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:c900223cc6e5a110f21e350d414d5985bc4bfba7f2fc8f8a965d57f2686c41f5
+oid sha256:2c0caa4ce0798f8a1e0ed9158407d65dd191ad291cba00c9975d35151fff186d
 size 25192592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83fefe4c6a2e96a4bfe7726087c43b4e4b3bd87643f553f2ce257c21618a3b32
+oid sha256:91c8d969f34f11c89e1b1f8be8e9d4cd4871925cc521f1da2eaeba0ca647aea5
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8711885916a6de54b63f0ee56c53e205ad0e9da996e690aaa268ed01f2e267c
+oid sha256:e58b9d1afa51d36de3d7ca6e57e2e9e6692f3cd84afbc1b02efc61c4136b7704
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004253056884635832,
+  "epoch": 0.008506113769271665,
   "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": 72.554,
       "eval_steps_per_second": 36.277,
       "step": 10
+    },
+    {
+      "epoch": 0.005103668261562998,
+      "grad_norm": 39.573326110839844,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 6.302,
+      "step": 12
+    },
+    {
+      "epoch": 0.006379585326953748,
+      "grad_norm": 26.355426788330078,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 6.5024,
+      "step": 15
+    },
+    {
+      "epoch": 0.006379585326953748,
+      "eval_loss": 1.5709365606307983,
+      "eval_runtime": 13.5669,
+      "eval_samples_per_second": 72.972,
+      "eval_steps_per_second": 36.486,
+      "step": 15
+    },
+    {
+      "epoch": 0.007655502392344498,
+      "grad_norm": 27.330434799194336,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 6.3002,
+      "step": 18
+    },
+    {
+      "epoch": 0.008506113769271665,
+      "eval_loss": 1.5609004497528076,
+      "eval_runtime": 13.5405,
+      "eval_samples_per_second": 73.114,
+      "eval_steps_per_second": 36.557,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 181428402782208.0,
+  "total_flos": 358431722569728.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null