Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1ba11c3907ff10759f1f55fb0e5e40ac436fd17caff80cc794a59b2888a4fe4
+oid sha256:8ed090d487cdc9b5aa3341481357254b238cfd291f94ab79b0f143526da57202
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef656700a5944accddc894e83b805b77aa296b66c0db854deb35c56279f1e958
+oid sha256:72c21c0ece7af4b4a9cf8ca83046e312bc388078c867b0c13c7a7fce691a9e90
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb665841853cc42c910cb63819d00b335b3d08b5c5ab669fcca3e270facf08f4
+oid sha256:cb8f742328bfffa68d3697fe4655cdfe31ad19b761f081134e1ec9c8c44b0fce
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d605401690d7669ff16aeaca6820cbd8d0d605afe748c51045ce90888810a22
+oid sha256:baae720e33260fead254c87141d85e241b839ae924033bfd9652fb777f3f1bf0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0008633155634213196,
+  "epoch": 0.0012949733451319795,
   "eval_steps": 13,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -65,6 +65,42 @@
       "learning_rate": 0.00018090169943749476,
       "loss": 6.7296,
       "step": 18
+    },
+    {
+      "epoch": 0.0009064813415923856,
+      "grad_norm": 3.6164493560791016,
+      "learning_rate": 0.00016494480483301836,
+      "loss": 6.2438,
+      "step": 21
+    },
+    {
+      "epoch": 0.0010359786761055835,
+      "grad_norm": 4.651533603668213,
+      "learning_rate": 0.00014539904997395468,
+      "loss": 6.3792,
+      "step": 24
+    },
+    {
+      "epoch": 0.0011223102324477154,
+      "eval_loss": 1.5663001537322998,
+      "eval_runtime": 956.4981,
+      "eval_samples_per_second": 10.199,
+      "eval_steps_per_second": 5.1,
+      "step": 26
+    },
+    {
+      "epoch": 0.0011654760106187814,
+      "grad_norm": 3.52091383934021,
+      "learning_rate": 0.00012334453638559057,
+      "loss": 6.5441,
+      "step": 27
+    },
+    {
+      "epoch": 0.0012949733451319795,
+      "grad_norm": 4.742680549621582,
+      "learning_rate": 0.0001,
+      "loss": 6.3389,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -84,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6534646443540480.0,
+  "total_flos": 9801969665310720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null