Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:177243b74e1d1cce7058724d2aceda1f267b5387b4bddc0eea59d016f3be83a1
+oid sha256:4e554a6ddcf6b401a428ac4c2addea12a796d20914a40c75bdc629d1c1de5c4d
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4884dec45525a3391a731901a1a1dffb1cbb17176692c8eecec33cb4e9d54cef
+oid sha256:8a2389b005625d3141aebbfb4e36ab87b7472a587fa7e653fed3fbac8862feb8
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bebe9623d6986cc41007dc063eed3db9cefd4f4608731e8404713d008de3d95a
+oid sha256:a7fa4cc5e4c54240a40a09fd5dcfbbb810da4a034b6346087aa3ef80ea319364
 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": 0.004107479034742427,
+  "epoch": 0.00616121855211364,
   "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": 15.14,
       "eval_steps_per_second": 7.582,
       "step": 6
+    },
+    {
+      "epoch": 0.004792058873866164,
+      "grad_norm": 0.9566445350646973,
+      "learning_rate": 0.00014,
+      "loss": 0.5755,
+      "step": 7
+    },
+    {
+      "epoch": 0.005476638712989902,
+      "grad_norm": 0.7170482277870178,
+      "learning_rate": 0.00016,
+      "loss": 0.3715,
+      "step": 8
+    },
+    {
+      "epoch": 0.00616121855211364,
+      "grad_norm": 0.7598028182983398,
+      "learning_rate": 0.00018,
+      "loss": 0.6636,
+      "step": 9
+    },
+    {
+      "epoch": 0.00616121855211364,
+      "eval_loss": 0.7286975383758545,
+      "eval_runtime": 39.8807,
+      "eval_samples_per_second": 15.421,
+      "eval_steps_per_second": 7.723,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 425082731102208.0,
+  "total_flos": 637624096653312.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null