Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05b68a2c4e0d04ae65af7d491854f8563ed062dbdde321a30972cd933dcc45f5
+oid sha256:64e59543ed3db35d3955efe36505b11461d18d025fa3637bf32a8e83d86c5c2c
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6073cbcb989fbea8f12cc9a08ab485085992ed426e50335f09fa20cf147a2614
+oid sha256:650c66d43d672dfb37662a980b13caaac5d26a3368bcee98aeaa79335dd88bbf
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5727736a3dd8a3d982c0258cc59e117d798ca87e20e5f2b5c0e95c713a0d726
+oid sha256:e643e91a378a8f5ebe700250e11649841cfdf971f423f62c9d5f416e35fe6130
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0003383636732760371,
+  "epoch": 0.0005075455099140556,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 0.0773,
       "step": 18
+    },
+    {
+      "epoch": 0.00035528185693983896,
+      "grad_norm": 0.19737200438976288,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.045,
+      "step": 21
+    },
+    {
+      "epoch": 0.0004060364079312445,
+      "grad_norm": 0.22253718972206116,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0293,
+      "step": 24
+    },
+    {
+      "epoch": 0.0004060364079312445,
+      "eval_loss": 0.06464230269193649,
+      "eval_runtime": 1263.0193,
+      "eval_samples_per_second": 19.705,
+      "eval_steps_per_second": 9.853,
+      "step": 24
+    },
+    {
+      "epoch": 0.00045679095892265005,
+      "grad_norm": 0.43239113688468933,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.0639,
+      "step": 27
+    },
+    {
+      "epoch": 0.0005075455099140556,
+      "grad_norm": 0.3265659213066101,
+      "learning_rate": 0.0,
+      "loss": 0.0522,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1479717609799680.0,
+  "total_flos": 2200275750223872.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null