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:fb095cd5a6f3cc93ad48167810333cda5aeac561277561d30b2a8135b9323f5a
+oid sha256:c1816ecb608ce59605f888f9ebbaf2da4d20ad64395b7cae943a04a5275b982a
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2701be192c094ab334416513542f276fe29e25f6845d9bc50427a9e05726f623
+oid sha256:0a4bd27f57720b31f591668c8017a52263f39b00228362a57efdced0a8633a12
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:808aa4126203bda27bd920cdb2164280ef875265d5f5729594b460163bd18bcd
+oid sha256:1c6bb5e0cc9fda198c3d9bbe49d0991fd184b8f2477df493060af0e41e52039e
 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": 0.012557606005111589,
+  "epoch": 0.01609949487834819,
   "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": 386.822,
       "eval_steps_per_second": 48.364,
       "step": 30
+    },
+    {
+      "epoch": 0.012879595902678554,
+      "grad_norm": 3.2545878887176514,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 177.2961,
+      "step": 40
+    },
+    {
+      "epoch": 0.012879595902678554,
+      "eval_loss": 11.077543258666992,
+      "eval_runtime": 53.4199,
+      "eval_samples_per_second": 391.671,
+      "eval_steps_per_second": 48.971,
+      "step": 40
+    },
+    {
+      "epoch": 0.01609949487834819,
+      "grad_norm": 3.210357904434204,
+      "learning_rate": 0.0,
+      "loss": 177.2341,
+      "step": 50
+    },
+    {
+      "epoch": 0.01609949487834819,
+      "eval_loss": 11.076793670654297,
+      "eval_runtime": 53.6808,
+      "eval_samples_per_second": 389.767,
+      "eval_steps_per_second": 48.732,
+      "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": 9876277297152.0,
+  "total_flos": 12615401078784.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null