Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bebc6f61c7de98206559d6c0c94746fec850053ae01604695dbc28ec389394f
+oid sha256:eef5ca795f3fd55e32817624fd956b1a7b878cae38211e6d8ce2df7c8ee9d51b
 size 1134088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4af5ccff3dc5e99701589efd0f6250525d8f198952310ba225cc00a5120b5b21
+oid sha256:4c439aca9013529964556cce48732545f4e846d65438bba067f36949d39c6687
 size 608186

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8722eae63c381f92c6d94d24ace69d7fcf532d72874bbfed0a1d65ec7ba4cff9
+oid sha256:3ab98faee1fc7a78f5149310a3a4857ece162a237f55b0aa346dbdad5d5a9990
 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": 0.5596412556053811,
+  "epoch": 0.7174887892376681,
   "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": 324.296,
       "eval_steps_per_second": 40.71,
       "step": 30
+    },
+    {
+      "epoch": 0.5739910313901345,
+      "grad_norm": 1.1063145399093628,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.6222,
+      "step": 40
+    },
+    {
+      "epoch": 0.5739910313901345,
+      "eval_loss": 1.585193395614624,
+      "eval_runtime": 1.4516,
+      "eval_samples_per_second": 323.771,
+      "eval_steps_per_second": 40.644,
+      "step": 40
+    },
+    {
+      "epoch": 0.7174887892376681,
+      "grad_norm": 1.091284155845642,
+      "learning_rate": 0.0,
+      "loss": 1.5933,
+      "step": 50
+    },
+    {
+      "epoch": 0.7174887892376681,
+      "eval_loss": 1.5734552145004272,
+      "eval_runtime": 1.401,
+      "eval_samples_per_second": 335.473,
+      "eval_steps_per_second": 42.113,
+      "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": 1294151165411328.0,
+  "total_flos": 1655309630177280.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null