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:f4293f909592115111438dad1611f0f471ffa5e7de47a7b9462c26b94d3ed5d6
+oid sha256:d86810f7ac80774e47e1ac2abd920d0fa0ba1b25c947518426a2e748c01cba0e
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc9baca8e9f50fce50857b12d2641448b4adf61852f7375edca098d3003947d0
+oid sha256:3c720128473db6af6eecb2bfdf0790936f0ceee45795e46887725af92a32b681
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90b49e55746f1efde0c49b53b1686f55fab15d8870510125361a613a63a60f9c
+oid sha256:6988304369cf1930141352fe7025e91f20bdfbba03640e6a295c2917f2efb5d3
 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": 0.029712163416898793,
+  "epoch": 0.059424326833797586,
   "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": 4.15,
       "eval_steps_per_second": 2.075,
       "step": 2
+    },
+    {
+      "epoch": 0.04456824512534819,
+      "grad_norm": 1.9398624897003174,
+      "learning_rate": 3e-05,
+      "loss": 37.8162,
+      "step": 3
+    },
+    {
+      "epoch": 0.059424326833797586,
+      "grad_norm": 2.3769500255584717,
+      "learning_rate": 4e-05,
+      "loss": 38.1807,
+      "step": 4
+    },
+    {
+      "epoch": 0.059424326833797586,
+      "eval_loss": 2.3615305423736572,
+      "eval_runtime": 27.4708,
+      "eval_samples_per_second": 4.15,
+      "eval_steps_per_second": 2.075,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5065926676316160.0,
+  "total_flos": 1.005269824831488e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null