Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a7fa707801eb2a85c0eb913593472c5ad0fc96f789ef8042576c324e3c0857e
+oid sha256:12557827d7df63a6d7d9fc35b34bf4b968e70b1a192e7a711f127b7a76e1e632
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c100f2f111eef7ee87ddec67ddad69b03729efd39d9a47d50c6f9d4d0a6b93ea
+oid sha256:ff137f64c4c764c8d3d9f41390d5c02c976aa04c059e8e781896a139a5434106
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba60c260384233e5cb0e7bbfabb0bd75f441fc8b78b5fed933e9ca48341a17ab
+oid sha256:3d1b8821978c7450bd2cb49e068182933549eb330933b29022697a95533c47a4
 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": 0.004253056884635832,
+  "epoch": 0.008506113769271665,
   "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": 0.7197,
       "step": 9
+    },
+    {
+      "epoch": 0.005103668261562998,
+      "grad_norm": 0.5403614044189453,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.6963,
+      "step": 12
+    },
+    {
+      "epoch": 0.006379585326953748,
+      "grad_norm": 0.5106764435768127,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.6779,
+      "step": 15
+    },
+    {
+      "epoch": 0.006804891015417331,
+      "eval_loss": 0.6631687879562378,
+      "eval_runtime": 130.792,
+      "eval_samples_per_second": 7.569,
+      "eval_steps_per_second": 3.785,
+      "step": 16
+    },
+    {
+      "epoch": 0.007655502392344498,
+      "grad_norm": 0.5691841244697571,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.6017,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3709436417802240.0,
+  "total_flos": 7418872835604480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null