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:ae4b54924b38dc5d3b2c5a0d3179bfe435639aa76247de61b10ad16ec0b48226
+oid sha256:89aa4a4dcc334dddcbac154876a6e4a46886c870b2c07610938ac867e832bd76
 size 9864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2be07d2c6153dbc5840197d0624d8a0fae10543ff899133f1bf8e3c275c50724
+oid sha256:e214287cd3c1cdc9fbc713fa589d7fac1dfd37c90636b3dc21e0f17af4089d97
 size 24006

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:deabd56c17b610f6d8e6c3c09d2dcb705e4d72db3bc1813e41a578dadc2811d7
+oid sha256:5b1dbe479f6756df2ff500203698c9f57bca85e9e4a1cdb231db97e90dac145f
 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": 0.0006826404532732609,
+  "epoch": 0.0013652809065465218,
   "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": 46.0,
       "step": 9
+    },
+    {
+      "epoch": 0.0008191685439279131,
+      "grad_norm": 2.0053583284607157e-05,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 46.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.0010239606799098914,
+      "grad_norm": 2.8997801564401016e-05,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 46.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.0010922247252372176,
+      "eval_loss": 11.5,
+      "eval_runtime": 63.3764,
+      "eval_samples_per_second": 97.323,
+      "eval_steps_per_second": 48.662,
+      "step": 16
+    },
+    {
+      "epoch": 0.0012287528158918697,
+      "grad_norm": 2.1670148271368816e-05,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 46.0,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 438856974336.0,
+  "total_flos": 847791882240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null