Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64f9772489ea45241c3b74220937da4c4eb5484153c0557326a15c06d42f648d
+oid sha256:41f5792c3a76e286360e46a3c921d7887502be9fb019afa4aa4b790c082351d6
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc8062de69e742cf052a7407287bf2662082593b95974cce2a5d0af9bf461f78
+oid sha256:f61de9a324e9cd3b6c83056698d6dcef727109b4912422e475e84efe9d0004bc
 size 56088148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc4262f26a7ae3e87b963a0c97bf7c35ec6460c0fba62e7fd4e3ce9d7a94f7e7
+oid sha256:4b17ea9222f849df45fb42b477e3d57caefe1e563a3e7a364cbecb2349a17614
 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": 0.002551834130781499,
+  "epoch": 0.003827751196172249,
   "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": 17.88,
       "eval_steps_per_second": 8.94,
       "step": 6
+    },
+    {
+      "epoch": 0.0029771398192450825,
+      "grad_norm": 0.5397375822067261,
+      "learning_rate": 0.00014,
+      "loss": 0.3469,
+      "step": 7
+    },
+    {
+      "epoch": 0.0034024455077086655,
+      "grad_norm": 0.4392431676387787,
+      "learning_rate": 0.00016,
+      "loss": 0.2646,
+      "step": 8
+    },
+    {
+      "epoch": 0.003827751196172249,
+      "grad_norm": 0.9264920353889465,
+      "learning_rate": 0.00018,
+      "loss": 0.4984,
+      "step": 9
+    },
+    {
+      "epoch": 0.003827751196172249,
+      "eval_loss": 0.30864137411117554,
+      "eval_runtime": 55.347,
+      "eval_samples_per_second": 17.887,
+      "eval_steps_per_second": 8.944,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1795355301642240.0,
+  "total_flos": 2745837520158720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null