Training in progress, step 4, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:717fb609ab909ccf38e7e12d81f3e42dad712eb4831267d4495f0ae96df9da34
+oid sha256:13ffe4664a235436601e39d8b6eb3f196ac3894fcec2c4a0237b1808c432e2e8
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0089472c3cfcad377895088495bcab0fd72bf2c4d0d3336410792b19b279683
+oid sha256:929bb5fec9436f892a991ba3be35d7bb0b77bf1fd982f6c87788c5602b0ab051
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc25fd3ce8b608cd5f1eb1770a93590a061eb465f0c9532df06d429ccad012ad
+oid sha256:06f7a776eb140b6aebd6cf0a67e09ea2f64ccd47b4895b84cbd24827bc294150
 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": 0.008519701810436636,
+  "epoch": 0.01703940362087327,
   "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": 12.247,
       "eval_steps_per_second": 6.124,
       "step": 2
+    },
+    {
+      "epoch": 0.012779552715654952,
+      "grad_norm": 19.740352630615234,
+      "learning_rate": 3e-05,
+      "loss": 16.2762,
+      "step": 3
+    },
+    {
+      "epoch": 0.01703940362087327,
+      "grad_norm": 19.82746124267578,
+      "learning_rate": 4e-05,
+      "loss": 15.088,
+      "step": 4
+    },
+    {
+      "epoch": 0.01703940362087327,
+      "eval_loss": 0.9377003908157349,
+      "eval_runtime": 32.3171,
+      "eval_samples_per_second": 12.254,
+      "eval_steps_per_second": 6.127,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2541371189624832.0,
+  "total_flos": 5170375868547072.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null