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:f82f0245db55d96d9f94a2988999618fae7f5b8bb3d01b5a7bb84f9f9f4f7e4b
+oid sha256:994067ea78c27cf68633268d2babb7c8735ede4ed33070e46c0708ce0cf11ee5
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2ebd6e52e935accca36f0cb4a0d2115b2e403c0ed0d724aebe77f5358f17bcb
+oid sha256:f7344674f821309bbe5e993b49e1da2bdeabc6925140aa345b6c768a12d56444
 size 11710970

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": 0.002416821074679771,
+  "epoch": 0.0032224280995730285,
   "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": 140.103,
       "eval_steps_per_second": 70.051,
       "step": 15
+    },
+    {
+      "epoch": 0.0025779424796584225,
+      "grad_norm": 0.7156417369842529,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.1565,
+      "step": 16
+    },
+    {
+      "epoch": 0.002739063884637074,
+      "grad_norm": 0.6914603114128113,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.1457,
+      "step": 17
+    },
+    {
+      "epoch": 0.0029001852896157255,
+      "grad_norm": 0.6389317512512207,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.1318,
+      "step": 18
+    },
+    {
+      "epoch": 0.003061306694594377,
+      "grad_norm": 0.7102766036987305,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.1477,
+      "step": 19
+    },
+    {
+      "epoch": 0.0032224280995730285,
+      "grad_norm": 0.5916241407394409,
+      "learning_rate": 0.0,
+      "loss": 0.1028,
+      "step": 20
+    },
+    {
+      "epoch": 0.0032224280995730285,
+      "eval_loss": 0.13295121490955353,
+      "eval_runtime": 74.6245,
+      "eval_samples_per_second": 140.088,
+      "eval_steps_per_second": 70.044,
+      "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": 1443273092628480.0,
+  "total_flos": 1924364123504640.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null