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:c7d08b11f13000915f41b674acdad55e80460b5d9c5203d9b9dbce30765dfaa4
+oid sha256:650d5eda33759d985f20d1f5ed4316fc6dfadf6eccec50089d61e1930ef6cee7
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36159a5834d3137ffce518a2daa944dedbc7d631dcd8c5ab38dbaf5bc9d0587a
+oid sha256:36d6197fdae9bf4194c24711c105df515305202e901d371bc22bdce19854946c
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dfa6087f1333349f8c87fa40e3b6d63d5e0153b2e826b8c64a8e0b997c209be
+oid sha256:1a8d63b333275153bc702a2b401d1e3a52307e5f460fbd5adb4e8ecd55c57dca
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fd8212ec5ec3406d74a7f927b717dd30ea8a06115ee6582e14976f7b84b4b58
+oid sha256:b489c13e2d776471e9a48162938854a24466ce6713df9c0fb59abd9a09fb226b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.175054704595186,
+  "epoch": 0.26258205689277897,
   "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": 36.412,
       "eval_steps_per_second": 18.282,
       "step": 100
+    },
+    {
+      "epoch": 0.1925601750547046,
+      "grad_norm": 0.5494540929794312,
+      "learning_rate": 8.79463319744677e-05,
+      "loss": 0.139,
+      "step": 110
+    },
+    {
+      "epoch": 0.2100656455142232,
+      "grad_norm": 1.3071264028549194,
+      "learning_rate": 7.217825360835473e-05,
+      "loss": 0.1121,
+      "step": 120
+    },
+    {
+      "epoch": 0.2275711159737418,
+      "grad_norm": 0.791406512260437,
+      "learning_rate": 5.713074385969457e-05,
+      "loss": 0.0977,
+      "step": 130
+    },
+    {
+      "epoch": 0.24507658643326038,
+      "grad_norm": 0.7328794002532959,
+      "learning_rate": 4.3193525326884435e-05,
+      "loss": 0.0691,
+      "step": 140
+    },
+    {
+      "epoch": 0.26258205689277897,
+      "grad_norm": 2.1033480167388916,
+      "learning_rate": 3.072756464904006e-05,
+      "loss": 0.0896,
+      "step": 150
+    },
+    {
+      "epoch": 0.26258205689277897,
+      "eval_loss": 0.08178930729627609,
+      "eval_runtime": 6.5966,
+      "eval_samples_per_second": 36.534,
+      "eval_steps_per_second": 18.343,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5000973307084800.0,
+  "total_flos": 7501459960627200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null