Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8cf3c75ed154144930a89770022dbc00ce375ca91b3f45450d73711dcc7337a
+oid sha256:563f421ffa442d3aa13b8be3b878dc4a53a7a53d20eed2601be49f2cc43d0183
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74769fb53a9e304920fc5af682df0a32dd0909b9ec16ffbd062568a61cb10794
+oid sha256:53d567ca27f19ffb5e54a1120e8d62298eafe2678a97306cf40c97db14a9bc71
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff5440c0314dadc3defe4b4803f353543d71edfcba882e67961bec9458fb6240
+oid sha256:9ea24ba22f005ab5531315a7c25fe17ce3b0d82d32e4d057cd4a8d9beeaa0eb4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
+oid sha256:532138a5ca880d8da393ae449e5715b2766def36b8838785ca08d07228b119b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.025518341307814992,
+  "epoch": 0.03402445507708666,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 8.323,
       "eval_steps_per_second": 4.162,
       "step": 15
+    },
+    {
+      "epoch": 0.027219564061669324,
+      "grad_norm": 0.26081982254981995,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.5636,
+      "step": 16
+    },
+    {
+      "epoch": 0.028920786815523656,
+      "grad_norm": 0.2586057484149933,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.5703,
+      "step": 17
+    },
+    {
+      "epoch": 0.03062200956937799,
+      "grad_norm": 0.27153581380844116,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.5962,
+      "step": 18
+    },
+    {
+      "epoch": 0.03232323232323232,
+      "grad_norm": 0.2530609965324402,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.5838,
+      "step": 19
+    },
+    {
+      "epoch": 0.03402445507708666,
+      "grad_norm": 0.2491098791360855,
+      "learning_rate": 0.0,
+      "loss": 0.5973,
+      "step": 20
+    },
+    {
+      "epoch": 0.03402445507708666,
+      "eval_loss": 0.5983208417892456,
+      "eval_runtime": 118.9206,
+      "eval_samples_per_second": 8.325,
+      "eval_steps_per_second": 4.162,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.826444695044096e+16,
+  "total_flos": 2.455296539413709e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null