bae7aa74f775
+oid sha256:b79d6c738525786d8d024bebde7ff54252eade5a767213fcce4683fdcd8800e4
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bfc6817cc47d3b8a25497a2ad26296992cd474e95d624110a39523f11d0c6c4
+oid sha256:dd114e07ac02776a619f90cdd586afe7eeed91c34f863224075824ea5a7e6e77
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c683a96b3a33504bcf104bd66d70d07f59ed807698ad96230e879f4b6bf5d00a
+oid sha256:27b9c1be8d8bae4df98ae1a27353c07078eed013c40757a6521cd0fbfb3c8fb9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b4906f488285c3d93b3de9477b5cdb50810bb8e8a714368724d443d38a5757a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.4047619047619047,
+  "epoch": 1.880952380952381,
   "eval_steps": 3,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,6 +160,49 @@
       "eval_samples_per_second": 15.762,
       "eval_steps_per_second": 7.881,
       "step": 15
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.1736566573381424,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 1.1874,
+      "step": 16
+    },
+    {
+      "epoch": 1.5952380952380953,
+      "grad_norm": 0.16423116624355316,
+      "learning_rate": 0.00014539904997395468,
+      "loss": 1.1152,
+      "step": 17
+    },
+    {
+      "epoch": 1.6904761904761905,
+      "grad_norm": 0.19566665589809418,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.1665,
+      "step": 18
+    },
+    {
+      "epoch": 1.6904761904761905,
+      "eval_loss": 1.148561954498291,
+      "eval_runtime": 6.4854,
+      "eval_samples_per_second": 15.419,
+      "eval_steps_per_second": 7.71,
+      "step": 18
+    },
+    {
+      "epoch": 1.7857142857142856,
+      "grad_norm": 0.21023060381412506,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 1.2285,
+      "step": 19
+    },
+    {
+      "epoch": 1.880952380952381,
+      "grad_norm": 0.21021750569343567,
+      "learning_rate": 0.0001,
+      "loss": 1.2653,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -179,7 +222,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2835124715520000.0,
+  "total_flos": 3791128769593344.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null