Training in progress, step 1120, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a7f05f8343cd00e937878886b5c05bcfa4c92bcc117e4700c1624e6fb6186b3
+oid sha256:1953745bb1e4d1a52adab1da9a3ffac023ee80f911184724df85c70b02bb3ff3
 size 218138576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da243c69c28e5cb1d59bde1fe2d142c5094b57d6fbdadac0ca6f57be21b6f017
+oid sha256:56fadcca18d07e6b0dcf0ad8b18bf4a204fdf4ad948163efcee300bb5e8db634
 size 436423418

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05955f1a63690c3140a697c1676af18f4c452997a7f110c4100413a44d761508
+oid sha256:5612005e57bd15a47b619f3ec26c56a8dcaa1d6eadef7d23851ee0274186a06f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58b2bec7c365a791aa5c363675631695f865a0b61ed6a602f13b80529ecf344b
+oid sha256:e05a1947ee0fa86dffa6b4fcaeb0fc556a1c156b269fd0266bdb33aa5b4d903b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 19.982142857142858,
+  "epoch": 20.0,
   "eval_steps": 500,
-  "global_step": 1119,
+  "global_step": 1120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1568,6 +1568,13 @@
       "learning_rate": 2.4587060106245895e-09,
       "loss": 0.5558,
       "step": 1115
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 1.2500131130218506,
+      "learning_rate": 0.0,
+      "loss": 0.6466,
+      "step": 1120
     }
   ],
   "logging_steps": 5,
@@ -1582,12 +1589,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.0394450225056973e+17,
+  "total_flos": 1.0403739277983744e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null