Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79392552a34cf7abb8be5a94069449dc771d418b2bf6a1d03621592d43d3b5b7
+oid sha256:2adbd98d67bbf65c1661de3040741bdef0e4859769d8e4611b79070db6c8d3e9
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ecaa99ab53b6bbb2351d0fd49836c7aa22cc9ce538b9506c0a1916533f1d2b1
+oid sha256:fdcc28b02775aa4752b22f9a63ace0ed23b21425c634e9f61423e48c4c047021
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cefa6a2299162804c371eb63bafa7bf7943efdc7f99741c213760a8ea7e6c23e
+oid sha256:6761911e6819de9cd274861f1611d39f913abc881c13393fa15796081fb917ee
 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": 0.009608277900960829,
+  "epoch": 0.01231830500123183,
   "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": 0.7209,
       "step": 35
+    },
+    {
+      "epoch": 0.009854644000985464,
+      "grad_norm": 0.4157666862010956,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.6725,
+      "step": 40
+    },
+    {
+      "epoch": 0.009854644000985464,
+      "eval_loss": 0.6030021905899048,
+      "eval_runtime": 187.4873,
+      "eval_samples_per_second": 9.115,
+      "eval_steps_per_second": 4.56,
+      "step": 40
+    },
+    {
+      "epoch": 0.011086474501108648,
+      "grad_norm": 0.3123442232608795,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4155,
+      "step": 45
+    },
+    {
+      "epoch": 0.01231830500123183,
+      "grad_norm": 0.26258960366249084,
+      "learning_rate": 0.0,
+      "loss": 0.6081,
+      "step": 50
+    },
+    {
+      "epoch": 0.01231830500123183,
+      "eval_loss": 0.6012914180755615,
+      "eval_runtime": 186.2751,
+      "eval_samples_per_second": 9.175,
+      "eval_steps_per_second": 4.59,
+      "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": 1.2438319568781312e+16,
+  "total_flos": 1.5813774321647616e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null