Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:368f6e128196ba20ff6f212e43a3cb9d4f631b4aaaea747c668b026bbf4c227e
+oid sha256:322aa42badd51bdbe0db04196641ac69a7dc43ee695c929779694133d9d76405
 size 31064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46fc85bc4faaad1e8d122cff7d5cf4a1a1ad3964bf64f5ab8326acdd107f9e83
+oid sha256:456d23e981e22ae1bd648c64a7b2ad638053dec464e5a1b79fa6df69e5c07cc6
 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": 0.08669074742984162,
+  "epoch": 0.11114198388441233,
   "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": 374.015,
       "eval_steps_per_second": 46.767,
       "step": 30
+    },
+    {
+      "epoch": 0.08891358710752988,
+      "grad_norm": 1.0100077390670776,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 165.981,
+      "step": 40
+    },
+    {
+      "epoch": 0.08891358710752988,
+      "eval_loss": 10.373748779296875,
+      "eval_runtime": 8.3115,
+      "eval_samples_per_second": 364.677,
+      "eval_steps_per_second": 45.6,
+      "step": 40
+    },
+    {
+      "epoch": 0.11114198388441233,
+      "grad_norm": 1.0934573411941528,
+      "learning_rate": 0.0,
+      "loss": 165.984,
+      "step": 50
+    },
+    {
+      "epoch": 0.11114198388441233,
+      "eval_loss": 10.373699188232422,
+      "eval_runtime": 8.0968,
+      "eval_samples_per_second": 374.344,
+      "eval_steps_per_second": 46.808,
+      "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": 32029689249792.0,
+  "total_flos": 41063704166400.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null