Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72b394f35445d3e33d98530b4b2fb74e8b484927b0acc3d9311896b2f28c7f7d
+oid sha256:85f3d48f15219755c4f112a18724eaa1fd20d91d8383050175a66fd4653f33cc
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5c723abbd0d5ee2b9d324bbc73f57cc1e5741bad7401b75bfc904edb8e1afe3
+oid sha256:e3dbf3c98cc81f7c226d702159b9c62bdcec235152120836d5f92795a7f4a823
 size 48260756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c98afc215468fe49340fcc1e8d06e1a0e4426237e618a149fa37ce1204c3ce0e
+oid sha256:be8a0f455b08eb43e4bbf87a595cb3be3a091262695326052d0a7f317aaadfe1
 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": 0.022598870056497175,
+  "epoch": 0.02897291032884253,
   "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": 3.9499,
       "step": 35
+    },
+    {
+      "epoch": 0.023178328263074026,
+      "grad_norm": 5.339483737945557,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.6152,
+      "step": 40
+    },
+    {
+      "epoch": 0.023178328263074026,
+      "eval_loss": 0.8557589054107666,
+      "eval_runtime": 101.3172,
+      "eval_samples_per_second": 7.175,
+      "eval_steps_per_second": 3.593,
+      "step": 40
+    },
+    {
+      "epoch": 0.02607561929595828,
+      "grad_norm": 4.450899124145508,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.743,
+      "step": 45
+    },
+    {
+      "epoch": 0.02897291032884253,
+      "grad_norm": 4.0835089683532715,
+      "learning_rate": 0.0,
+      "loss": 3.4918,
+      "step": 50
+    },
+    {
+      "epoch": 0.02897291032884253,
+      "eval_loss": 0.8489733934402466,
+      "eval_runtime": 101.3195,
+      "eval_samples_per_second": 7.175,
+      "eval_steps_per_second": 3.593,
+      "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": 1.112594089771008e+16,
+  "total_flos": 1.4264026791936e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null