Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14af54d1bff653783908b908888dbc1948022361f8b41d710bc50bc6acdee2cb
+oid sha256:96560be515fe73b42a1922866843ae499b8ae564876bef1f0a8592e835ad165e
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3393c7aa11e15ede1fe9eaac25fa5d5a9a22fff768e34355fa60edc8ae73220
+oid sha256:8cc319b0d475cd67cab98af7c0bf05281b9810955945520388b1a41b3091bf0b
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff5440c0314dadc3defe4b4803f353543d71edfcba882e67961bec9458fb6240
+oid sha256:9ea24ba22f005ab5531315a7c25fe17ce3b0d82d32e4d057cd4a8d9beeaa0eb4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
+oid sha256:532138a5ca880d8da393ae449e5715b2766def36b8838785ca08d07228b119b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.11444921316165951,
+  "epoch": 0.15259895088221268,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 13.592,
       "eval_steps_per_second": 6.827,
       "step": 15
+    },
+    {
+      "epoch": 0.12207916070577014,
+      "grad_norm": 0.17542776465415955,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.2538,
+      "step": 16
+    },
+    {
+      "epoch": 0.12970910824988077,
+      "grad_norm": 0.22913815081119537,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.4404,
+      "step": 17
+    },
+    {
+      "epoch": 0.13733905579399142,
+      "grad_norm": 0.16341139376163483,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.2628,
+      "step": 18
+    },
+    {
+      "epoch": 0.14496900333810206,
+      "grad_norm": 0.17043715715408325,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.3106,
+      "step": 19
+    },
+    {
+      "epoch": 0.15259895088221268,
+      "grad_norm": 0.15494485199451447,
+      "learning_rate": 0.0,
+      "loss": 0.2552,
+      "step": 20
+    },
+    {
+      "epoch": 0.15259895088221268,
+      "eval_loss": 0.22873683273792267,
+      "eval_runtime": 9.7741,
+      "eval_samples_per_second": 22.611,
+      "eval_steps_per_second": 11.357,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.1362467066085376e+16,
+  "total_flos": 2.8529528527650816e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null