Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7534673fa1d5739af0b1fd9bea0e02e2e61a69c8ea1d990c3414b8fa2350b2bb
+oid sha256:d835f6730863b88d70068f455956a60f5c96edd55da2eeced7aea2b7c80b95cf
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9a254fb661e5f6edab19decf857c858429e54afdbf4718cb447f825bccda8c1
+oid sha256:287b9a09e864eb71d68c74c6ba4d81d2fa524dd23b28b7ad9e4457e92f96d9ce
 size 166439638

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:186a3f9d4bf6a30ebfd775dfe4ce0a26d72676319e85d3735f87cc1dd27b763c
+oid sha256:bb693ce61919bf80f2b88c9133c0d8e3384ced58afdc63fffa022c32fd41329e
 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": 0.02542911633820725,
+  "epoch": 0.0508582326764145,
   "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": 2.1303,
       "step": 9
+    },
+    {
+      "epoch": 0.030514939605848695,
+      "grad_norm": 0.8389137387275696,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 2.0045,
+      "step": 12
+    },
+    {
+      "epoch": 0.03814367450731087,
+      "grad_norm": 0.7117744088172913,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 1.889,
+      "step": 15
+    },
+    {
+      "epoch": 0.040686586141131596,
+      "eval_loss": 1.8759232759475708,
+      "eval_runtime": 8.9673,
+      "eval_samples_per_second": 18.512,
+      "eval_steps_per_second": 9.256,
+      "step": 16
+    },
+    {
+      "epoch": 0.04577240940877304,
+      "grad_norm": 0.6732363700866699,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.9495,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1030430747787264.0,
+  "total_flos": 2111126410100736.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null