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:b8b37257c7931ffcea801219776a2b2aacd194025a11cca7aaf0295b0a5bc87f
+oid sha256:8a51f534522d70b88ea693b093a95e8f94fb71e28c5bdeb64817188137a16dcf
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:857aad6a72e1d1416a69a321d9afa84f9a503f9839f3ec6f2adc9dc908912a6c
+oid sha256:2165b7f79a5a78b01a8e036dc43ee3bf815a9ce16c69878322b9933595b188b8
 size 48260756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:241143b21cc924d430c26337fe782eca95bd4e2597092f90ee9241ee7d7a4b6c
+oid sha256:f59726f487b5ed348f0ab0883dc9cc88111fc1bbf85690706ad84a62e4544e63
 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": 0.014074341392998917,
+  "epoch": 0.01804402742692169,
   "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": 3.404,
       "step": 35
+    },
+    {
+      "epoch": 0.014435221941537351,
+      "grad_norm": 3.5075478553771973,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.4593,
+      "step": 40
+    },
+    {
+      "epoch": 0.014435221941537351,
+      "eval_loss": 0.8535332083702087,
+      "eval_runtime": 189.7319,
+      "eval_samples_per_second": 6.151,
+      "eval_steps_per_second": 3.078,
+      "step": 40
+    },
+    {
+      "epoch": 0.01623962468422952,
+      "grad_norm": 4.0576958656311035,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.2911,
+      "step": 45
+    },
+    {
+      "epoch": 0.01804402742692169,
+      "grad_norm": 3.0427911281585693,
+      "learning_rate": 0.0,
+      "loss": 3.4048,
+      "step": 50
+    },
+    {
+      "epoch": 0.01804402742692169,
+      "eval_loss": 0.8458905816078186,
+      "eval_runtime": 191.182,
+      "eval_samples_per_second": 6.104,
+      "eval_steps_per_second": 3.055,
+      "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": 2.225188179542016e+16,
+  "total_flos": 2.8528053583872e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null