Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:845838bb35778967640dea03273e5f464cb88cb72297e187a3b497b90c003abc
+oid sha256:dcc9961c0add1cb53a3e3bac8117f83ba4b5420dd091e989cc9d94484bf8b97c
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54b2c724e415fce6885638b8eb14db4eabc27b9e1e069d8b63c43bc8280b6811
+oid sha256:03fc615e99f9f5fbb1dbcb766bc5027296e5b7c9266b0a8ec998bee952074f94
 size 400264058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db3c27a041dac9ea85d68d87c5ef6512ed857ee5506eaaab19f22faf7ae226c7
+oid sha256:5d60ff9e5296a4be04a3c9b1cd16bfec534158bba41fe711a52834fceeb9e334
 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": 0.0006185343827800028,
+  "epoch": 0.0012370687655600056,
   "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": 2.658,
       "step": 9
+    },
+    {
+      "epoch": 0.0007422412593360033,
+      "grad_norm": 1.6369829177856445,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 2.7217,
+      "step": 12
+    },
+    {
+      "epoch": 0.0009278015741700042,
+      "grad_norm": 1.4151548147201538,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 2.7007,
+      "step": 15
+    },
+    {
+      "epoch": 0.0009896550124480045,
+      "eval_loss": 2.6173229217529297,
+      "eval_runtime": 1258.8962,
+      "eval_samples_per_second": 5.408,
+      "eval_steps_per_second": 2.704,
+      "step": 16
+    },
+    {
+      "epoch": 0.001113361889004005,
+      "grad_norm": 1.4854135513305664,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.621,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4697227964448768.0,
+  "total_flos": 9394455928897536.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null