Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:347ef3444efb93404812ad3e98492728a424b5639833961f995d10334022a99c
+oid sha256:bb66c9abc7746f2f626a7d6484e9521532b62a02d4da2d6d414818ce86401b01
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6de8d131ad2ad4ec3a9357f6c5f2aad32b9935834d1cf3b100256deea373fc94
+oid sha256:c150d6c207a76db4e48de6a91262263dcba21e086b0c05e77a027d5ba7007077
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dca3e02eebe83d24045a6a34961b86f2d2953f340af948f4ff2d9c1cc24f691a
+oid sha256:d52de5368f5ce61262c2d589ee36ea6650cbb194994badad3cc71c4ee2f14c31
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b80fcc7599efca0c6313d990c467c2eb3001742b23ddaadc22e3499c12cea79
+oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0099000099000099,
+  "epoch": 0.0198000198000198,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 11.96,
       "eval_steps_per_second": 5.983,
       "step": 50
+    },
+    {
+      "epoch": 0.01188001188001188,
+      "grad_norm": 1.5985904932022095,
+      "learning_rate": 0.0002,
+      "loss": 3.7766,
+      "step": 60
+    },
+    {
+      "epoch": 0.01386001386001386,
+      "grad_norm": 1.0298365354537964,
+      "learning_rate": 0.0002,
+      "loss": 3.9574,
+      "step": 70
+    },
+    {
+      "epoch": 0.01584001584001584,
+      "grad_norm": 1.3167791366577148,
+      "learning_rate": 0.0002,
+      "loss": 3.5841,
+      "step": 80
+    },
+    {
+      "epoch": 0.01782001782001782,
+      "grad_norm": 1.6314549446105957,
+      "learning_rate": 0.0002,
+      "loss": 3.5142,
+      "step": 90
+    },
+    {
+      "epoch": 0.0198000198000198,
+      "grad_norm": 0.9245526790618896,
+      "learning_rate": 0.0002,
+      "loss": 3.4552,
+      "step": 100
+    },
+    {
+      "epoch": 0.0198000198000198,
+      "eval_loss": 0.8583095669746399,
+      "eval_runtime": 177.6926,
+      "eval_samples_per_second": 11.97,
+      "eval_steps_per_second": 5.988,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.430077154361344e+16,
+  "total_flos": 4.883900991012864e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null