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:ae278b3e85383875f421ff36b4eee7e5005fe8d313b4f062df299d62b4a24a29
+oid sha256:45a26f1d361cd3849876e65f79c4f32a05322ed7373cea3a9ca6bcfe5aeb7746
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24303179311cba1a348c5db8a5b04b807ea04ca8c092ba7b9e2def36d26550cc
+oid sha256:0583678e6e6f4c9481e2c987a6c402372464e783c750fb8444c5692dde18977c
 size 13685516

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": 0.42328042328042326,
+  "epoch": 0.564373897707231,
   "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": 115.351,
       "eval_steps_per_second": 57.676,
       "step": 15
+    },
+    {
+      "epoch": 0.4514991181657848,
+      "grad_norm": 3.738027811050415,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 4.8855,
+      "step": 16
+    },
+    {
+      "epoch": 0.47971781305114636,
+      "grad_norm": 3.98640775680542,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 4.7694,
+      "step": 17
+    },
+    {
+      "epoch": 0.5079365079365079,
+      "grad_norm": 3.7007837295532227,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 4.4581,
+      "step": 18
+    },
+    {
+      "epoch": 0.5361552028218695,
+      "grad_norm": 3.676358699798584,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 4.7911,
+      "step": 19
+    },
+    {
+      "epoch": 0.564373897707231,
+      "grad_norm": 3.9247279167175293,
+      "learning_rate": 0.0,
+      "loss": 5.0012,
+      "step": 20
+    },
+    {
+      "epoch": 0.564373897707231,
+      "eval_loss": 4.537546634674072,
+      "eval_runtime": 0.488,
+      "eval_samples_per_second": 122.95,
+      "eval_steps_per_second": 61.475,
+      "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": 1534751869501440.0,
+  "total_flos": 2046335826001920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null