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:c36bb47c0c2382a0f3ceb84444eeb698c8fe807facaadfa4bdd6b299653f7265
+oid sha256:92c3ae45a134aeabf5c340275e335c1c9c7a161c90bb0e9a813ad6b703e04bdc
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d31254b9a3e89f8093d9346659f0925649d794c15a44077da314b915d18d8b8
+oid sha256:625aa9477ca8586bb161eecc95b21487151ea2103b2347c3ffd5415b5586c62c
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c2fdb38126bec91fa63804962e3448cc4fcaad4f83a5b93d7f41f106d1ea322
+oid sha256:8288cb8cb0b54526d97f2ff59da883c307360a17e99a5d7d1d6e7afb2436e03b
 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": 0.016842105263157894,
+  "epoch": 0.03368421052631579,
   "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": 3.2467,
       "step": 9
+    },
+    {
+      "epoch": 0.020210526315789474,
+      "grad_norm": 2.0705854892730713,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 2.5268,
+      "step": 12
+    },
+    {
+      "epoch": 0.02526315789473684,
+      "grad_norm": 2.0589914321899414,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 1.9183,
+      "step": 15
+    },
+    {
+      "epoch": 0.026947368421052633,
+      "eval_loss": 1.4310015439987183,
+      "eval_runtime": 33.4479,
+      "eval_samples_per_second": 7.474,
+      "eval_steps_per_second": 3.737,
+      "step": 16
+    },
+    {
+      "epoch": 0.03031578947368421,
+      "grad_norm": 1.4359524250030518,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.2323,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6347792213606400.0,
+  "total_flos": 1.26955844272128e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null