Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b5b970d09d4cbd24a80743cc054aeff9963ded3de71eb0c85c035ffa82c4ddd
+oid sha256:8fdd1d088b9a8f5ca677392c5d220f1c1b9af5e6974e157737a1969a04285411
 size 78480072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ef54933cabdae91fc35f701aa5d1e254f0f2935284153355ec8f76df7f389d4
+oid sha256:c321c63f5a9918f67f6c64c6fd5966f5a0227b729c4bba93d5767c990749d967
 size 157104826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee53bcfdd5f1a8c97c44b57116be4b9598eeed231f258e11af07fe6b34c0936f
+oid sha256:9227cc7da75332ec0331d435737788eaf49b16cbca5fc059b601ca71ff219c8c
 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": 0.0027267459695286137,
+  "epoch": 0.004090118954292921,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 2.2332,
       "step": 18
+    },
+    {
+      "epoch": 0.0028630832680050446,
+      "grad_norm": 0.9254711270332336,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.019,
+      "step": 21
+    },
+    {
+      "epoch": 0.0032720951634343364,
+      "grad_norm": 0.8415443897247314,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.1299,
+      "step": 24
+    },
+    {
+      "epoch": 0.0032720951634343364,
+      "eval_loss": 2.0182554721832275,
+      "eval_runtime": 157.4278,
+      "eval_samples_per_second": 19.622,
+      "eval_steps_per_second": 9.814,
+      "step": 24
+    },
+    {
+      "epoch": 0.0036811070588636287,
+      "grad_norm": 0.7659211754798889,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.1099,
+      "step": 27
+    },
+    {
+      "epoch": 0.004090118954292921,
+      "grad_norm": 0.586293637752533,
+      "learning_rate": 0.0,
+      "loss": 2.1006,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2631599048884224.0,
+  "total_flos": 3885912614240256.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null