Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a221136dbd7c845c6c0c1550e77be0de60812d4d279b8dc7ce7a58800c49e9c
+oid sha256:7f4a808bd67186d7d670e4b2906f3abad9a64c53bca704ef674f7fb9fbafe356
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45663c9877b6e891d5df26606662cb699528ca87d2351c211a10529b55c9a87a
+oid sha256:6e7b05e382a0dc585a1edddaa3981f4516a2749fb31ef358641805de2c253630
 size 97487290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:011d57303a75fb8a2e485a8073e0f691c69b7d80a9f1120b703e475e9e6035b4
+oid sha256:ad03281210143d9b425d68b803482d2d514057ab8f987b89392de2b79cdb25d0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.001691411388836685,
+  "epoch": 0.0018793459875963165,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,13 @@
       "eval_samples_per_second": 21.164,
       "eval_steps_per_second": 21.164,
       "step": 9
+    },
+    {
+      "epoch": 0.0018793459875963165,
+      "grad_norm": 0.36688560247421265,
+      "learning_rate": 0.0002,
+      "loss": 2.0788,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -116,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 626150741114880.0,
+  "total_flos": 695723045683200.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null