Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e65af51061ddcb0153792fd0c3ff42952d4471ca2f8231231f4cd4b97c6f290
+oid sha256:92970767440e650f9ecee75279d927fee05b4b45f8aae6410e696a55d4f8c7b9
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d1ad122b951e7a3de69ea50c1390e4ccbc253440e33a2c15959eb7426fcfec6
+oid sha256:c95adac7141828a1c880eccdb190471dd3e76b3bcac547424eb8398884a3299a
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bfb8b553a99e1506bcfc89287f05eb8ba57802768f914f650c4c584e5bc1b0e
+oid sha256:e3317c9cf685312b14428bab5fd7de4dd3669dfe2faff83579404ef6f7eee09f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7131428571428572,
+  "epoch": 0.9142857142857143,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,36 @@
       "eval_samples_per_second": 16.527,
       "eval_steps_per_second": 2.105,
       "step": 30
+    },
+    {
+      "epoch": 0.7314285714285714,
+      "grad_norm": 0.07180826365947723,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.501,
+      "step": 40
+    },
+    {
+      "epoch": 0.7314285714285714,
+      "eval_loss": 1.4780809879302979,
+      "eval_runtime": 22.2666,
+      "eval_samples_per_second": 16.572,
+      "eval_steps_per_second": 2.111,
+      "step": 40
+    },
+    {
+      "epoch": 0.9142857142857143,
+      "grad_norm": 0.08199798315763474,
+      "learning_rate": 0.0,
+      "loss": 1.4879,
+      "step": 50
+    },
+    {
+      "epoch": 0.9142857142857143,
+      "eval_loss": 1.4767606258392334,
+      "eval_runtime": 22.3248,
+      "eval_samples_per_second": 16.529,
+      "eval_steps_per_second": 2.105,
+      "step": 50
     }
   ],
   "logging_steps": 10,
@@ -74,12 +104,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.0234207339020288e+17,
+  "total_flos": 1.31207786397696e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null