Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b5a3bad60768167ececa1ab7f92bb55b38a64f6a968de4be7f96346c4430d62
+oid sha256:33a9fb099d28cd45498012bf304953ce45f6983500b457d9d1c6549cc0f0862c
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88944251bc7fe1b1f5ff347d405b9f0bb3fd728d3f13c14d035940c2eb5f955c
+oid sha256:24b7d8c6c695813fbc1fc64a0d06cb7c63fee5bb09529bbcca40c8fca8a394f8
 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 sha256:35e92785679980f3fcd23b14ce1acaffcae115e3e9164492d0e4b31775d32447
+oid sha256:d8712da1b2787df41952a507984ec77e0f72c59fac7ee6cf21606445686249de
 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": 54.887,
       "eval_steps_per_second": 27.471,
       "step": 13
+    },
+    {
+      "epoch": 0.008348987685243165,
+      "grad_norm": 1.7537938356399536,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 2.9006,
+      "step": 20
+    },
+    {
+      "epoch": 0.010853683990816114,
+      "eval_loss": 2.9640495777130127,
+      "eval_runtime": 18.6391,
+      "eval_samples_per_second": 54.134,
+      "eval_steps_per_second": 27.094,
+      "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