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:a7815ed3c09a50985496ed590e244b83031353f519f1dc2a0f52ca6222c9e8d1
+oid sha256:943fd5bf6f5308bdc99e90093962bd7efc9863c6aac4841f873bea771ccf8009
 size 5327496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c09d36e747c248a7f4f95a356ce0d997230f1d869b9182817d8a8d7389fad12d
+oid sha256:4114c261efca8ee2b658d1f7514c75410cdb644e8729222e8c2d8575b84d5cd9
 size 2857722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6146a8a9abe4087455e34e0d672ef03b47202a9ec724afa8e74ad89db062abd3
+oid sha256:b37eb23c7db03165d9b298533a106ef93fbe349e32cf744565e4d6da5d2b28dc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.009819967266775777,
+  "epoch": 0.016366612111292964,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "eval_samples_per_second": 65.366,
       "eval_steps_per_second": 32.683,
       "step": 6
+    },
+    {
+      "epoch": 0.011456628477905073,
+      "grad_norm": 1.263313889503479,
+      "learning_rate": 0.00014,
+      "loss": 7.2238,
+      "step": 7
+    },
+    {
+      "epoch": 0.01309328968903437,
+      "grad_norm": 2.363508701324463,
+      "learning_rate": 0.00016,
+      "loss": 10.8441,
+      "step": 8
+    },
+    {
+      "epoch": 0.014729950900163666,
+      "grad_norm": 1.4241231679916382,
+      "learning_rate": 0.00018,
+      "loss": 6.0752,
+      "step": 9
+    },
+    {
+      "epoch": 0.014729950900163666,
+      "eval_loss": 2.0876362323760986,
+      "eval_runtime": 3.9381,
+      "eval_samples_per_second": 65.514,
+      "eval_steps_per_second": 32.757,
+      "step": 9
+    },
+    {
+      "epoch": 0.016366612111292964,
+      "grad_norm": 1.7291141748428345,
+      "learning_rate": 0.0002,
+      "loss": 9.4806,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 12733630119936.0,
+  "total_flos": 21222716866560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null