Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afe801195588dcca0b42bf42c8762282d3e28d187ab08a3429c9a2649a9e4654
+oid sha256:7a7c4ea12a8e3ac3890b037bb3936898f0379fea4dca7d48336d227dfcb26c21
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b38192017499d88b35afb9510265953c345011536228ffed21a7bbbf8ef95c56
+oid sha256:02c9719df590440ca34a2c10daad68af9af5fac6d295805e28cec2d3315a52f3
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:345968a5a188539d394ed023335b7f413df9a60bcf364c913f284e67123ad6cf
+oid sha256:4871bdb487ae2495439e7e9e24e41cf3db620a0da968c15e1b08df276dfabdd9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
+oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0028110862212851937,
+  "epoch": 0.003513857776606492,
   "eval_steps": 2,
-  "global_step": 4,
+  "global_step": 5,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,13 @@
       "eval_samples_per_second": 12.118,
       "eval_steps_per_second": 6.061,
       "step": 4
+    },
+    {
+      "epoch": 0.003513857776606492,
+      "grad_norm": 0.6244788765907288,
+      "learning_rate": 5e-05,
+      "loss": 16.8381,
+      "step": 5
     }
   ],
   "logging_steps": 1,
@@ -73,12 +80,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9656984131338240.0,
+  "total_flos": 1.203165236035584e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null