Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90df770a7f8e139ea1924b5175c7731c4d86d6de0e9828008fe2d46bee5b8655
+oid sha256:ce80b425795190903fb3ef7f4a458bb3e944828f724d90fffdff0952230f5af3
 size 556856304

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fc8ace2482ca6fbbe1d6d3b2feddba8b2bccfdb90411101276c5ccb1daf18b1
+oid sha256:30fecc5ea90faada7cf690a12b7e55363b32c900d50b03067f483cffe92b3b6e
 size 21599060

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42d1547cfe165d7076e0ab2f512ea7be0b299ed9e6de1e605a4b531e6745a46e
+oid sha256:e366af8effa8e611032ee14d35d0beb9af6ce001f26b03eb553dccb7c9dcb689
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.014268727705112961,
+  "epoch": 0.02140309155766944,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 48.891,
       "eval_steps_per_second": 24.446,
       "step": 6
+    },
+    {
+      "epoch": 0.016646848989298454,
+      "grad_norm": 3.635242462158203,
+      "learning_rate": 0.00014,
+      "loss": 9.9527,
+      "step": 7
+    },
+    {
+      "epoch": 0.019024970273483946,
+      "grad_norm": 4.8683881759643555,
+      "learning_rate": 0.00016,
+      "loss": 10.211,
+      "step": 8
+    },
+    {
+      "epoch": 0.02140309155766944,
+      "grad_norm": 3.6629574298858643,
+      "learning_rate": 0.00018,
+      "loss": 9.8779,
+      "step": 9
+    },
+    {
+      "epoch": 0.02140309155766944,
+      "eval_loss": 2.4013938903808594,
+      "eval_runtime": 3.5756,
+      "eval_samples_per_second": 49.781,
+      "eval_steps_per_second": 24.891,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 473388259737600.0,
+  "total_flos": 750891722342400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null