Training in progress, step 4, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19c75ffcd32833697ba32d14139488538ad36026e55ccc65aa74484b72bdf51c
+oid sha256:46d268f515f443325f0d1aeae3a2954d033c9978efa11137dc73489da61c5b5a
 size 32856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edb6a631d64e86a3e7f68891ea7ad9e6687c24c9be7abe939ce94a826f2b8d05
+oid sha256:87ec68aa6fe771a138f817cbe4b9989dff71e471dd5e06633e950d7268f2485f
 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": 0.0006864448591715469,
+  "epoch": 0.0013728897183430937,
   "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": 854.303,
       "eval_steps_per_second": 427.239,
       "step": 2
+    },
+    {
+      "epoch": 0.0010296672887573203,
+      "grad_norm": 4.281859874725342,
+      "learning_rate": 3e-05,
+      "loss": 177.0625,
+      "step": 3
+    },
+    {
+      "epoch": 0.0013728897183430937,
+      "grad_norm": 4.1518964767456055,
+      "learning_rate": 4e-05,
+      "loss": 177.3125,
+      "step": 4
+    },
+    {
+      "epoch": 0.0013728897183430937,
+      "eval_loss": 11.07065200805664,
+      "eval_runtime": 5.9277,
+      "eval_samples_per_second": 827.811,
+      "eval_steps_per_second": 413.99,
+      "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