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:a3ef76f7cfba626d2931c74c23c78b46c203e1c17b7834d3de74536dfed5f95a
+oid sha256:fa7e226c96a167f2b79b56af5f87770e7212d5b8951865ff964ef112ced3bc12
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb8cd74da008f2013b8435f2560306701d052359d1d1e76c966970a0693c79d9
+oid sha256:784f79825e3d1776965c43dcbf4e77c8ef583adb2ef56e04f3865a07d6b3060c
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b77ec1d9059fbf29655439de7be3898314e6d6e711dfa2949a49c214c62651ad
+oid sha256:d43ab25a0e82acb814d1ea8e6e3081e15589e0ffbcf9e9292c2a91fda2e5dfa4
 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": 0.027972027972027972,
+  "epoch": 0.04195804195804196,
   "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": 3.973,
       "eval_steps_per_second": 2.008,
       "step": 6
+    },
+    {
+      "epoch": 0.03263403263403263,
+      "grad_norm": 1.7764925956726074,
+      "learning_rate": 0.00014,
+      "loss": 1.7216,
+      "step": 7
+    },
+    {
+      "epoch": 0.037296037296037296,
+      "grad_norm": 2.334268808364868,
+      "learning_rate": 0.00016,
+      "loss": 1.5436,
+      "step": 8
+    },
+    {
+      "epoch": 0.04195804195804196,
+      "grad_norm": 2.2170941829681396,
+      "learning_rate": 0.00018,
+      "loss": 1.2657,
+      "step": 9
+    },
+    {
+      "epoch": 0.04195804195804196,
+      "eval_loss": 0.9850502610206604,
+      "eval_runtime": 22.9684,
+      "eval_samples_per_second": 3.962,
+      "eval_steps_per_second": 2.003,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4451323701362688.0,
+  "total_flos": 6676985552044032.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null