Training in progress, step 243, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e158d8231abfabf27daa95080c28c4a83772bf8ff4d41f89a1e66a8411f16beb
+oid sha256:f39d0de6c5dccbad833e1bf2991b7b006e353142a384efb5d377e46829b41d24
 size 17462432

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:569973a3e5a124cf6a66b859203c4dcdbd9b69a89cb9dfbeada6e54e963f9f4c
+oid sha256:2101d8d980d182b57e7a1a5326639527263ad055a41ab95174c1d6b2b235f035
 size 9114746

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:906a241dcf8546970aea8f02380e1c2df5213df8101d9bcbcf9de8ff3a87159b
+oid sha256:9561e34a5e765795c4e0009b56662d9625fe09748c6f85dc859b8c7da98b3843
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f1b8c119ed37337ec3dea8f96e3af3bb3e6556229f6c151fabee0c7861a44e6
+oid sha256:8adc451d2cc8569c2d20428550a3d71e682be30e73eb1b9d4837c45d2e178726
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.5491589903831482,
   "best_model_checkpoint": "checkpoints/checkpoint-200",
-  "epoch": 2.443076923076923,
+  "epoch": 2.9723076923076923,
   "eval_steps": 100,
-  "global_step": 200,
+  "global_step": 243,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,38 @@
       "gpu_memory": 4887.19873046875,
       "learning_rate": 2.5137453979444762e-05,
       "step": 200
+    },
+    {
+      "epoch": 2.566153846153846,
+      "gpu_memory": 4887.19873046875,
+      "grad_norm": 0.4115428924560547,
+      "learning_rate": 1.4981922608692365e-05,
+      "loss": 0.7901,
+      "step": 210
+    },
+    {
+      "epoch": 2.689230769230769,
+      "gpu_memory": 4887.19873046875,
+      "grad_norm": 0.404224157333374,
+      "learning_rate": 7.34152255572697e-06,
+      "loss": 0.7795,
+      "step": 220
+    },
+    {
+      "epoch": 2.812307692307692,
+      "gpu_memory": 4887.19873046875,
+      "grad_norm": 0.382841020822525,
+      "learning_rate": 2.3585800173432813e-06,
+      "loss": 0.7933,
+      "step": 230
+    },
+    {
+      "epoch": 2.9353846153846153,
+      "gpu_memory": 4887.19873046875,
+      "grad_norm": 0.4079365134239197,
+      "learning_rate": 1.259177849420312e-07,
+      "loss": 0.828,
+      "step": 240
     }
   ],
   "logging_steps": 10,
@@ -201,12 +233,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.020807021474611e+16,
+  "total_flos": 3.675188391365837e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null