Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32f0cb0755aac3238b4c39ee76c78cad3e79ee5bfa12f7b4477f13768a9a20a5
+oid sha256:f108bf778242b1c0d7befa5636ef545b6278c2bd398b9166c3f07b2a853c8c52
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0a51d05d57dccdf3bd6f8ff44d32052877e18f2964c468a41061f641dff71b3
+oid sha256:98f4353fe907b9499ab1263eaedb96a102a7e5beb15eab95cfc5ec649bdc138d
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc932c524eaaac87bc8d6c7f717be72004261bf8c0a408ff938e5602032d24e0
+oid sha256:c73b88f5a325402ade8b631cbde07f764e38136b3a98cd5bf088404635b73f25
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fec74e92563bbe4b510ec939dc1c78d591826119d26043cc49e0a868b67121a2
+oid sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005426841995408057,
+  "epoch": 0.010853683990816114,
   "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": 59.712,
       "eval_steps_per_second": 29.885,
       "step": 13
+    },
+    {
+      "epoch": 0.008348987685243165,
+      "grad_norm": 1.8960473537445068,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 2.8603,
+      "step": 20
+    },
+    {
+      "epoch": 0.010853683990816114,
+      "eval_loss": 2.9474551677703857,
+      "eval_runtime": 16.936,
+      "eval_samples_per_second": 59.577,
+      "eval_steps_per_second": 29.818,
+      "step": 26
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 129105337516032.0,
+  "total_flos": 244854950461440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null