Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c2bd2e06cb1031cb71d034ed7ab5d95ed4b3c174eea0ac8152e9bba64f629a8
+oid sha256:60d32d48078b620c9a6f47add386236b72d9b1eb15186be35bfb4825222bec25
 size 56662952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03d72b31e1b8a0561d3f928f38d1a9dfbb4e7293c4b97fee9ec1bf1d16667eb1
+oid sha256:e64ebac3067342ec186ce45e3428d0dc2a30113d7827beedea7b2d1daef9d264
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c215893315df5685993bbe9ee121746bc6a7e21d48b2a7c12c8354f000c024e
+oid sha256:f9529e546cf341a145a50d98de64242b3f32033a0c0b27a23a66d4e5bf961a4e
 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": 0.07648183556405354,
+  "epoch": 0.15296367112810708,
   "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": 17.4632,
       "step": 9
+    },
+    {
+      "epoch": 0.09177820267686425,
+      "grad_norm": 15.489852905273438,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 17.1185,
+      "step": 12
+    },
+    {
+      "epoch": 0.1147227533460803,
+      "grad_norm": 12.425662994384766,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 14.8632,
+      "step": 15
+    },
+    {
+      "epoch": 0.12237093690248566,
+      "eval_loss": 3.3697333335876465,
+      "eval_runtime": 1.9488,
+      "eval_samples_per_second": 28.223,
+      "eval_steps_per_second": 14.368,
+      "step": 16
+    },
+    {
+      "epoch": 0.13766730401529637,
+      "grad_norm": 13.362841606140137,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 13.0895,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 601010208768000.0,
+  "total_flos": 1202020417536000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null