Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f8d7c1f0f792d5521f2984c7e83f1d753f2b7fccf175ea14ee5502a380be231
+oid sha256:25a8b5861b88c98f2d0644df3e89a5824209a13e4dfd80d9e805bbe1e2f03d1f
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f2fcf57821bb6e00f537c7469cb857ddebe2e6370221ac15e02d8ef19e7dc14
+oid sha256:9cc2cf51b4a5059c5a7859ee786d8a22458a4bf4142848037f947d6488e4e9a5
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:494c8c60ef0549be376f24afcc76568f7deec252f4421bd32e533c506e648827
+oid sha256:4657ed5dc8f18f92b9c19e106cbb47a5d3654d9de41fb19730a5634e589e2b00
 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": 0.002012467234517838,
+  "epoch": 0.003018700851776757,
   "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": 24.373,
       "eval_steps_per_second": 12.187,
       "step": 100
+    },
+    {
+      "epoch": 0.002213713957969622,
+      "grad_norm": 1.271390676498413,
+      "learning_rate": 0.0002,
+      "loss": 1.3306,
+      "step": 110
+    },
+    {
+      "epoch": 0.0024149606814214057,
+      "grad_norm": 0.9250841736793518,
+      "learning_rate": 0.0002,
+      "loss": 1.1564,
+      "step": 120
+    },
+    {
+      "epoch": 0.0026162074048731894,
+      "grad_norm": 1.0612225532531738,
+      "learning_rate": 0.0002,
+      "loss": 1.2448,
+      "step": 130
+    },
+    {
+      "epoch": 0.002817454128324973,
+      "grad_norm": 0.643467366695404,
+      "learning_rate": 0.0002,
+      "loss": 1.1702,
+      "step": 140
+    },
+    {
+      "epoch": 0.003018700851776757,
+      "grad_norm": 1.3284869194030762,
+      "learning_rate": 0.0002,
+      "loss": 1.2826,
+      "step": 150
+    },
+    {
+      "epoch": 0.003018700851776757,
+      "eval_loss": 1.407882809638977,
+      "eval_runtime": 858.6574,
+      "eval_samples_per_second": 24.367,
+      "eval_steps_per_second": 12.184,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.331531527847936e+16,
+  "total_flos": 3.48774183469056e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null