Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b588f798133e98c0aeb3b8e6b265345e7721052d7d887a1e704b3c020708375
+oid sha256:c9a83d3a8b5c5044e699a21cfcbeeeef5f62376187bccc3a528ec786ed55182f
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ef515f13580ed0853e31f9c1ab850d8c40d4e5aa55a911eb7ce22f1c347e5c2
+oid sha256:42c276f62379f071fd32f27fe91d2bcdd6e3048347eb4fc8324da57834c1097f
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4af29472032cf1b18d6c89c9a1251eb93ed20825e4fd81298d6c3a6949cf5fad
+oid sha256:d00eb0941e803989f62d4d2098846434473988bfd8534d340f800a64a4724e0d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005263157894736842,
+  "epoch": 0.010526315789473684,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 19.731,
       "eval_steps_per_second": 9.866,
       "step": 3
+    },
+    {
+      "epoch": 0.007017543859649123,
+      "grad_norm": 2.6294302940368652,
+      "learning_rate": 8e-05,
+      "loss": 1.866,
+      "step": 4
+    },
+    {
+      "epoch": 0.008771929824561403,
+      "grad_norm": 3.6487789154052734,
+      "learning_rate": 0.0001,
+      "loss": 2.1895,
+      "step": 5
+    },
+    {
+      "epoch": 0.010526315789473684,
+      "grad_norm": 2.667315721511841,
+      "learning_rate": 0.00012,
+      "loss": 1.4294,
+      "step": 6
+    },
+    {
+      "epoch": 0.010526315789473684,
+      "eval_loss": 1.2546732425689697,
+      "eval_runtime": 12.3056,
+      "eval_samples_per_second": 19.503,
+      "eval_steps_per_second": 9.752,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 812213851914240.0,
+  "total_flos": 1767759560048640.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null