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:eef49ba54ff5ce4182a3309c5e577f11362c3c102628bb68ab75173919ada57a
+oid sha256:9a3cf1f4dfd4a46c22b3c2861dfeda1018e8c7027e0698206c3cf40e241738ba
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e158d79bce209c237fa34566ecc216646bea8cb0699a1dd4f0959e82c3339c59
+oid sha256:ff49eb7721a5fdd6fc806bfdd98efd5d8c39cf576ec4facd0fae28695e539330
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5038562034e3fb7746f0f33a324281a510fea3cd63a44cb1d968e86f32f52f9
+oid sha256:7c4a4ec28779ce8465436e6ff167fb1f67546297f6473ac35b92379d085a9bb6
 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": 0.0022536004788901018,
+  "epoch": 0.0028170005986126274,
   "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": 8.063,
       "eval_steps_per_second": 4.031,
       "step": 4
+    },
+    {
+      "epoch": 0.0028170005986126274,
+      "grad_norm": 2.100451946258545,
+      "learning_rate": 5e-05,
+      "loss": 13.6954,
+      "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": 9181992100823040.0,
+  "total_flos": 1.139833502171136e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null