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:d69fd011342df5b81942f3c0d4a35dfb028568b434ef1778afac49a6f0546045
+oid sha256:088420d9f7de655722f680fc6d3703c30d39a2372c5cb3daf82475d6cd5701a4
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f99845766e6998cae62b90dac0b64511c9d99a7934ca10978de349e4c25d6fa
+oid sha256:910522f35ad48cd7c7461c5bf4c8d7e8c2e1b1d515a66e8c56761da6058088f3
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48d41985628b63b1f03308534e42f5f4fade1dc9f1a7ca147144af3b829d1153
+oid sha256:52c1e8dd4ba9ace9e6fcca937683862f29cfd6bf4fb3642d8d44c9c9a4359dc1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0008318669012957927,
+  "epoch": 0.0010664960273022983,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 10.3764,
       "step": 35
+    },
+    {
+      "epoch": 0.0008531968218418387,
+      "grad_norm": 0.032152269035577774,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.3746,
+      "step": 40
+    },
+    {
+      "epoch": 0.0008531968218418387,
+      "eval_loss": 10.374410629272461,
+      "eval_runtime": 131.6182,
+      "eval_samples_per_second": 149.979,
+      "eval_steps_per_second": 74.99,
+      "step": 40
+    },
+    {
+      "epoch": 0.0009598464245720685,
+      "grad_norm": 0.028517883270978928,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.3742,
+      "step": 45
+    },
+    {
+      "epoch": 0.0010664960273022983,
+      "grad_norm": 0.02776319906115532,
+      "learning_rate": 0.0,
+      "loss": 10.3748,
+      "step": 50
+    },
+    {
+      "epoch": 0.0010664960273022983,
+      "eval_loss": 10.374374389648438,
+      "eval_runtime": 131.5939,
+      "eval_samples_per_second": 150.007,
+      "eval_steps_per_second": 75.003,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 982749020160.0,
+  "total_flos": 1267228999680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null