Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ea613c1bd30b1668db6c9a1bb4149ba77b5fc14e0b229e4bcf2c9cdefb10a0a
+oid sha256:42c522b8f0989f317efdfc644d6c0bfad55dd892acfa3dd90eb6fb79e559640f
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac620220980d7bc2d0f8d1c45a534f9625edf18437813879b8aac6d370d43f91
+oid sha256:4ba3c0d4db88364aaa698a9d3bdb2bba5f6d5992f7efd1d26a9d1487b87efa74
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60197ddd2b9e7ee46919c36404e76c5aca074008f3439670b71d1d51cb8b8db7
+oid sha256:d9a8129b15783fce809c3d71373b8daf1f14f9ed4a08489d93cdef55470a4373
 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": 0.0009212290139896894,
+  "epoch": 0.0011810628384483195,
   "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": 1.9827,
       "step": 35
+    },
+    {
+      "epoch": 0.0009448502707586557,
+      "grad_norm": 1.4972468614578247,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.8617,
+      "step": 40
+    },
+    {
+      "epoch": 0.0009448502707586557,
+      "eval_loss": 1.9017900228500366,
+      "eval_runtime": 1093.2305,
+      "eval_samples_per_second": 16.306,
+      "eval_steps_per_second": 8.153,
+      "step": 40
+    },
+    {
+      "epoch": 0.0010629565546034876,
+      "grad_norm": 1.6116687059402466,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.7783,
+      "step": 45
+    },
+    {
+      "epoch": 0.0011810628384483195,
+      "grad_norm": 1.700925350189209,
+      "learning_rate": 0.0,
+      "loss": 1.8563,
+      "step": 50
+    },
+    {
+      "epoch": 0.0011810628384483195,
+      "eval_loss": 1.8956127166748047,
+      "eval_runtime": 1093.018,
+      "eval_samples_per_second": 16.309,
+      "eval_steps_per_second": 8.154,
+      "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": 6109362554142720.0,
+  "total_flos": 7810963533987840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null