Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b891d1a88a6d8538c81d0ae54206736d1ca32e83773de7e2952d26860e39786
+oid sha256:4885e3e7f9d28a44eb297b44b29ad483bbb4d36156e7091cbe6877ab447915e7
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88ddcda6b60af6c1f9fe624d59206dbb32e0a5080158f1330c3d2313cbfc149c
+oid sha256:a0bc7bd56436db90e9609f3bcf8154581ceaedf0673a275da42bdfb08bdc603e
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:947ece98332d99683d37bd2fee1ac65ac73ce29b75c2120387902d8224d62275
+oid sha256:771a2b7acf09f9321d9c22119214bb5c3c4692ad9077faf996561805c2ddf873
 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": 0.009569377990430622,
+  "epoch": 0.0122684333210649,
   "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": 44.0055,
       "step": 35
+    },
+    {
+      "epoch": 0.00981474665685192,
+      "grad_norm": 2.319875478744507,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 44.0187,
+      "step": 40
+    },
+    {
+      "epoch": 0.00981474665685192,
+      "eval_loss": 10.99793529510498,
+      "eval_runtime": 11.8249,
+      "eval_samples_per_second": 145.117,
+      "eval_steps_per_second": 72.559,
+      "step": 40
+    },
+    {
+      "epoch": 0.01104158998895841,
+      "grad_norm": 2.260441780090332,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 43.9902,
+      "step": 45
+    },
+    {
+      "epoch": 0.0122684333210649,
+      "grad_norm": 2.374315023422241,
+      "learning_rate": 0.0,
+      "loss": 43.9643,
+      "step": 50
+    },
+    {
+      "epoch": 0.0122684333210649,
+      "eval_loss": 10.994427680969238,
+      "eval_runtime": 11.7619,
+      "eval_samples_per_second": 145.895,
+      "eval_steps_per_second": 72.948,
+      "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": 684780945408.0,
+  "total_flos": 882499387392.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null