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:f1b477bc3b50b59f83640a0aa7b22f7d921b912ab7f84d99e112d666f5ac4d3e
+oid sha256:18dc6060de8c128e117c5ce24d9e4da4ad79d23eba34dafe403d1ed7226cb8f8
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d117bccee93787ade0cf5dba2b05a731bc32f2153f0d4306e4e185bc4df4c311
+oid sha256:45cbb3b0323cae4e143143f477d8c2646acbf186987abd9e7c48a313fd419fde
 size 25152500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07826b0a1715771cf8401779e148b2e054e92f43284fa32f35d7a2caedc00d70
+oid sha256:4ae91c81bb1bda2bfa96330f9b07ba8a071665d1b8c7a5fc225f5ea9c74fbbc2
 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": 0.006594800253646164,
+  "epoch": 0.008454872120059184,
   "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": 0.4694,
       "step": 35
+    },
+    {
+      "epoch": 0.006763897696047347,
+      "grad_norm": 0.4488641023635864,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4668,
+      "step": 40
+    },
+    {
+      "epoch": 0.006763897696047347,
+      "eval_loss": 0.50519859790802,
+      "eval_runtime": 142.7619,
+      "eval_samples_per_second": 17.442,
+      "eval_steps_per_second": 8.721,
+      "step": 40
+    },
+    {
+      "epoch": 0.007609384908053266,
+      "grad_norm": 0.3778371512889862,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.5074,
+      "step": 45
+    },
+    {
+      "epoch": 0.008454872120059184,
+      "grad_norm": 0.33311334252357483,
+      "learning_rate": 0.0,
+      "loss": 0.4794,
+      "step": 50
+    },
+    {
+      "epoch": 0.008454872120059184,
+      "eval_loss": 0.5040430426597595,
+      "eval_runtime": 141.9754,
+      "eval_samples_per_second": 17.538,
+      "eval_steps_per_second": 8.769,
+      "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": 4417841340088320.0,
+  "total_flos": 5600570517749760.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null