Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f91552f07a99b4c01b0e68cd3263be2da8d0a4d1d8a848df1e8d1aad6fa0044
+oid sha256:f7bc874a66a24ce27587e4b6d12670bb5b0e2ca3b827351a5d14e84d8e0c92e1
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1dea5cbc8294d641cd14638bd21bd201af01bf653ea26538153739caa585688
+oid sha256:f058e7844cab96730b441184a3b604f31c0253f13594925959fd4c0e9019a150
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8ad0b3c8c5cceedf5a189a90eb9b07f92d6d9af65176e2a41a16db159f342c9
+oid sha256:3aae4c725c8b8e7408fdaf6588ee4472e1fe374a10f99e0334dc9b8fe25267ec
 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": 0.025236593059936908,
+  "epoch": 0.031545741324921134,
   "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": 11.151,
       "eval_steps_per_second": 5.596,
       "step": 4
+    },
+    {
+      "epoch": 0.031545741324921134,
+      "grad_norm": 7.284046649932861,
+      "learning_rate": 5e-05,
+      "loss": 52.5808,
+      "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": 4886199407738880.0,
+  "total_flos": 6189185916469248.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null