Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9eb0a489e550a277a2cdf24a31186a08d844159d52be874114c9514ae63cc945
+oid sha256:e02f0e95e81e17dd9b2c3a209b083534687fdfb642b3ced3bfe112f94a017910
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b5e911361919dc0e5ec48d5b9044264452c0a4772a271620f0abc58e0fda340
+oid sha256:4bb34872813f816cdecd9e2b4106c053f907bb4a510940cf142219de5202fa97
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46f095f52b97b7bccb542e54340cb700c4842060cb5eae55d2f7ac1450ce3c2c
+oid sha256:49b82873c526874b00fed9950656b9110d30784208c19733f95d310ed659280e
 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": 0.010407632263660017,
+  "epoch": 0.013343118286743613,
   "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": 1.2783,
       "step": 35
+    },
+    {
+      "epoch": 0.01067449462939489,
+      "grad_norm": 0.31695592403411865,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.2705,
+      "step": 40
+    },
+    {
+      "epoch": 0.01067449462939489,
+      "eval_loss": 1.3098112344741821,
+      "eval_runtime": 52.1649,
+      "eval_samples_per_second": 30.25,
+      "eval_steps_per_second": 15.125,
+      "step": 40
+    },
+    {
+      "epoch": 0.012008806458069251,
+      "grad_norm": 0.33602485060691833,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.2586,
+      "step": 45
+    },
+    {
+      "epoch": 0.013343118286743613,
+      "grad_norm": 0.3920798599720001,
+      "learning_rate": 0.0,
+      "loss": 1.3313,
+      "step": 50
+    },
+    {
+      "epoch": 0.013343118286743613,
+      "eval_loss": 1.3084073066711426,
+      "eval_runtime": 52.5608,
+      "eval_samples_per_second": 30.022,
+      "eval_steps_per_second": 15.011,
+      "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": 1374881883095040.0,
+  "total_flos": 1752175051014144.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null