Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:727bdd6a9beeda1194700b9c70686c0ab3366217c6c0115ce3171692cf5aa6c0
+oid sha256:dfd58d2eadf0dadb692b2498d8aa5a8dc053e77196e2eb134755ade424f0712a
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f805ace5fd19a0e7da48bbae960930d79bc17b56cbbbc46d968b2c7dd1e88b63
+oid sha256:2520f010404f96366ecfb5f827d92bc3e8e3de48435ca43aefba9d077e9fe551
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f5747607b5d29e5207bb2665581cc33fefa21fc4bf0d5a940841f4802219bdc
+oid sha256:5a0d81cbc96d19404eb8160ab4b67820062c76894bae24585c18f6d80ce5c98c
 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": 0.0014855254117690751,
+  "epoch": 0.0022282881176536127,
   "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": 17.434,
       "eval_steps_per_second": 8.719,
       "step": 20
+    },
+    {
+      "epoch": 0.0015598016823575288,
+      "grad_norm": 10.149421691894531,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 6.4206,
+      "step": 21
+    },
+    {
+      "epoch": 0.00178263049412289,
+      "grad_norm": 7.656150817871094,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 6.4307,
+      "step": 24
+    },
+    {
+      "epoch": 0.001856906764711344,
+      "eval_loss": 1.5194510221481323,
+      "eval_runtime": 325.1484,
+      "eval_samples_per_second": 17.435,
+      "eval_steps_per_second": 8.719,
+      "step": 25
+    },
+    {
+      "epoch": 0.002005459305888251,
+      "grad_norm": 9.99641227722168,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 6.298,
+      "step": 27
+    },
+    {
+      "epoch": 0.0022282881176536127,
+      "grad_norm": 10.378310203552246,
+      "learning_rate": 0.0,
+      "loss": 5.5548,
+      "step": 30
+    },
+    {
+      "epoch": 0.0022282881176536127,
+      "eval_loss": 1.5158554315567017,
+      "eval_runtime": 324.9413,
+      "eval_samples_per_second": 17.446,
+      "eval_steps_per_second": 8.725,
+      "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": 7382868191870976.0,
+  "total_flos": 1.1074302287806464e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null