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:b1bf815ac380ac8ab158dba6dc9b537c83ae05694d8296e9f32b75e26bb90b67
+oid sha256:be63056b19e546c2f0de5daacc0fb04ea8576a6e010817b13f4913583223edee
 size 28350504

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d079feea3fd91891468985268e482629488401ebe9d5ae896ed5c83e2c07de1
+oid sha256:1e20dad75344906899e09469361808a87add652fefcedf201ebe45f899053118
 size 14714004

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": 0.009418043401483342,
+  "epoch": 0.01255739120197779,
   "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": 32.171,
       "eval_steps_per_second": 16.091,
       "step": 15
+    },
+    {
+      "epoch": 0.010045912961582231,
+      "grad_norm": 1.5516988039016724,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 22.9258,
+      "step": 16
+    },
+    {
+      "epoch": 0.01067378252168112,
+      "grad_norm": 3.2057738304138184,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 23.6406,
+      "step": 17
+    },
+    {
+      "epoch": 0.01130165208178001,
+      "grad_norm": 3.0766243934631348,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 24.7305,
+      "step": 18
+    },
+    {
+      "epoch": 0.0119295216418789,
+      "grad_norm": 1.9255625009536743,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 21.9883,
+      "step": 19
+    },
+    {
+      "epoch": 0.01255739120197779,
+      "grad_norm": 1.7242449522018433,
+      "learning_rate": 0.0,
+      "loss": 21.7461,
+      "step": 20
+    },
+    {
+      "epoch": 0.01255739120197779,
+      "eval_loss": 1.4681618213653564,
+      "eval_runtime": 84.5809,
+      "eval_samples_per_second": 31.721,
+      "eval_steps_per_second": 15.866,
+      "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": 2785651690831872.0,
+  "total_flos": 3756522253320192.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null