Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73a85a4e3ab91fad626e863f709f3c1f02ffde48fb0a9e68df30643565afdfc2
+oid sha256:144ed1d40db4028269bdc66b938d788bf81dbe8e73b32087dbf70fa1f15e5139
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6acb2310b9d1c95e3490826770bbb86e1a3d3d7be2cd6400fbed3dcfbe842793
+oid sha256:74909fd4745e3a403b3566fddf3dfb62893b0a09e673d9c8d5cc87ed4b45acb0
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cf78a05d0eb988ddd2b7ce1e2b60a5542f57ac36b2214240dcabf031d342635
+oid sha256:79e1d4e220c2e87a35da930aab1a7ef3cfb78808e84af2a47ce768e8083ff26c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007739938080495356,
+  "epoch": 0.015479876160990712,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 4.897,
       "eval_steps_per_second": 2.453,
       "step": 10
+    },
+    {
+      "epoch": 0.009287925696594427,
+      "grad_norm": 3.83369779586792,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 5.9687,
+      "step": 12
+    },
+    {
+      "epoch": 0.011609907120743035,
+      "grad_norm": 1.0999690294265747,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 7.028,
+      "step": 15
+    },
+    {
+      "epoch": 0.011609907120743035,
+      "eval_loss": 1.5518581867218018,
+      "eval_runtime": 111.3292,
+      "eval_samples_per_second": 4.895,
+      "eval_steps_per_second": 2.452,
+      "step": 15
+    },
+    {
+      "epoch": 0.01393188854489164,
+      "grad_norm": 1.7612863779067993,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 6.8503,
+      "step": 18
+    },
+    {
+      "epoch": 0.015479876160990712,
+      "eval_loss": 1.4609495401382446,
+      "eval_runtime": 111.3426,
+      "eval_samples_per_second": 4.895,
+      "eval_steps_per_second": 2.452,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4084154027212800.0,
+  "total_flos": 8576723457146880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null