Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a4b1b9f92f2c3f801f4027f95d4c80de298a5b2d3de9cb507f8ca53cd4a14b9
+oid sha256:5b3322447b5a0a1477bb336f2f5190ab31f39d4fc94075602d6444751e2a40f0
 size 25192496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33d7c08a12c11dc5458f94a3d6b41ab1d6f9cc1aedc689cdcee6f067d4e7d658
+oid sha256:9711b4f17575fc441de48135815b12847a512f52abc210fa643bcdf399b560b1
 size 13005178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c7830ee97fa51bd1d743895da89276028ce6a6b88f43103020645687fd0ef70
+oid sha256:feb4313e9c2200d08445473756443c5eddd90c375e2aa78ddce9ac0bf4f49945
 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": 0.0006472142818618197,
+  "epoch": 0.0008297618998228458,
   "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": 0.488,
       "step": 35
+    },
+    {
+      "epoch": 0.0006638095198582767,
+      "grad_norm": 6.433207035064697,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4755,
+      "step": 40
+    },
+    {
+      "epoch": 0.0006638095198582767,
+      "eval_loss": 0.09560307115316391,
+      "eval_runtime": 690.6129,
+      "eval_samples_per_second": 36.738,
+      "eval_steps_per_second": 18.369,
+      "step": 40
+    },
+    {
+      "epoch": 0.0007467857098405612,
+      "grad_norm": 6.775955677032471,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4671,
+      "step": 45
+    },
+    {
+      "epoch": 0.0008297618998228458,
+      "grad_norm": 2.749504327774048,
+      "learning_rate": 0.0,
+      "loss": 0.3641,
+      "step": 50
+    },
+    {
+      "epoch": 0.0008297618998228458,
+      "eval_loss": 0.0893232449889183,
+      "eval_runtime": 689.7774,
+      "eval_samples_per_second": 36.783,
+      "eval_steps_per_second": 18.391,
+      "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": 1179360857948160.0,
+  "total_flos": 1507790463959040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null