Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4654dd518a7bf22dc9ce4f0c59ba082875b3cfa3f47cc858e590badba99dc057
+oid sha256:f1fee4b14d709f3163fb7442262256e1d8d9df5ab1607dc15421fcbc2f3dec13
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed4a6c5026f89feaae8f61a8d1c67752883101c2ad40bb8cb5ab31d07d032b4f
+oid sha256:52c93ceeed21e54f2ac8fb096fe5950407f6ecf0302e5ff109f2dc6b48a39973
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db09b140128a78da98f28da6f39e290e9550692345a1a0d0f7ed1cbb8aa74cc3
+oid sha256:22cc4a9a02a6f74d668e9df70ad462220b16b60af37292d30446f2a841cfc377
 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": 0.0009417673834562863,
+  "epoch": 0.0018835347669125726,
   "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": 36.304,
       "eval_steps_per_second": 18.152,
       "step": 3
+    },
+    {
+      "epoch": 0.0012556898446083817,
+      "grad_norm": 8.001363754272461,
+      "learning_rate": 8e-05,
+      "loss": 17.8501,
+      "step": 4
+    },
+    {
+      "epoch": 0.0015696123057604772,
+      "grad_norm": 7.333746433258057,
+      "learning_rate": 0.0001,
+      "loss": 19.9848,
+      "step": 5
+    },
+    {
+      "epoch": 0.0018835347669125726,
+      "grad_norm": 8.180486679077148,
+      "learning_rate": 0.00012,
+      "loss": 16.195,
+      "step": 6
+    },
+    {
+      "epoch": 0.0018835347669125726,
+      "eval_loss": 17.218795776367188,
+      "eval_runtime": 37.143,
+      "eval_samples_per_second": 36.131,
+      "eval_steps_per_second": 18.065,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 522790813827072.0,
+  "total_flos": 1045581627654144.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null