Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b9c8339d1c47e0a4bcd66467ba812c91763286283f13bd46213e2d70a3e8e6e
+oid sha256:7d3398b2727113a04febaeb92c3b0a8af2dee554e23d8aa7a21d61c744301ccc
 size 247944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcf2cc8ca3ef9409067c7f22817433bf0c7778fc6bc90d1151a9ad418be018e1
+oid sha256:a0d517673dde3306f37670529f5ad1d5420c382ac75c5b65ffd69f6bd3a56b3a
 size 263088

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59d799f504d9e96669c3b322ccf044cf42ed69181feb6c152cba674fa2359f08
+oid sha256:8b3f32ce9472813d7cc4998dd6f54d487ccf79d88132a529ec2b28324f14a0f2
 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": 0.043478260869565216,
+  "epoch": 0.04830917874396135,
   "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": 56.855,
       "eval_steps_per_second": 28.428,
       "step": 9
+    },
+    {
+      "epoch": 0.04830917874396135,
+      "grad_norm": 4.50685977935791,
+      "learning_rate": 0.0002,
+      "loss": 44.0248,
+      "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": 748783927296.0,
+  "total_flos": 831982141440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null