Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7f700e43364cea37a4977743a68076c493b164e2e9f129449b6b2a055870d61
+oid sha256:6a8700b8d4d4fb41a7e5e434aca30a1623884fc51748f947f6635f550aaeb309
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:478dc67ec032cf0fef24cc72bb295555a29e7bca4095725e229a3075486cf438
+oid sha256:89069e715a5f0c1b7c3674352180fd6a0c554919f799b350ddb131b22096d49f
 size 168149074

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a51a564a9acaa6f52f6d5c610defc3027f9872eda07a196dcfa4d35a3357966d
+oid sha256:679804c92bce17811c5948ecfc2f441f07bd418fa9cf59ccc02ed84ece0ee87e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06829946ff807c7143728448cc1bf384944e638865601317db4b29a92003bb11
+oid sha256:008d83c4f5ee0c3b0aa2ca88e92cb7f21d43acfd48a8bc37442b67fb3134fa7c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6666666666666666,
+  "epoch": 1.0,
   "eval_steps": 2,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -125,6 +125,57 @@
       "eval_samples_per_second": 7.363,
       "eval_steps_per_second": 4.207,
       "step": 10
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 3.651534080505371,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.9021,
+      "step": 11
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.674623489379883,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.6883,
+      "step": 12
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 2.8664534091949463,
+      "eval_runtime": 0.948,
+      "eval_samples_per_second": 7.384,
+      "eval_steps_per_second": 4.219,
+      "step": 12
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 3.0388295650482178,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.6667,
+      "step": 13
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 2.702390193939209,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.5641,
+      "step": 14
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "eval_loss": 2.833918333053589,
+      "eval_runtime": 0.9702,
+      "eval_samples_per_second": 7.215,
+      "eval_steps_per_second": 4.123,
+      "step": 14
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.66922926902771,
+      "learning_rate": 0.0,
+      "loss": 3.031,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -139,12 +190,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3699128496291840.0,
+  "total_flos": 5502453638234112.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null