Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25e593ddca91674cab63db2b02dcb6e7650d6ff03ea178eb255f14755c064849
+oid sha256:a3a1b03a4c1e0b3db1fe4e581b9cdcb661d6d346c5c8a7ce12c2a3efa96036d4
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65fdc950ade5f3c6659245cfad1e839a496954a053232542383dd21817f56961
+oid sha256:dfffe10226d6d3e10d3bb0569eb65858d3e481a18c24f09074ed17a2e1d33c6a
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f9113e1eb32f6a8faa87851ebb8b8eebb4dee14e16a8f7564c198b2fb33406f
+oid sha256:3b3e9cb7d72ad5355aa5115b4e6ebee8f90c4be037c337d2c06e0f5bf6a33c02
 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": 0.0021315260906991677,
+  "epoch": 0.0027327257573066255,
   "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": 1.9174,
       "step": 35
+    },
+    {
+      "epoch": 0.0021861806058453004,
+      "grad_norm": 1.5157208442687988,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.8911,
+      "step": 40
+    },
+    {
+      "epoch": 0.0021861806058453004,
+      "eval_loss": 1.8702598810195923,
+      "eval_runtime": 303.5017,
+      "eval_samples_per_second": 25.384,
+      "eval_steps_per_second": 12.692,
+      "step": 40
+    },
+    {
+      "epoch": 0.002459453181575963,
+      "grad_norm": 1.9048547744750977,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.9542,
+      "step": 45
+    },
+    {
+      "epoch": 0.0027327257573066255,
+      "grad_norm": 1.4434877634048462,
+      "learning_rate": 0.0,
+      "loss": 1.9435,
+      "step": 50
+    },
+    {
+      "epoch": 0.0027327257573066255,
+      "eval_loss": 1.8613083362579346,
+      "eval_runtime": 306.1968,
+      "eval_samples_per_second": 25.16,
+      "eval_steps_per_second": 12.58,
+      "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": 694497677672448.0,
+  "total_flos": 890381638041600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null