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:aa878d5c7ba1dcf38ea7c9593b57d924ae067ab07bbca32086de8e5b567eefa1
+oid sha256:c4b36801039b7203e635bd732adfe2072950c5cb8ae24fc72ed41baaf8ef26a7
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:453f18ace058d63836a26ab6e10c4ccd660f1e161ef2112eaa44e37a6a803d28
+oid sha256:fa08011ebbddcd3c98b59dc11ecdf630ca480d488560a7080664387e8358c055
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c900d4c6853d677a7868b2838751ed164390e83255a80643445dc284e68bad62
+oid sha256:2fea276383daa6be11cb41bcf079e20917a66b8a1df06264809ff50445c989c9
 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": 0.01876348625574632,
+  "epoch": 0.028145229383619477,
   "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": 270.204,
       "eval_steps_per_second": 135.102,
       "step": 100
+    },
+    {
+      "epoch": 0.02063983488132095,
+      "grad_norm": 0.061177678406238556,
+      "learning_rate": 0.0002,
+      "loss": 10.3511,
+      "step": 110
+    },
+    {
+      "epoch": 0.02251618350689558,
+      "grad_norm": 0.05322906747460365,
+      "learning_rate": 0.0002,
+      "loss": 10.3508,
+      "step": 120
+    },
+    {
+      "epoch": 0.024392532132470213,
+      "grad_norm": 0.03260466456413269,
+      "learning_rate": 0.0002,
+      "loss": 10.3486,
+      "step": 130
+    },
+    {
+      "epoch": 0.026268880758044844,
+      "grad_norm": 0.03364917263388634,
+      "learning_rate": 0.0002,
+      "loss": 10.3492,
+      "step": 140
+    },
+    {
+      "epoch": 0.028145229383619477,
+      "grad_norm": 0.053879886865615845,
+      "learning_rate": 0.0002,
+      "loss": 10.3484,
+      "step": 150
+    },
+    {
+      "epoch": 0.028145229383619477,
+      "eval_loss": 10.347860336303711,
+      "eval_runtime": 8.1947,
+      "eval_samples_per_second": 273.837,
+      "eval_steps_per_second": 136.918,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2450407096320.0,
+  "total_flos": 3701472460800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null