Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:916e533f7ff18bed52c57bae4984dfb01d821e2739218550e9c6eefc420c886b
+oid sha256:52f1eaf03c7cc8b429c3d910ffe74f0f57383ccfdf36bab0994b9a6f42c26b2f
 size 25192688

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:029aeb43f5f7c57bbc82d3853b7a73df252cc72767723aadf863b09823a40546
+oid sha256:3032787d8bdf08a92a1c863e31d50f6847de3cf07900b37328e53f88e30fe9ae
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae27f7b41ce550bc2f2daf16c7d3f7ba4ba093c2050f241d7f74c271f07b0995
+oid sha256:4dab0c5e10c8896646e93964667566c959535ff7a242ad9726ec34c0427448ee
 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": 0.0004031140560832431,
+  "epoch": 0.0006046710841248646,
   "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": 9.1496,
       "step": 18
+    },
+    {
+      "epoch": 0.0004232697588874052,
+      "grad_norm": 4.392923355102539,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 7.797,
+      "step": 21
+    },
+    {
+      "epoch": 0.00048373686729989165,
+      "grad_norm": 1135.9619140625,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 8.145,
+      "step": 24
+    },
+    {
+      "epoch": 0.00048373686729989165,
+      "eval_loss": 1.8751978874206543,
+      "eval_runtime": 710.7939,
+      "eval_samples_per_second": 29.39,
+      "eval_steps_per_second": 14.695,
+      "step": 24
+    },
+    {
+      "epoch": 0.0005442039757123781,
+      "grad_norm": 480.12786865234375,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 6.7705,
+      "step": 27
+    },
+    {
+      "epoch": 0.0006046710841248646,
+      "grad_norm": 4.261571407318115,
+      "learning_rate": 0.0,
+      "loss": 7.6497,
+      "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": 364045186105344.0,
+  "total_flos": 538483504447488.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null