Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:957d4f4c8a6fc3fc1c01a4f709e209cf5fe1d71e3429b5683495ae31d324fea8
+oid sha256:f038c7fd34c79b980301bf781b90ff90fdf47b7372516d863ab830ce97aa9487
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec397ab488d5c21ea573198c281007fb8fa66bf30170cb2cb8eb316af4590b9a
+oid sha256:77853fcd7f0d70fc2097cfdd6673560975dde5baa2cbb26854a45d53749ea48d
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bc95f8ef66804917a60b19acbb3aaab5647926085d4ddb008103acb36348fb2
+oid sha256:2bc49e406d40d15d4c77a549f46af25554828e4ccf4a2549a6e443a9a7b138dc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007415647015202077,
+  "epoch": 0.014831294030404153,
   "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": 0.00018,
       "loss": 7.9929,
       "step": 9
+    },
+    {
+      "epoch": 0.008898776418242492,
+      "grad_norm": 5.074840545654297,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 2.8182,
+      "step": 12
+    },
+    {
+      "epoch": 0.011123470522803115,
+      "grad_norm": 98.48111724853516,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 1.2382,
+      "step": 15
+    },
+    {
+      "epoch": 0.011865035224323322,
+      "eval_loss": 0.35880428552627563,
+      "eval_runtime": 81.1112,
+      "eval_samples_per_second": 7.003,
+      "eval_steps_per_second": 3.501,
+      "step": 16
+    },
+    {
+      "epoch": 0.013348164627363738,
+      "grad_norm": 12.51295280456543,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.2371,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3267323221770240.0,
+  "total_flos": 6534646443540480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null