Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0712975b6e96fbbe46ec14cba73b55f7675ce4118f04d7d00fecbac579685537
+oid sha256:afe760b9f32c4107bab1c86cdce3e357c1ba7193d889365631fd13920daea33d
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5b1d8b26f17388ac1d22e13a542893fc2434bc9e2ba6ca7dce28b6c237c9a7f
+oid sha256:7a58f557a4c9be893b810b83cdeb000e4f05c7ec0baaf4d49c5da15bd9b0ed50
 size 201478138

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd8f3e267d986e8404462522682a3b8750e660907c3ebc5aab2b14c410169f12
+oid sha256:2b4fcafe51467334025a2305f8c44550e6e8bfc0bc4e21468cb79f88a0d21f9f
 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": 0.007665772326561901,
+  "epoch": 0.015331544653123802,
   "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": 5.2817,
       "step": 9
+    },
+    {
+      "epoch": 0.009198926791874281,
+      "grad_norm": 2.100029706954956,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 4.5409,
+      "step": 12
+    },
+    {
+      "epoch": 0.011498658489842852,
+      "grad_norm": 1.713498830795288,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 4.2998,
+      "step": 15
+    },
+    {
+      "epoch": 0.012265235722499043,
+      "eval_loss": 0.9625716805458069,
+      "eval_runtime": 111.8928,
+      "eval_samples_per_second": 4.915,
+      "eval_steps_per_second": 2.458,
+      "step": 16
+    },
+    {
+      "epoch": 0.013798390187811422,
+      "grad_norm": 1.6698487997055054,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 3.8355,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1842091508367360.0,
+  "total_flos": 3684183016734720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null