Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3508c765930f2c454e2344c1bd61450bbccff5d86970ecbeb73676503332b56a
+oid sha256:0b1e3ded9c7ce873c8575c3a6ab36543a4461e8505da39d1720764f8ba20d213
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a60742d450518cd571645478aa75dde4ba848c5b27b9aea262aeee1d8e2b0de
+oid sha256:2fa3d93a2d867ff71e5bbaa58e09c7cbbe53be6251f41d8e7b3550f43d208530
 size 36135892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37b90603b481d5e77d9e25318fb7b0fb887a56cb21d65a236112bb3a1488aa62
+oid sha256:a7a7fedc6ccb3fa4fc081ee12b608061e2cb5dc420feb509e3f96eaf960dd3de
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb0a9ae08a837d696210720a364c40061c9c8b036f36570a99f11fe3b8d70f51
+oid sha256:562360b448a53e7366b8643d15ad250a0f706aaefd28e30d76b7f5f4480c7196
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0030653147842489977,
+  "epoch": 0.0061306295684979955,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 60.958,
       "eval_steps_per_second": 30.513,
       "step": 13
+    },
+    {
+      "epoch": 0.004715868898844612,
+      "grad_norm": 1.5342705249786377,
+      "learning_rate": 0.0002,
+      "loss": 1.5709,
+      "step": 20
+    },
+    {
+      "epoch": 0.0061306295684979955,
+      "eval_loss": 1.5492371320724487,
+      "eval_runtime": 14.9616,
+      "eval_samples_per_second": 59.686,
+      "eval_steps_per_second": 29.876,
+      "step": 26
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 66904113020928.0,
+  "total_flos": 131501187661824.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null