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:fe9fe7bb41e9d5cad0e143416092fad193893b3cba23937f98bbc2ddc7283915
+oid sha256:88987cbb817a7e58ccf0bed064bb2b77123ab35b728c801680288cac6c0a3d9d
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f07b904023671fa683349126973a33a7df837ee7fc1b8f4f6b6e93a157765700
+oid sha256:d646ac6fd71e12c0a70e5f5d4bd3341343fe8a961099254fd12a8fc187071e70
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dd60e9ba809120cc78feb8bd27109edcdf93018d99882fdeecb2257ff3c3de7
+oid sha256:b56d11a87a079cc6eb722f7d6d9ce7ea6e5c6de036055dca171cb4062e17b7a1
 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": 0.0003288634605290064,
+  "epoch": 0.0004216198211910338,
   "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": 3.1792,
       "step": 35
+    },
+    {
+      "epoch": 0.00033729585695282705,
+      "grad_norm": 15.089554786682129,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.8384,
+      "step": 40
+    },
+    {
+      "epoch": 0.00033729585695282705,
+      "eval_loss": 0.7566215395927429,
+      "eval_runtime": 4498.0748,
+      "eval_samples_per_second": 11.101,
+      "eval_steps_per_second": 5.551,
+      "step": 40
+    },
+    {
+      "epoch": 0.00037945783907193046,
+      "grad_norm": 4.627601146697998,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.4376,
+      "step": 45
+    },
+    {
+      "epoch": 0.0004216198211910338,
+      "grad_norm": 3.869359254837036,
+      "learning_rate": 0.0,
+      "loss": 3.0871,
+      "step": 50
+    },
+    {
+      "epoch": 0.0004216198211910338,
+      "eval_loss": 0.755088746547699,
+      "eval_runtime": 4485.5267,
+      "eval_samples_per_second": 11.132,
+      "eval_steps_per_second": 5.566,
+      "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": 1.052065728036864e+16,
+  "total_flos": 1.337000196046848e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null