Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e165c2e7f946c742f3915fb66a16eeaa1749ed305b45991840bd7874fddb253d
+oid sha256:b9176d6cb285a7565b6c883525273c1bc829fd5df5462ddea1532b8127fbb357
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aadd5744c82c030f567adec032896b0c610d21596db1625f38d96b29f9e410d0
+oid sha256:917072ddd5c3248ca903161fb833b274adc234d20344b446cc6598e0441ade70
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24f47c54df36a0fc93d41badfcbca78fafacd8a01e20d0c8945ea43ab1f962bf
+oid sha256:ac387a221e32ece68b5109e931eb6896f3dc51b7ed68765c472ef81382fe9890
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03351235230934479,
+  "epoch": 0.04296455424274973,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 0.0839,
       "step": 35
+    },
+    {
+      "epoch": 0.034371643394199784,
+      "grad_norm": 0.5819281935691833,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0618,
+      "step": 40
+    },
+    {
+      "epoch": 0.034371643394199784,
+      "eval_loss": 0.08588320761919022,
+      "eval_runtime": 25.4483,
+      "eval_samples_per_second": 19.255,
+      "eval_steps_per_second": 9.627,
+      "step": 40
+    },
+    {
+      "epoch": 0.03866809881847476,
+      "grad_norm": 0.5416504144668579,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0687,
+      "step": 45
+    },
+    {
+      "epoch": 0.04296455424274973,
+      "grad_norm": 1.3137935400009155,
+      "learning_rate": 0.0,
+      "loss": 0.1332,
+      "step": 50
+    },
+    {
+      "epoch": 0.04296455424274973,
+      "eval_loss": 0.08247209340333939,
+      "eval_runtime": 25.2792,
+      "eval_samples_per_second": 19.384,
+      "eval_steps_per_second": 9.692,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4428262790922240.0,
+  "total_flos": 5596832138526720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null