Training in progress, step 4, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ca6fad1afea9fc8d422cdec71b2f03f1204597a7eace3b6b0f934e475ae1c04
+oid sha256:2cbf0864f0aa8de4d896fd13b3aa842d71ac879b706ad3a0d8a4fd6b9efde96f
 size 32856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40b2934518ce43eb1c0cfc11c21944bbb0d79652f000106ea78e57d73d1df2bc
+oid sha256:2c9b928c6c37d809e31fb873483ca130fb387f1a0cf751bf4de8f08fbcc44d70
 size 71358

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f038db249d80ff27a0bc300d721fbbfd6aa33f22e42efc2048660f2d9f8c09f6
+oid sha256:1b5059cf0c71c51f02ee969590c9c397dea8c41610c914bdf8477692d8344aa4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60f8f27a9d76e31d3721bb37f2f4c76e866b8dedf8d4315f175dac906a4a966d
+oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006817213463996591,
+  "epoch": 0.013634426927993182,
   "eval_steps": 2,
-  "global_step": 2,
+  "global_step": 4,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,28 @@
       "eval_samples_per_second": 270.187,
       "eval_steps_per_second": 135.366,
       "step": 2
+    },
+    {
+      "epoch": 0.010225820195994887,
+      "grad_norm": 5.093106746673584,
+      "learning_rate": 3e-05,
+      "loss": 177.0,
+      "step": 3
+    },
+    {
+      "epoch": 0.013634426927993182,
+      "grad_norm": 4.387277126312256,
+      "learning_rate": 4e-05,
+      "loss": 176.9375,
+      "step": 4
+    },
+    {
+      "epoch": 0.013634426927993182,
+      "eval_loss": 11.062247276306152,
+      "eval_runtime": 2.1776,
+      "eval_samples_per_second": 227.31,
+      "eval_steps_per_second": 113.885,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5976883200.0,
+  "total_flos": 11953766400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null