Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ab8bd92a5457e6a83088d6ee86aea30cc7d3d313ed238f6a9556ae9af5d9523
+oid sha256:2bc0b329491f5eb9dbed0ead09397a09e3ccdc9798a3b5717e52dad7741cedf0
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5327897190b510245142ef3102eb541973d4181966402c0b68263bae8e7c2d1
+oid sha256:ca559821466b2085e09a6cb5c6e0233d8266e160c1ceb140316b6b5d32fcab1c
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b788255f43ed346a2f05cbdfc10299905ae58c13da185ea457f87ede82c55897
+oid sha256:77dc391d601077d8ff5172ee7e6fea08789829ee8cf6516f401f745801dc9fcd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43427779b8e6e83ef9780afcdea7472d2419de40e6f85cfedb90b60f89a2ff0f
+oid sha256:d2d754412c61116546142914503e7369d0cc35d3c380a07e5218f595d76b6d96
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.527027027027027,
+  "epoch": 2.7027027027027026,
   "eval_steps": 17,
-  "global_step": 187,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -537,6 +537,34 @@
       "eval_samples_per_second": 7.253,
       "eval_steps_per_second": 0.928,
       "step": 187
+    },
+    {
+      "epoch": 2.554054054054054,
+      "grad_norm": 0.5464707016944885,
+      "learning_rate": 8.247462563808817e-07,
+      "loss": 0.8524,
+      "step": 189
+    },
+    {
+      "epoch": 2.5945945945945947,
+      "grad_norm": 0.6008809804916382,
+      "learning_rate": 4.367965336512403e-07,
+      "loss": 0.8633,
+      "step": 192
+    },
+    {
+      "epoch": 2.635135135135135,
+      "grad_norm": 0.5401892066001892,
+      "learning_rate": 1.7077534966650766e-07,
+      "loss": 0.8186,
+      "step": 195
+    },
+    {
+      "epoch": 2.6756756756756754,
+      "grad_norm": 0.5296628475189209,
+      "learning_rate": 2.7337132953697554e-08,
+      "loss": 0.8183,
+      "step": 198
     }
   ],
   "logging_steps": 3,
@@ -551,12 +579,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.919508635693875e+17,
+  "total_flos": 5.262308567427318e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null