Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d06933c6870b994f52d8d7797843622d5920abc1973f39264e0951139ea9c84
+oid sha256:287163bd46659117c6e985625f546317fce3d93ef10f4679b17d3b61d95db6ed
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a378d36b5b13d9f1a259b4e15aecf95a4443af300f838d4263d5aef9d15dc55
+oid sha256:9f40cb70b4a3a521264f420c676a85b6c03a98ecfa678cf57b8d69da93246788
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78e02c0328f398f788338849956de254efada23c555cc02b42767039b16f4772
+oid sha256:aecc225c29f796cd114bc0047e277b88c065033821bb23bad4b4a6fd5b14da34
 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": 0.2421420256111758,
+  "epoch": 0.3104384943733023,
   "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": 69.913,
       "eval_steps_per_second": 8.763,
       "step": 30
+    },
+    {
+      "epoch": 0.24835079549864184,
+      "grad_norm": 0.47105929255485535,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.8699,
+      "step": 40
+    },
+    {
+      "epoch": 0.24835079549864184,
+      "eval_loss": 0.8705499172210693,
+      "eval_runtime": 15.5382,
+      "eval_samples_per_second": 69.828,
+      "eval_steps_per_second": 8.753,
+      "step": 40
+    },
+    {
+      "epoch": 0.3104384943733023,
+      "grad_norm": 0.47211363911628723,
+      "learning_rate": 0.0,
+      "loss": 0.8423,
+      "step": 50
+    },
+    {
+      "epoch": 0.3104384943733023,
+      "eval_loss": 0.867393970489502,
+      "eval_runtime": 15.5747,
+      "eval_samples_per_second": 69.664,
+      "eval_steps_per_second": 8.732,
+      "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": 1.5010040163336192e+16,
+  "total_flos": 1.92436412350464e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null