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:e33e00267a8fc8e5863db515f1304e5b5eb1e311317c4b46ba0bb293c7741a29
+oid sha256:a0ec6488897e18bac0942589a93da1c8221f4a2149c0e6200077dd61ae22bfdd
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85e864983f05e856573bd7f530ecb96acac508bedda0a931c4861965378bf52a
+oid sha256:52ff8479c171ed7e534ea5f42a588efe29ae6018145d51d10ad26460e5fe63ae
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dd824ab7bf9f8eea6d9bd6e51d86488e2d9ca4852207360bea549e24419edb8
+oid sha256:7af5d8915c382105692ed749d9b6188f0a4abba79bdfb71cd3d9dfe9637ef600
 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": 0.0008983380745620602,
+  "epoch": 0.0013475071118430903,
   "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": 29.753,
       "eval_steps_per_second": 14.882,
       "step": 6
+    },
+    {
+      "epoch": 0.0010480610869890701,
+      "grad_norm": 7.51618766784668,
+      "learning_rate": 0.00014,
+      "loss": 12.9868,
+      "step": 7
+    },
+    {
+      "epoch": 0.0011977840994160803,
+      "grad_norm": 7.297400951385498,
+      "learning_rate": 0.00016,
+      "loss": 11.1761,
+      "step": 8
+    },
+    {
+      "epoch": 0.0013475071118430903,
+      "grad_norm": 8.24133586883545,
+      "learning_rate": 0.00018,
+      "loss": 10.9402,
+      "step": 9
+    },
+    {
+      "epoch": 0.0013475071118430903,
+      "eval_loss": 2.616652250289917,
+      "eval_runtime": 94.4398,
+      "eval_samples_per_second": 29.786,
+      "eval_steps_per_second": 14.898,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1099405738377216.0,
+  "total_flos": 1588030510989312.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null