Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:634978b10ee5e16b35200706fcc1d67f34cf68f5fab0bc35f882a5e65130a68f
+oid sha256:3f6624869a5ed5cd83a1a97ddbf40e239cc099285ac7632858698ae22ddecd67
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63ef4a40f95f6d9c4a2904214c087846d8b3ea10fa2cb9392b6e422e18014d81
+oid sha256:6e9b79ba23b276b2c6e4e348307900cd994ad9457c32dbfced2550e223669c6e
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f7f0699d26fb5c906f4d0b0d3679818c9f2542754956a4af3ee86c893a9a522
+oid sha256:4371c8ff7bcbd6ba3a72cb293b153e305d915775ae14f45a174ace763eeef792
 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": 0.04834211341803533,
+  "epoch": 0.061977068484660676,
   "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": 1.0238,
       "step": 35
+    },
+    {
+      "epoch": 0.04958165478772854,
+      "grad_norm": 1.3113014698028564,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.0754,
+      "step": 40
+    },
+    {
+      "epoch": 0.04958165478772854,
+      "eval_loss": 1.103080153465271,
+      "eval_runtime": 72.0279,
+      "eval_samples_per_second": 4.72,
+      "eval_steps_per_second": 2.36,
+      "step": 40
+    },
+    {
+      "epoch": 0.05577936163619461,
+      "grad_norm": 1.3435271978378296,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.9994,
+      "step": 45
+    },
+    {
+      "epoch": 0.061977068484660676,
+      "grad_norm": 1.486733317375183,
+      "learning_rate": 0.0,
+      "loss": 1.0947,
+      "step": 50
+    },
+    {
+      "epoch": 0.061977068484660676,
+      "eval_loss": 1.0898029804229736,
+      "eval_runtime": 72.0292,
+      "eval_samples_per_second": 4.72,
+      "eval_steps_per_second": 2.36,
+      "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": 1.252912722345984e+16,
+  "total_flos": 1.6061930309419008e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null