Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a6d06a192563b418a2f6118a3fdde7c56a5430719736a80ac1d98bafb158449
+oid sha256:66ad56e718ada3dd75faaa0787ae3cbff456e7157762d0a5ceae5a121aa56be7
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a7b8f29e4f85da9842b5f44c4861a1b2d7a921ab74fc9089b32823c5e02e576
+oid sha256:0c34343cbbdae79182114ab1d165c885bf67867bd46bdb16a117197627eb9b02
 size 335810490

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47898aacdfc05ed88d31ece4d750c31cbcf7ceceaa3e1e6598cfb52a47918a31
+oid sha256:e4c296fedb9152521e877e7944e7ca9a7bb83224c2090a586705dafb5d5e04b8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0013178486121406803,
+  "epoch": 0.0019767729182110206,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 2.1804,
       "step": 18
+    },
+    {
+      "epoch": 0.0013837410427477144,
+      "grad_norm": 0.6730942130088806,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.0049,
+      "step": 21
+    },
+    {
+      "epoch": 0.0015814183345688165,
+      "grad_norm": 0.5569067001342773,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.9578,
+      "step": 24
+    },
+    {
+      "epoch": 0.0015814183345688165,
+      "eval_loss": 1.9681271314620972,
+      "eval_runtime": 1194.7544,
+      "eval_samples_per_second": 5.348,
+      "eval_steps_per_second": 2.674,
+      "step": 24
+    },
+    {
+      "epoch": 0.0017790956263899185,
+      "grad_norm": 0.6647498607635498,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.9623,
+      "step": 27
+    },
+    {
+      "epoch": 0.0019767729182110206,
+      "grad_norm": 0.5334838032722473,
+      "learning_rate": 0.0,
+      "loss": 2.2075,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.020112731635712e+16,
+  "total_flos": 1.5579903537709056e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null