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:e032d92be86c1b8e9da9dfd4955ba866437581f7ba1e025aa273d4531276fd8f
+oid sha256:aeb616e8ff6ac618b92f5a78d960d3dcc48c4b2c2a4f920ab3df56196b559279
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b09ae0bc37051ed27136f17dc029d20588e86988f615a882c8311574076cf519
+oid sha256:b06ef87b992d39684ee5bfd47fd7ae4fe4c124f1407caf53d3f70510145ee571
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d73744cc9da6cf4515a44034b122856d46a3fed397efa1e527493ee573696292
+oid sha256:da70fcbf4bc000d633bdd59ff5bb75c3f527ccd5147f13a7552f0015370d4e68
 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": 0.0010875660611416045,
+  "epoch": 0.0013594575764270056,
   "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": 41.828,
       "eval_steps_per_second": 20.917,
       "step": 4
+    },
+    {
+      "epoch": 0.0013594575764270056,
+      "grad_norm": 47.0827522277832,
+      "learning_rate": 5e-05,
+      "loss": 29.7547,
+      "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": 2804271657517056.0,
+  "total_flos": 3505339571896320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null