Training in progress, step 7, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12d983fb77b7fe853a56397d420b018a96a1883d74f6de8c327035acfa6fd38c
+oid sha256:53fbe16d720690337e01130e2ae3a4240a091d59a6ac189ed2789fe2a9e3ae77
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1146031d96072a620b4bc0926116eab7917994af6c0f15779513ad896790f63
+oid sha256:c2153d11a38206602ecba503b32f795936548465c27a3cc5869ef91ffcbee92a
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c30b90cacd6043668a9fceb65b4815e3ca7a9635af8292b75bda3517456e3b3
+oid sha256:536cf2ee5714e0fe8574a09e9451435b7dd3aa7fe0c5509c99b29cdd87d45c39
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
+oid sha256:5d44c0ecfb16f05885a8478afdaa40e988069bb6891bbc6c82185a9b1533b4c7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9795918367346939,
+  "epoch": 1.1428571428571428,
   "eval_steps": 2,
-  "global_step": 6,
+  "global_step": 7,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -81,6 +81,13 @@
       "eval_samples_per_second": 38.836,
       "eval_steps_per_second": 21.183,
       "step": 6
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 6.098566055297852,
+      "learning_rate": 7e-05,
+      "loss": 2.4494,
+      "step": 7
     }
   ],
   "logging_steps": 1,
@@ -95,12 +102,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3995970589163520.0,
+  "total_flos": 4655099758510080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null