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:ae3dfdf8c3ccb05d8cb8514811f3ee2176d88cd792b2e50791abd9d580ecf65b
+oid sha256:86641e4efbf4a90d25d325c1bafea4d3a4bd0f9f25adf568ac5d8dd9872c4cf9
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5203a94a71b1b6b59a0fbd5c729acbbc3289cd46c0a7bf4b33487fae3ba68924
+oid sha256:7f98133f27b939ef73fe438d4f35556e073811207227c914c7ffd8816da84e23
 size 48260756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbee6f84100698b0431eb48ba6934e5b0162eed4307a92814544f14034fe8b20
+oid sha256:a762665c33b077a903eef579f59c7c23cfce003261a8125c5bcb83768eab4ba7
 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": 0.015918367346938776,
+  "epoch": 0.02040816326530612,
   "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": 3.1349,
       "step": 35
+    },
+    {
+      "epoch": 0.0163265306122449,
+      "grad_norm": 2.757094621658325,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.8461,
+      "step": 40
+    },
+    {
+      "epoch": 0.0163265306122449,
+      "eval_loss": 0.7422359585762024,
+      "eval_runtime": 100.6434,
+      "eval_samples_per_second": 10.254,
+      "eval_steps_per_second": 5.127,
+      "step": 40
+    },
+    {
+      "epoch": 0.018367346938775512,
+      "grad_norm": 2.56603741645813,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.8422,
+      "step": 45
+    },
+    {
+      "epoch": 0.02040816326530612,
+      "grad_norm": 2.2543857097625732,
+      "learning_rate": 0.0,
+      "loss": 2.915,
+      "step": 50
+    },
+    {
+      "epoch": 0.02040816326530612,
+      "eval_loss": 0.7383472323417664,
+      "eval_runtime": 100.892,
+      "eval_samples_per_second": 10.229,
+      "eval_steps_per_second": 5.114,
+      "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": 1.397874625609728e+16,
+  "total_flos": 1.74734328201216e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null