Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:604190b91607495a96c7bb7e7cd1cbec5251930c92d0e89349f627fda735557a
+oid sha256:e860bf0515fd077598000b645c16894a72c856acda2e727e0a2ccef96fe1ad61
 size 3152296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:585223b93a53a805cffea836299f92d386281b91ed9343edfa576a53986cac69
+oid sha256:d4af30bd1bb5e26a4eb16973a47ead61fb8cdb6975b0a3c99f3f210281c91252
 size 1656058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:456bf484f2805c5eb5383d929dec834f74d12009334db2c37db29af2053d4bfc
+oid sha256:0b9c008c53bd43dddd700dd53d4fc40b32330d14b9af4a071419d30caa919a84
 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": 8.899535370090886e-05,
+  "epoch": 0.0001334930305513633,
   "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": 10.716,
       "eval_steps_per_second": 5.358,
       "step": 6
+    },
+    {
+      "epoch": 0.00010382791265106034,
+      "grad_norm": 1748.5992431640625,
+      "learning_rate": 0.00014,
+      "loss": 92.2292,
+      "step": 7
+    },
+    {
+      "epoch": 0.00011866047160121182,
+      "grad_norm": 1009.4827880859375,
+      "learning_rate": 0.00016,
+      "loss": 93.0452,
+      "step": 8
+    },
+    {
+      "epoch": 0.0001334930305513633,
+      "grad_norm": 1561.128173828125,
+      "learning_rate": 0.00018,
+      "loss": 94.7347,
+      "step": 9
+    },
+    {
+      "epoch": 0.0001334930305513633,
+      "eval_loss": 23.4540958404541,
+      "eval_runtime": 2399.9327,
+      "eval_samples_per_second": 11.828,
+      "eval_steps_per_second": 5.914,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 53623740432384.0,
+  "total_flos": 80435610648576.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null