Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0227ea21b482889b6b9215e506ed2b6a0f242c8955bc7db2c065f5adda720a46
+oid sha256:451eb27bba7caf7fdd110ed84b63b231eaf5ffc5810eed714a958a9f5f641104
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cb10f0056347bbf31af8aa56466cc5d812eb616c9c2692811552e966343b20d
+oid sha256:540a561bc873be092fc37506942c9231d690a3400dfec8d8d0c83e67a001bd0b
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:788a5350037a9552785a4747e6f5c194cdf141b5f070d4e230a64f6c3f0e771f
+oid sha256:9b042b4d598925f64321dd5bc833bccb2097be341c30bff2b10758fdf4a3fb46
 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": 0.006167129201356768,
+  "epoch": 0.012334258402713537,
   "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": 3.1377,
       "step": 9
+    },
+    {
+      "epoch": 0.0074005550416281225,
+      "grad_norm": 0.894902765750885,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 3.0202,
+      "step": 12
+    },
+    {
+      "epoch": 0.009250693802035153,
+      "grad_norm": 0.5678002834320068,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 2.8962,
+      "step": 15
+    },
+    {
+      "epoch": 0.009867406722170829,
+      "eval_loss": 2.8576066493988037,
+      "eval_runtime": 93.4677,
+      "eval_samples_per_second": 7.307,
+      "eval_steps_per_second": 3.659,
+      "step": 16
+    },
+    {
+      "epoch": 0.011100832562442183,
+      "grad_norm": 0.9780793190002441,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.8131,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4084113761894400.0,
+  "total_flos": 7514769321885696.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null