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:b5daf99fbc67f78f3732de61d507c0219ef5f2b4cdab752164cb288231963850
+oid sha256:9f8232d71b04ea9fb82001782fda2a6809f9aa0e6de1d05283df2767a17579a6
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caffc911962f8e0eccda3755e5ed515835658eca874399b9d5cc64ab9f43e332
+oid sha256:0a125e64d7028e2fc972a34eb3bcb0a22c54863264cdaa04ccd3eccb551ac232
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac2fbbcfec39a266c55920bef9e4f13dec185fbafadb2891cdbdeaddfff2bb90
+oid sha256:6e39d3bd6aca35d9c2c4af115bc55fc6bc26ea5767dd3a367c3979f22ceabe3d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b489c13e2d776471e9a48162938854a24466ce6713df9c0fb59abd9a09fb226b
+oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2177858439201452,
+  "epoch": 0.29038112522686027,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 30.582,
       "eval_steps_per_second": 15.291,
       "step": 150
+    },
+    {
+      "epoch": 0.2323049001814882,
+      "grad_norm": 9.756109237670898,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 3.0355,
+      "step": 160
+    },
+    {
+      "epoch": 0.24682395644283123,
+      "grad_norm": 6.9620466232299805,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 1.9431,
+      "step": 170
+    },
+    {
+      "epoch": 0.2613430127041742,
+      "grad_norm": 7.356261730194092,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 1.8571,
+      "step": 180
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 6.641462326049805,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 2.0129,
+      "step": 190
+    },
+    {
+      "epoch": 0.29038112522686027,
+      "grad_norm": 7.481417655944824,
+      "learning_rate": 0.0,
+      "loss": 2.2513,
+      "step": 200
+    },
+    {
+      "epoch": 0.29038112522686027,
+      "eval_loss": 1.837255835533142,
+      "eval_runtime": 9.5016,
+      "eval_samples_per_second": 30.521,
+      "eval_steps_per_second": 15.261,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.77434637221888e+16,
+  "total_flos": 3.69912849629184e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null