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:f9241ca99d31e85f2e93b3c6fb3c6ac6e40e2db9e636e3f685526cfb1b474a0b
+oid sha256:61cb99a9bbee72b004c29ddd06adc8ffdf285bcbcad02dde57ab72cce54b79c1
 size 216151256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:895f4dcccd2e37c35ad41e620aafc39d6edb948755392e9a82b1c1b45b2e7b1e
+oid sha256:3b5a2c734f69d0e6c9cc04f1c83da5a63e8a704519919033045f4389eaff5bf1
 size 432640054

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c694eff5aaa14fa6b9402c982ac4a33096ccdd0bdc388345f34bbd5b7b81f5a
+oid sha256:18cdfd1a7fa60e289cc18d625c0521e2f7c3a13ca6e47ed3eb3247b271c31cd9
 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": 0.009784735812133072,
+  "epoch": 0.019569471624266144,
   "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": 3.1889,
       "step": 9
+    },
+    {
+      "epoch": 0.011741682974559686,
+      "grad_norm": 3.9382309913635254,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 2.7903,
+      "step": 12
+    },
+    {
+      "epoch": 0.014677103718199608,
+      "grad_norm": 2.91917085647583,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 2.9457,
+      "step": 15
+    },
+    {
+      "epoch": 0.015655577299412915,
+      "eval_loss": 2.708803176879883,
+      "eval_runtime": 40.6668,
+      "eval_samples_per_second": 10.598,
+      "eval_steps_per_second": 5.311,
+      "step": 16
+    },
+    {
+      "epoch": 0.01761252446183953,
+      "grad_norm": 2.821608543395996,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.8381,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4118062710128640.0,
+  "total_flos": 8236125420257280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null