Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c9c34b5aa61a37ee2b53486e49d7e00f7af5d3c76ae2114ed0d4be29626b8c2
+oid sha256:e755591a8a624afb81b978fe271f60682517b87b0810eb5a6ccc5694503de5be
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cddb53a621357c80a6b5a559521ef8b255895b67ed328f3ba367ce941ff19c6
+oid sha256:186fdfc752eece3fb571761dffea136a83a04e74b24f73c815871e7be3f8ee05
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8aeca134f7586c746af7a8dabb5d65178bb190c2f8f63160e7b8259f3f735ec0
+oid sha256:bfb718e76d9b16d02c497c2ede8a036c7d08af1cbcc5f32f9af79dccf0b427a2
 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": 0.003282724661469019,
+  "epoch": 0.004924086992203529,
   "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": 14.874,
       "eval_steps_per_second": 7.437,
       "step": 6
+    },
+    {
+      "epoch": 0.0038298454383805225,
+      "grad_norm": 41.94812774658203,
+      "learning_rate": 0.00014,
+      "loss": 13.2626,
+      "step": 7
+    },
+    {
+      "epoch": 0.004376966215292026,
+      "grad_norm": 45.55237579345703,
+      "learning_rate": 0.00016,
+      "loss": 12.713,
+      "step": 8
+    },
+    {
+      "epoch": 0.004924086992203529,
+      "grad_norm": 52.35283660888672,
+      "learning_rate": 0.00018,
+      "loss": 13.6203,
+      "step": 9
+    },
+    {
+      "epoch": 0.004924086992203529,
+      "eval_loss": 2.82289981842041,
+      "eval_runtime": 51.8845,
+      "eval_samples_per_second": 14.841,
+      "eval_steps_per_second": 7.42,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1095419245363200.0,
+  "total_flos": 1621220483137536.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null