Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f6d32b846963fce3b0ce83bc9ac9a904e044e8fdc2b2aa11ee14ec67e67c82b
+oid sha256:fdb0f1a4e3d377390242989c7597b4a161e73c35ca58a07278d73b93d7c02910
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a63a7155896dcbc653500b72848d0bb43bb7c65fc786fdea9a10aad2c660d39
+oid sha256:e53b522184bb7b4cfb0172b7a5570736b4ce12e1e2a5343437fa8715641f4f04
 size 18810036

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1408ea0898f967d863a6906088863086fda9adc1a0df2c6b0f931de941d308d7
+oid sha256:8ef17e9ba410bc3f5d9b461dda2259c2a90231bdf98f5d1ec6b03d36c8366fcd
 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": 0.001315068493150685,
+  "epoch": 0.0017534246575342466,
   "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": 9.188,
       "eval_steps_per_second": 4.594,
       "step": 15
+    },
+    {
+      "epoch": 0.0014027397260273973,
+      "grad_norm": 2.817159414291382,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.3368,
+      "step": 16
+    },
+    {
+      "epoch": 0.0014904109589041095,
+      "grad_norm": 3.2762200832366943,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.6302,
+      "step": 17
+    },
+    {
+      "epoch": 0.0015780821917808219,
+      "grad_norm": 3.8624162673950195,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.3912,
+      "step": 18
+    },
+    {
+      "epoch": 0.0016657534246575342,
+      "grad_norm": 3.024617910385132,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.4863,
+      "step": 19
+    },
+    {
+      "epoch": 0.0017534246575342466,
+      "grad_norm": 2.6845686435699463,
+      "learning_rate": 0.0,
+      "loss": 1.4299,
+      "step": 20
+    },
+    {
+      "epoch": 0.0017534246575342466,
+      "eval_loss": 1.0315130949020386,
+      "eval_runtime": 4189.8673,
+      "eval_samples_per_second": 9.17,
+      "eval_steps_per_second": 4.585,
+      "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": 8651451609907200.0,
+  "total_flos": 1.15352688132096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null