Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88b9cb482fe460d3a045a5b39a056f4c236899a3096e3d0dc70a9928d7b3b024
+oid sha256:cce16819f3b2a3f86f81b51bc95aace7e5cd8b689d9b4879d3712a3d01e1f407
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bf01d2d6b825b7be7cb638e33103c34e907c5ecdd6252e5397114e14496f9f7
+oid sha256:030de5a7a7da1080c6e178766ffb60a1a91e8a7cdc7d3238ff1112f0e8f18b90
 size 43122580

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86152328387bf4d06e154ce72c80c1e37ad9b4670390d983a136b7723139aeec
+oid sha256:e0cc4f5771e128923b9430595abb172a5e72b2e428383e97a55cc2fb392c3c2d
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b6a20c76ee9618e0647deb8c445da5bd6342388307bcf338931fe3c22c75fe2
+oid sha256:9266f1829e37195a290d895cb32368ff61948718ec0088d449dbeb80be37ba11
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f29ee702fb88b51e8b0f5ef18a0af6b3582ef2f9d5591203f8b3c2639e4a5730
+oid sha256:343e8e950274507c676abad7d0877f6d1de98c010bdb20e2daef3337f5cbc833
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:046b7b8139527cac471c01c3dae2e7434e9471dc6563d41a3f634f19133b5b17
+oid sha256:0c986b424c4411be258ea4120367a1ac1c89ea70ed1457d2d84732fe2842fffd
 size 15024

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": 0.11214953271028037,
+  "epoch": 0.16822429906542055,
   "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": 91.989,
       "eval_steps_per_second": 12.13,
       "step": 6
+    },
+    {
+      "epoch": 0.1308411214953271,
+      "grad_norm": 1.3764944076538086,
+      "learning_rate": 0.00014,
+      "loss": 1.8747,
+      "step": 7
+    },
+    {
+      "epoch": 0.14953271028037382,
+      "grad_norm": 1.407188892364502,
+      "learning_rate": 0.00016,
+      "loss": 1.637,
+      "step": 8
+    },
+    {
+      "epoch": 0.16822429906542055,
+      "grad_norm": 1.341946005821228,
+      "learning_rate": 0.00018,
+      "loss": 1.718,
+      "step": 9
+    },
+    {
+      "epoch": 0.16822429906542055,
+      "eval_loss": 1.5427663326263428,
+      "eval_runtime": 0.987,
+      "eval_samples_per_second": 92.195,
+      "eval_steps_per_second": 12.158,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4438954195550208.0,
+  "total_flos": 6658431293325312.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null