Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12a67b918ec83ab7425d638d6fade29fa527aa548c14e0edf1937e4ac252c9d6
+oid sha256:efa4076d3036e92da0d3df4bd29c1411832b1ec2193be577bf158fed7126dd3d
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b313d77671947acb5bd8acc8715ed392879628ed05dee616c7d189a7fd6b7306
+oid sha256:05c31c3c5111ced63a5d1e389e6ffc0b7188711535e376190c8328943b8920f0
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:097784a8459b5523bce7987c706d00d9b0797f9210986fe9634a24ded975f97c
+oid sha256:62ed3fd3312f96c17ea93ab3f7344a9def6141fa3d024e167875cba869f24ea5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011368480886741509,
+  "epoch": 0.017052721330112264,
   "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": 17.036,
       "eval_steps_per_second": 8.529,
       "step": 20
+    },
+    {
+      "epoch": 0.011936904931078584,
+      "grad_norm": 1.7508783340454102,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 2.0437,
+      "step": 21
+    },
+    {
+      "epoch": 0.013642177064089812,
+      "grad_norm": 1.6392158269882202,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.0193,
+      "step": 24
+    },
+    {
+      "epoch": 0.014210601108426887,
+      "eval_loss": 2.1386632919311523,
+      "eval_runtime": 43.4885,
+      "eval_samples_per_second": 17.039,
+      "eval_steps_per_second": 8.531,
+      "step": 25
+    },
+    {
+      "epoch": 0.015347449197101038,
+      "grad_norm": 1.4378986358642578,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 1.913,
+      "step": 27
+    },
+    {
+      "epoch": 0.017052721330112264,
+      "grad_norm": 1.2889617681503296,
+      "learning_rate": 0.0,
+      "loss": 2.0382,
+      "step": 30
+    },
+    {
+      "epoch": 0.017052721330112264,
+      "eval_loss": 2.1310107707977295,
+      "eval_runtime": 43.4946,
+      "eval_samples_per_second": 17.037,
+      "eval_steps_per_second": 8.53,
+      "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": 7511608746049536.0,
+  "total_flos": 1.1221045163851776e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null