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:d4d46302f762904ba5583473e43963a5dbd6a7cddc5e750bfef0d5e268e91cea
+oid sha256:f24cff8d6d88a2fdd17e47a5843628fc16072601cab174e454379fb57a41c205
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1877d8fb8d7a50ea821ee44f3a684af78bdae56bef1ee882b499090920c24825
+oid sha256:f10ea1411132619d2c3013952e8cd2067bb02d7be96c7e2294b446c3492178e6
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d52990953d1b8a81a00b7cecfd9c211b1ca6db6b881889b76e3a32894320cdb
+oid sha256:529c9e51cf346c9538de8a198d0e350de38ac30f5061dd3c6b0f0716ac464501
 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": 0.1342,
       "step": 35
+    },
+    {
+      "epoch": 0.006763897696047347,
+      "grad_norm": 1.667202115058899,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.1783,
+      "step": 40
+    },
+    {
+      "epoch": 0.006763897696047347,
+      "eval_loss": 0.1387166827917099,
+      "eval_runtime": 145.4243,
+      "eval_samples_per_second": 17.122,
+      "eval_steps_per_second": 8.561,
+      "step": 40
+    },
+    {
+      "epoch": 0.007609384908053266,
+      "grad_norm": 0.30066943168640137,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1361,
+      "step": 45
+    },
+    {
+      "epoch": 0.008454872120059184,
+      "grad_norm": 2.7212069034576416,
+      "learning_rate": 0.0,
+      "loss": 0.1554,
+      "step": 50
+    },
+    {
+      "epoch": 0.008454872120059184,
+      "eval_loss": 0.14785736799240112,
+      "eval_runtime": 145.2718,
+      "eval_samples_per_second": 17.14,
+      "eval_steps_per_second": 8.57,
+      "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": 6352059230060544.0,
+  "total_flos": 8143665679564800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null