Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc7af10d094d26f6ed7f16da5568dc436500bc9aeed19f871f817c33a3bbae44
+oid sha256:d1ff5894c2514a95f86e6b612ebd365a6b9c1d90547cf7a031e294d332ad449e
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d5226bcb0887fdebeb087f7fd5ad45fe2f69aeff7e70de0f14b9721c3ff7131
+oid sha256:46f17ea3cf88576e35dd5c383c52acf6cb249d63db58f1fecedbbb6c780a7a6f
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40256b3b8d4166663178ef6cb46bc795138c6f18e7705718776bf54ff08ab4eb
+oid sha256:6425776668305c004e03f9019bc158962fb5b8b75d34b017106a5817399724df
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
+oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00942951438000943,
+  "epoch": 0.01885902876001886,
   "eval_steps": 5,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,28 @@
       "eval_samples_per_second": 12.994,
       "eval_steps_per_second": 1.63,
       "step": 5
+    },
+    {
+      "epoch": 0.011315417256011316,
+      "grad_norm": 0.44942334294319153,
+      "learning_rate": 6e-05,
+      "loss": 1.6204,
+      "step": 6
+    },
+    {
+      "epoch": 0.016973125884016973,
+      "grad_norm": 0.3278067708015442,
+      "learning_rate": 9e-05,
+      "loss": 1.53,
+      "step": 9
+    },
+    {
+      "epoch": 0.01885902876001886,
+      "eval_loss": 1.3736556768417358,
+      "eval_runtime": 68.8401,
+      "eval_samples_per_second": 12.972,
+      "eval_steps_per_second": 1.627,
+      "step": 10
     }
   ],
   "logging_steps": 3,
@@ -49,7 +71,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7109443426713600.0,
+  "total_flos": 1.457435902476288e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null