Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cfa9aaf0d3cbf6a455ad798436f2b4617df52a98fedbf7f49bb6981d8e870d0
+oid sha256:0b1a0b9987616c43bf7b73c8b2e0676304e45a41d6a620889961c83aa4faf41c
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6f6e0396869827426534cd1740cee0867b7f09f45122fed1af7505e28b8d1f9
+oid sha256:692d60662f43cb761f40803f3fbf4ea8a635f60db78f216cd3e3e5f4389995c6
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af93c27c5bde1ecbb7889f2aeca50c50c9fe4237cbad3fb13649f213484bc331
+oid sha256:ea4c48ee7480df731ae4c1602581624f35ae613cd74affa179ec0272b4bae86a
 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": 0.0013753089072740948,
+  "epoch": 0.0017191361340926185,
   "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": 5.447,
       "eval_steps_per_second": 2.724,
       "step": 4
+    },
+    {
+      "epoch": 0.0017191361340926185,
+      "grad_norm": 8.735809326171875,
+      "learning_rate": 5e-05,
+      "loss": 58.6865,
+      "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": 5461736926740480.0,
+  "total_flos": 6807382256517120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null