Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:529c12e26cc5efe3e37fa8df3a9a4e7e8e45e1d30214e35de25d4948b8b30eff
+oid sha256:3fcce26e14b7795ec9a5621547286c8b09483766218cf7c31ee71dd74d692290
 size 66103768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0c0197e1ddc67703ec28b88c5aac3d53db9218c9618eae91731c58e922e48b8
+oid sha256:b317d39ae37e91179f92e983ca2a3ffb8a17c4b5891067a9b6a705f8488aa759
 size 33939412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc20dd1b8cfa41338db80f6d8ccb203d18d54fafe37ac263ffd04e3fd0d5ac82
+oid sha256:9bf80edb43fcc9aa4f5822b539948f7112e31e719e9c8ade0366343fc117f571
 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": 0.03351235230934479,
+  "epoch": 0.04296455424274973,
   "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": 3.6811,
       "step": 35
+    },
+    {
+      "epoch": 0.034371643394199784,
+      "grad_norm": 2.935652256011963,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.3253,
+      "step": 40
+    },
+    {
+      "epoch": 0.034371643394199784,
+      "eval_loss": 0.8391368985176086,
+      "eval_runtime": 66.1741,
+      "eval_samples_per_second": 7.405,
+      "eval_steps_per_second": 3.702,
+      "step": 40
+    },
+    {
+      "epoch": 0.03866809881847476,
+      "grad_norm": 2.1004343032836914,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.1562,
+      "step": 45
+    },
+    {
+      "epoch": 0.04296455424274973,
+      "grad_norm": 4.1379780769348145,
+      "learning_rate": 0.0,
+      "loss": 3.3475,
+      "step": 50
+    },
+    {
+      "epoch": 0.04296455424274973,
+      "eval_loss": 0.8348293900489807,
+      "eval_runtime": 66.1244,
+      "eval_samples_per_second": 7.41,
+      "eval_steps_per_second": 3.705,
+      "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": 1.0118742579566592e+16,
+  "total_flos": 1.3071542905276416e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null