Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7713e8b606ed36237741bc6ba1181c9ecbe3f74fb8238ad4c72c7617278cbb10
+oid sha256:7be501c558cf623508637efd46deeb94cd15e61cc607a0d9b1347f841b0b10ec
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31142c1508467a12c78a594d6c482df21c9fc529b4b3ed2bce7543d47eaddc74
+oid sha256:230ad684518514a30d9bab9353aa1919a1ddf11f10c092fb2d3aa3e5c2b641e1
 size 70667778

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6af341f557e09fbd0071556d25e02abc291cc2afadb89c9e933033b80be52dd4
+oid sha256:b282f04de260040fb20ce8f68d3f23a0f5f33e104a69b7ece5f30022e97e831e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bb840dbc65c27ef8840855786e35bfea033749e5d7571cf601f6645aa29cc1e
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.012051822838204279,
+  "epoch": 0.016069097117605704,
   "eval_steps": 3,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,6 +160,49 @@
       "eval_samples_per_second": 38.126,
       "eval_steps_per_second": 19.081,
       "step": 15
+    },
+    {
+      "epoch": 0.012855277694084564,
+      "grad_norm": 1.0272347927093506,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.2837,
+      "step": 16
+    },
+    {
+      "epoch": 0.01365873254996485,
+      "grad_norm": 1.063129186630249,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.2678,
+      "step": 17
+    },
+    {
+      "epoch": 0.014462187405845135,
+      "grad_norm": 1.1358978748321533,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.265,
+      "step": 18
+    },
+    {
+      "epoch": 0.014462187405845135,
+      "eval_loss": 0.2543899118900299,
+      "eval_runtime": 27.4127,
+      "eval_samples_per_second": 38.267,
+      "eval_steps_per_second": 19.152,
+      "step": 18
+    },
+    {
+      "epoch": 0.015265642261725419,
+      "grad_norm": 1.0389295816421509,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.2804,
+      "step": 19
+    },
+    {
+      "epoch": 0.016069097117605704,
+      "grad_norm": 1.001739263534546,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.2773,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -179,7 +222,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1081431451238400.0,
+  "total_flos": 1441908601651200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null