Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e647199bf95ee61d9fe9858f2dcda1f1245d807ddf6538274bf7cb73fe842cd4
+oid sha256:5fc4fd4c786a85ca3a196e03033cfd27ffbe6d49f091667f6f31b7384d2df44c
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:863546bd77606ffcfbb0b238fee97fa9dc32bdcfedcc7825995f8faf77537f39
+oid sha256:189a671a69fb5c6163f5edefeb886dbc3f6552f92137887b6bf92229b11a3658
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40bfb7a2bb9e09979ca0850fe7db152528103f342b31a7d7161ea872baf3db7f
+oid sha256:b58650bd0af9f9dcea9f0f97784c48ee7e253296f93b2228f5405c1d5b3c7785
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
+oid sha256:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006472387178201,
+  "epoch": 0.0097085807673015,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 33.405,
       "eval_steps_per_second": 16.703,
       "step": 100
+    },
+    {
+      "epoch": 0.0071196258960211,
+      "grad_norm": 0.9663441181182861,
+      "learning_rate": 0.0002,
+      "loss": 1.0741,
+      "step": 110
+    },
+    {
+      "epoch": 0.0077668646138412,
+      "grad_norm": 1.29120934009552,
+      "learning_rate": 0.0002,
+      "loss": 1.044,
+      "step": 120
+    },
+    {
+      "epoch": 0.0084141033316613,
+      "grad_norm": 0.9238539338111877,
+      "learning_rate": 0.0002,
+      "loss": 1.0563,
+      "step": 130
+    },
+    {
+      "epoch": 0.0090613420494814,
+      "grad_norm": 1.1232694387435913,
+      "learning_rate": 0.0002,
+      "loss": 1.0642,
+      "step": 140
+    },
+    {
+      "epoch": 0.0097085807673015,
+      "grad_norm": 0.957047700881958,
+      "learning_rate": 0.0002,
+      "loss": 1.0433,
+      "step": 150
+    },
+    {
+      "epoch": 0.0097085807673015,
+      "eval_loss": 0.9908371567726135,
+      "eval_runtime": 194.8244,
+      "eval_samples_per_second": 33.394,
+      "eval_steps_per_second": 16.697,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.873333749547008e+16,
+  "total_flos": 2.8056440342052864e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null