Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ef69f1fdab177168f116f4694d8bba73cbce1d7ee89a12090f26e85b3fc4215
+oid sha256:7e284692f0af614b561c2959cde542ba1636dbb9708d470d8d929540fc48acb3
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72870d5bb19cd3dfb1cba982af5d7aece8b9a837ed25f7a19da0b827e2398806
+oid sha256:4c851e7e06488d3b0a5b2f4daecde9a3ab0c55c6a933ef0b0a2e8802e533a6f7
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6f5db306e3a33142fbaf040789df3b7d4c6e0c9a6325a27bf7b7e7eac9c1504
+oid sha256:91d5ee23be97c1c2e19f360a5bf6f6b0943e757dd12970b1f423cc8e91d25092
 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": 0.0031641076607914326,
+  "epoch": 0.004056548283065939,
   "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": 0.3143,
       "step": 35
+    },
+    {
+      "epoch": 0.0032452386264527513,
+      "grad_norm": 2.2494866847991943,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.3821,
+      "step": 40
+    },
+    {
+      "epoch": 0.0032452386264527513,
+      "eval_loss": 0.3613074719905853,
+      "eval_runtime": 160.6531,
+      "eval_samples_per_second": 32.306,
+      "eval_steps_per_second": 16.153,
+      "step": 40
+    },
+    {
+      "epoch": 0.0036508934547593453,
+      "grad_norm": 2.456997871398926,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.391,
+      "step": 45
+    },
+    {
+      "epoch": 0.004056548283065939,
+      "grad_norm": 2.461636781692505,
+      "learning_rate": 0.0,
+      "loss": 0.3543,
+      "step": 50
+    },
+    {
+      "epoch": 0.004056548283065939,
+      "eval_loss": 0.3574821352958679,
+      "eval_runtime": 160.3167,
+      "eval_samples_per_second": 32.373,
+      "eval_steps_per_second": 16.187,
+      "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": 2080280621875200.0,
+  "total_flos": 2655417029099520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null