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:a7587c1a455bc9aa8608df00f712599d1c62d4e0a3d58a506c75b701bd59831f
+oid sha256:80b02b23f542cccc4d44529927bab264768eaae45cf0387cf8499c17be73fcde
 size 31064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a61238217d3529fb88d6810e32888f8ee1a3a3bd443fd32ee5536bebfd0c6e3d
+oid sha256:2c834b5e320be745581c7de77cd2cb59d93a5d07579b7a6945d662a99806b5c3
 size 71718

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bebbe731bd9094c7ae8f274487d73bb48b05017603343298a02474cb28c07b94
+oid sha256:fdedc6314c9f75a198e58bac1038c3adc8fc2a5f73e82a6a71a371fdac27e199
 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": 0.020148530836293185,
+  "epoch": 0.02583144979011947,
   "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": 688.962,
       "eval_steps_per_second": 86.12,
       "step": 30
+    },
+    {
+      "epoch": 0.020665159832095575,
+      "grad_norm": 5.858962059020996,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 165.0856,
+      "step": 40
+    },
+    {
+      "epoch": 0.020665159832095575,
+      "eval_loss": 10.315924644470215,
+      "eval_runtime": 18.8868,
+      "eval_samples_per_second": 690.43,
+      "eval_steps_per_second": 86.304,
+      "step": 40
+    },
+    {
+      "epoch": 0.02583144979011947,
+      "grad_norm": 5.817805290222168,
+      "learning_rate": 0.0,
+      "loss": 165.0616,
+      "step": 50
+    },
+    {
+      "epoch": 0.02583144979011947,
+      "eval_loss": 10.315557479858398,
+      "eval_runtime": 18.7652,
+      "eval_samples_per_second": 694.902,
+      "eval_steps_per_second": 86.863,
+      "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": 16014844624896.0,
+  "total_flos": 20531852083200.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null