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:d4495c81544f29e8c57674c66a99b5e87a16e453c307ff72ed45c3b12eb4d476
+oid sha256:2ea2c0afce6861a9d1adcda53d9869d324b76f501850e4ce5260c1f8e957c844
 size 161714

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fdb0e6c6545534785ce31cf6396692f0726ed62ce232d2c5001e39b01ce5797
+oid sha256:bae47a624d9d05de7b38d8de7ebded695d52b771e0c2ae496e2e72ede66ef083
 size 64750

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": 0.0027649132508467547,
+  "epoch": 0.0036865510011290063,
   "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": 757.629,
       "eval_steps_per_second": 378.856,
       "step": 15
+    },
+    {
+      "epoch": 0.002949240800903205,
+      "grad_norm": 0.10987330228090286,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 6.9401,
+      "step": 16
+    },
+    {
+      "epoch": 0.003133568350959655,
+      "grad_norm": 0.11077705770730972,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 6.9358,
+      "step": 17
+    },
+    {
+      "epoch": 0.0033178959010161054,
+      "grad_norm": 0.10548257827758789,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 6.937,
+      "step": 18
+    },
+    {
+      "epoch": 0.003502223451072556,
+      "grad_norm": 0.1043916642665863,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 6.9403,
+      "step": 19
+    },
+    {
+      "epoch": 0.0036865510011290063,
+      "grad_norm": 0.10964982956647873,
+      "learning_rate": 0.0,
+      "loss": 6.9381,
+      "step": 20
+    },
+    {
+      "epoch": 0.0036865510011290063,
+      "eval_loss": 6.937661170959473,
+      "eval_runtime": 12.1995,
+      "eval_samples_per_second": 748.968,
+      "eval_steps_per_second": 374.525,
+      "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": 79429404672.0,
+  "total_flos": 105796012032.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null