Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9618ce579a177860c0aed5a10bd56b0806952b54ac8809316f1e2179160d2446
+oid sha256:0741e4ee01070f98d6c2ee589dbcac7b76201b76bab653eb5cda49fce61c4b91
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6f6043dfc79334746158c1ed7ad454a9d8dd32aa1482649f396319e1d6e6447
+oid sha256:ba4a9547c30761f6436e07261b4fc47ea8108ddf21ff7b0cbe23780509c62cb4
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80a70d314aded6696f28475aa46cda23680487051fdbe5362785d282bb2a1f3c
+oid sha256:ca89fdf7eb52eabc419a7130285a92b126f2937b0b06ee55c501a2dc14427ea4
 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": 0.2631578947368421,
+  "epoch": 0.3508771929824561,
   "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": 20.649,
       "eval_steps_per_second": 10.324,
       "step": 150
+    },
+    {
+      "epoch": 0.2807017543859649,
+      "grad_norm": 0.3036251664161682,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 0.0091,
+      "step": 160
+    },
+    {
+      "epoch": 0.2982456140350877,
+      "grad_norm": 0.2512568533420563,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 0.0092,
+      "step": 170
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 0.2012607902288437,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 0.0058,
+      "step": 180
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.46869468688964844,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 0.0063,
+      "step": 190
+    },
+    {
+      "epoch": 0.3508771929824561,
+      "grad_norm": 0.19013503193855286,
+      "learning_rate": 0.0,
+      "loss": 0.0031,
+      "step": 200
+    },
+    {
+      "epoch": 0.3508771929824561,
+      "eval_loss": 0.00592783885076642,
+      "eval_runtime": 11.6387,
+      "eval_samples_per_second": 20.621,
+      "eval_steps_per_second": 10.31,
+      "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": 3.07859042598912e+16,
+  "total_flos": 4.10478723465216e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null