Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8894b9d8ac36c38b5080b99880a8e14b512f8a931c448da5c52fd1c66e52710e
+oid sha256:d746e37bcd051c5d2867a1a0f72113c7bc0245720bfe8a2018e3c6a77d68e070
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0a912df019ebbdc3ddc598a4fec6725c894e15a123235800b9e94429b6e5469
+oid sha256:bbfd276a1d0b524794778e0619af5594cd1c1fbf31c4eb78057af55fadb38259
 size 61926

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c21c3dc74b2937662ccab666858bfec21c3948be77f6128755465d6a551d61e7
+oid sha256:966a565451d95ffa4430f7404113c3a1fff75079169b5e76044e2be56be65931
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc7c1ef018b1e6de2abd772589c59dd72358c0b6677c85a565a049eb95faabc1
+oid sha256:36a475c26de9bb0c78147934fd1a828899cddbea48550be8571e54c23310d6e6
 size 14512

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": 0.004089805308226473,
+  "epoch": 0.005453073744301964,
   "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": 135.188,
       "eval_steps_per_second": 33.801,
       "step": 15
+    },
+    {
+      "epoch": 0.004362458995441571,
+      "grad_norm": 0.03549959138035774,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 11.9375,
+      "step": 16
+    },
+    {
+      "epoch": 0.004635112682656669,
+      "grad_norm": 0.0373225063085556,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 11.9432,
+      "step": 17
+    },
+    {
+      "epoch": 0.004907766369871768,
+      "grad_norm": 0.03938879817724228,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 11.944,
+      "step": 18
+    },
+    {
+      "epoch": 0.005180420057086865,
+      "grad_norm": 0.041206326335668564,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 11.9442,
+      "step": 19
+    },
+    {
+      "epoch": 0.005453073744301964,
+      "grad_norm": 0.03595578670501709,
+      "learning_rate": 0.0,
+      "loss": 11.9405,
+      "step": 20
+    },
+    {
+      "epoch": 0.005453073744301964,
+      "eval_loss": 11.938558578491211,
+      "eval_runtime": 182.5252,
+      "eval_samples_per_second": 135.373,
+      "eval_steps_per_second": 33.847,
+      "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": 359745454080.0,
+  "total_flos": 479660605440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null