Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b497e221b87b82d5cdbdd5dd25d2ef067aea7f69cb3482d0342360c1e2d5b4e
+oid sha256:c15fd40905c39b6a585d5ca0294c344111af19185eb1051b9c52136d9c770bc8
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:152e72acf6aee19d8c818757b8e1d1aac99e0382965a6b6f003e8dbce4ecf70a
+oid sha256:0a30500e9376f12fe53d54c5520d3ac4105160e2363ddd2ea7e3ee5383a4e5b7
 size 45276986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27664fe9ad8ed8445e33c7255f967acf6b37dd9b2ca722042210d22bd07b0640
+oid sha256:a55e9c336339d6fd13d64d8454d14449f18f5cdad9904b170065366b9868f8c6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab098d97568c94b26c087e3ff4fd649c3aaa775049e6dbf18e927dde2c5feee8
+oid sha256:06829946ff807c7143728448cc1bf384944e638865601317db4b29a92003bb11
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.671506352087114e-05,
+  "epoch": 0.00011343012704174228,
   "eval_steps": 2,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -66,6 +66,65 @@
       "learning_rate": 0.0001,
       "loss": 3.1715,
       "step": 5
+    },
+    {
+      "epoch": 6.805807622504538e-05,
+      "grad_norm": 1.5034862756729126,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 2.9514,
+      "step": 6
+    },
+    {
+      "epoch": 6.805807622504538e-05,
+      "eval_loss": 2.9851348400115967,
+      "eval_runtime": 873.7444,
+      "eval_samples_per_second": 42.484,
+      "eval_steps_per_second": 21.242,
+      "step": 6
+    },
+    {
+      "epoch": 7.94010889292196e-05,
+      "grad_norm": 1.6210209131240845,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 2.9009,
+      "step": 7
+    },
+    {
+      "epoch": 9.074410163339382e-05,
+      "grad_norm": 1.660132884979248,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 2.7984,
+      "step": 8
+    },
+    {
+      "epoch": 9.074410163339382e-05,
+      "eval_loss": 2.79468035697937,
+      "eval_runtime": 873.5775,
+      "eval_samples_per_second": 42.492,
+      "eval_steps_per_second": 21.246,
+      "step": 8
+    },
+    {
+      "epoch": 0.00010208711433756806,
+      "grad_norm": 1.53206205368042,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.7431,
+      "step": 9
+    },
+    {
+      "epoch": 0.00011343012704174228,
+      "grad_norm": 1.5387572050094604,
+      "learning_rate": 5e-05,
+      "loss": 2.6737,
+      "step": 10
+    },
+    {
+      "epoch": 0.00011343012704174228,
+      "eval_loss": 2.7065184116363525,
+      "eval_runtime": 873.6742,
+      "eval_samples_per_second": 42.487,
+      "eval_steps_per_second": 21.244,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -85,7 +144,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 240545515438080.0,
+  "total_flos": 481091030876160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null