Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b376b4e023f5d02eaa8a33082a0363eb6e4bb7a1e0aef97f5632511708b89c4
+oid sha256:bc1a1e40f8111cc8e3ad0e946d4999c36c298e878c75f03c9fa5b6ddd8d25fb8
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:601c8cf9a0f6e80f286e928eaf41a6f7c230c99935867c713c7349721fd60342
+oid sha256:48795db0ba61d803945acd4cbab606591bdbeee6ebf9cfe39445b617560fdd30
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f433ed62c38200cb99bd4ea92305aacec81b1a38d1e001768339ab1f472e6821
+oid sha256:efc34bf5a1aa1dda21c8afaad6d34fdfa99b7401dc8eff01d3fea28523c5f49b
 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": 0.06818181818181818,
+  "epoch": 0.08741258741258741,
   "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": 3.3863,
       "step": 35
+    },
+    {
+      "epoch": 0.06993006993006994,
+      "grad_norm": 2.0674448013305664,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.5705,
+      "step": 40
+    },
+    {
+      "epoch": 0.06993006993006994,
+      "eval_loss": 3.375098705291748,
+      "eval_runtime": 17.6331,
+      "eval_samples_per_second": 13.667,
+      "eval_steps_per_second": 6.862,
+      "step": 40
+    },
+    {
+      "epoch": 0.07867132867132867,
+      "grad_norm": 1.7660764455795288,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.384,
+      "step": 45
+    },
+    {
+      "epoch": 0.08741258741258741,
+      "grad_norm": 1.2882437705993652,
+      "learning_rate": 0.0,
+      "loss": 3.2939,
+      "step": 50
+    },
+    {
+      "epoch": 0.08741258741258741,
+      "eval_loss": 3.3708629608154297,
+      "eval_runtime": 17.5176,
+      "eval_samples_per_second": 13.758,
+      "eval_steps_per_second": 6.907,
+      "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": 8133662918836224.0,
+  "total_flos": 1.0598409257877504e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null