Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2902480b9e6adfadcaeb35003415dace1dde2e2b9320e45b8cdd3cc4b88f6912
+oid sha256:454a1484bf9ae663900bccbb23ef99732643ab20d1062dc2bbca3bc84c4bb7ed
 size 217931936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:972de804d26a57fc0b289ed180952511318cec7388e554670a049c272700f773
+oid sha256:368ca92e536d23cad970f7f3c189628cdf03fe35a6517b072ab84fc1d84dc4e8
 size 436083346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a981a3982444f3f90ed724af955dbb07ead0a66415ba6e15b2cbeaccf98cc58d
+oid sha256:877632ef3bd249f1e644a973de52fe2c669b9ad6827c9500f5f8d598a7bb9bcd
 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": 0.011537352177675224,
+  "epoch": 0.02307470435535045,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 9e-05,
       "loss": 0.5873,
       "step": 9
+    },
+    {
+      "epoch": 0.013844822613210269,
+      "grad_norm": 0.6607969403266907,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.5005,
+      "step": 12
+    },
+    {
+      "epoch": 0.017306028266512834,
+      "grad_norm": 1.0222777128219604,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.3922,
+      "step": 15
+    },
+    {
+      "epoch": 0.018459763484280356,
+      "eval_loss": 0.35566139221191406,
+      "eval_runtime": 114.13,
+      "eval_samples_per_second": 3.198,
+      "eval_steps_per_second": 1.603,
+      "step": 16
+    },
+    {
+      "epoch": 0.020767233919815404,
+      "grad_norm": 0.2591637074947357,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.3792,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8475499214929920.0,
+  "total_flos": 1.695099842985984e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null