Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cebd18fe972c71a283bf4163973f14fe45973fc225bafe14cb8bc09b13a17f5
+oid sha256:25836831483eddea62d9774b59f64cc2edbeb532b5a2ff6f7b003b276cb35b91
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06a42f61c0f0195ca39cf8fa0bd74cf30251d3b988d4c76a70c5117e85d3e2b1
+oid sha256:fe0240de2a227ad3ecacdc8d9025c709fb41a21f50f46a8a4b211f352861a484
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5095323b290578a89328d8247b6223badac2013fbf499b9514ebea4b896d297
+oid sha256:882f931c75a63dbadf1613ab2f34ceb65bcdc210992aa9cbd7ce762e1fde05cb
 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": 0.004281891168599465,
+  "epoch": 0.006422836752899197,
   "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": 14.468,
       "eval_steps_per_second": 7.234,
       "step": 6
+    },
+    {
+      "epoch": 0.0049955396966993755,
+      "grad_norm": 1.8274019956588745,
+      "learning_rate": 0.00014,
+      "loss": 8.3603,
+      "step": 7
+    },
+    {
+      "epoch": 0.005709188224799286,
+      "grad_norm": 1.92953360080719,
+      "learning_rate": 0.00016,
+      "loss": 7.3223,
+      "step": 8
+    },
+    {
+      "epoch": 0.006422836752899197,
+      "grad_norm": 2.5140371322631836,
+      "learning_rate": 0.00018,
+      "loss": 7.4628,
+      "step": 9
+    },
+    {
+      "epoch": 0.006422836752899197,
+      "eval_loss": 1.858712911605835,
+      "eval_runtime": 40.7818,
+      "eval_samples_per_second": 14.467,
+      "eval_steps_per_second": 7.234,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1913780359397376.0,
+  "total_flos": 2891029904621568.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null