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:f99e2c0891c41a5dce7865073ed977426d16d8c6f21239a53c24f90072c6a7a2
+oid sha256:1a46311d142248e794ec5cfab89b6c046036a1f22de50cbda11d4d5a287c925c
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5faff2e795189a4987b859db915259e6b7a6751b1bb0bc6c85185c797e5d064b
+oid sha256:11dd6ec10b9b1235d1d7c225c232baf7269bcaf4c09b2f5a9ec4b2e28220fe0d
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aaa9e3b74578bef08c8ce245263a3b35a95c650bc0dbb1e32e055768b69671b4
+oid sha256:7a10c667363305ba7ff759c9b1766381acfb4158c87ced3a770de08d220a2d9c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0018005446647610902,
+  "epoch": 0.0027008169971416353,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 4.115,
       "eval_steps_per_second": 2.058,
       "step": 20
+    },
+    {
+      "epoch": 0.0018905718979991448,
+      "grad_norm": 2.304891586303711,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 6.6758,
+      "step": 21
+    },
+    {
+      "epoch": 0.0021606535977133083,
+      "grad_norm": 1.581033706665039,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 5.6989,
+      "step": 24
+    },
+    {
+      "epoch": 0.002250680830951363,
+      "eval_loss": 1.5958346128463745,
+      "eval_runtime": 1135.7037,
+      "eval_samples_per_second": 4.118,
+      "eval_steps_per_second": 2.06,
+      "step": 25
+    },
+    {
+      "epoch": 0.002430735297427472,
+      "grad_norm": 2.6412482261657715,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 6.319,
+      "step": 27
+    },
+    {
+      "epoch": 0.0027008169971416353,
+      "grad_norm": 1.005195140838623,
+      "learning_rate": 0.0,
+      "loss": 6.5737,
+      "step": 30
+    },
+    {
+      "epoch": 0.0027008169971416353,
+      "eval_loss": 1.592824101448059,
+      "eval_runtime": 1135.5852,
+      "eval_samples_per_second": 4.119,
+      "eval_steps_per_second": 2.06,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.317174717186048e+16,
+  "total_flos": 1.951957713420288e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null