Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4df0da4a36a2d7521da494365f4db0c075df0c4aab724d60e31cbd414616c93a
+oid sha256:7027890e0bcf57812b55398e5aa4336927c93a932ba5282fc9a931b2b1783ae0
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d759edd606e0b2bda33de8b2fb3a1b405d95950bed21728bcfa12260b2138fd
+oid sha256:6b48dbb7bbb0dbe27b305601962b96317eb6c85a59d1d22215b0dd497e139348
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03b925f41b93ae978efc363ec176c67bd523156ae2461120bbde365bcfec0fe9
+oid sha256:41dd8f1c6cda4d03a8c80cccd9bb3b4abfaf15090577dd9d9134cf8078750727
 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": 0.0012827048627670247,
+  "epoch": 0.0016444934138038778,
   "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": 1.6267,
       "step": 35
+    },
+    {
+      "epoch": 0.0013155947310431021,
+      "grad_norm": 4.118277549743652,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.9963,
+      "step": 40
+    },
+    {
+      "epoch": 0.0013155947310431021,
+      "eval_loss": 1.7459853887557983,
+      "eval_runtime": 2010.8862,
+      "eval_samples_per_second": 6.366,
+      "eval_steps_per_second": 3.183,
+      "step": 40
+    },
+    {
+      "epoch": 0.00148004407242349,
+      "grad_norm": 3.1414225101470947,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.8742,
+      "step": 45
+    },
+    {
+      "epoch": 0.0016444934138038778,
+      "grad_norm": 4.184607028961182,
+      "learning_rate": 0.0,
+      "loss": 1.6942,
+      "step": 50
+    },
+    {
+      "epoch": 0.0016444934138038778,
+      "eval_loss": 1.7354694604873657,
+      "eval_runtime": 2007.8581,
+      "eval_samples_per_second": 6.376,
+      "eval_steps_per_second": 3.188,
+      "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": 1.490651304689664e+16,
+  "total_flos": 1.9110914162688e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null