Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ccad1dbf3a728d2ccc8f465f1589f429ec2b636d0027a7ce40b3946b1a8ae4f
+oid sha256:b5caaf07a3016f4f11eb6db2ed12340d14a004dd39a437a4d480d070be22b8d4
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0b5618261d1197bd7fc4b71125473863cbb3ba79f1b86f91187a06678ae736f
+oid sha256:341940c7ea6c09c56af84ef21af66ea0b84651a0e12c63454777a98f4f4b793d
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02a756382462073b0de6176b3e6342526a2c292eede77ec231bbca5b19bf17f2
+oid sha256:8136472075b4f3eb1fd5265173f2f3d5e826915e740384c04f7ac8b2b1e9ae0c
 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": 0.0063399170933918555,
+  "epoch": 0.008128098837681867,
   "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": 1.6408,
       "step": 35
+    },
+    {
+      "epoch": 0.006502479070145493,
+      "grad_norm": 0.21557150781154633,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.5326,
+      "step": 40
+    },
+    {
+      "epoch": 0.006502479070145493,
+      "eval_loss": 1.6094844341278076,
+      "eval_runtime": 75.0504,
+      "eval_samples_per_second": 34.523,
+      "eval_steps_per_second": 17.268,
+      "step": 40
+    },
+    {
+      "epoch": 0.0073152889539136795,
+      "grad_norm": 0.25057998299598694,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.6054,
+      "step": 45
+    },
+    {
+      "epoch": 0.008128098837681867,
+      "grad_norm": 0.2409868985414505,
+      "learning_rate": 0.0,
+      "loss": 1.5964,
+      "step": 50
+    },
+    {
+      "epoch": 0.008128098837681867,
+      "eval_loss": 1.6076915264129639,
+      "eval_runtime": 74.5511,
+      "eval_samples_per_second": 34.755,
+      "eval_steps_per_second": 17.384,
+      "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": 1246985893969920.0,
+  "total_flos": 1624279061889024.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null