Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f6786f47489588d7decb18e83caf9112b99a8fd4777af76392b1904c673b381
+oid sha256:8a26d2e8bceaad0530c38ffcf93b5e9a0f73a621870a788a8ba7840de826e568
 size 59933632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7ffae07139e3ea7fcd2bf21a89a3dcaed406a7e54d59e341fd8877bd3369939
+oid sha256:1f7e71482955dc8c5393aeba7dc2d936737f43fc153591383ce57b53d6efd591
 size 31822948

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a6c39d7c7b18386cb523125c3bb746ee8817c181da22d6aa933af9f7ec79f7a
+oid sha256:8de9aa3fb4c89c2e60a875efc9760e03e9fbfed4ec35e0b8fd54f353310a8414
 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": 0.017836725360164646,
+  "epoch": 0.0228675966155957,
   "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": 0.5406,
       "step": 35
+    },
+    {
+      "epoch": 0.01829407729247656,
+      "grad_norm": 0.6103530526161194,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5117,
+      "step": 40
+    },
+    {
+      "epoch": 0.01829407729247656,
+      "eval_loss": 0.5318560004234314,
+      "eval_runtime": 45.7702,
+      "eval_samples_per_second": 20.122,
+      "eval_steps_per_second": 10.072,
+      "step": 40
+    },
+    {
+      "epoch": 0.02058083695403613,
+      "grad_norm": 1.031596064567566,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.5938,
+      "step": 45
+    },
+    {
+      "epoch": 0.0228675966155957,
+      "grad_norm": 1.2413913011550903,
+      "learning_rate": 0.0,
+      "loss": 0.5196,
+      "step": 50
+    },
+    {
+      "epoch": 0.0228675966155957,
+      "eval_loss": 0.5278226137161255,
+      "eval_runtime": 45.4219,
+      "eval_samples_per_second": 20.277,
+      "eval_steps_per_second": 10.149,
+      "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": 2793847042080768.0,
+  "total_flos": 3616575005392896.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null