Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47ed86c4db1c3259c50821fc2f6aba36cda977723e4f3d0da59b8e9093a6764c
+oid sha256:16da78818e0ea0e143e99a713c8320da7bf63fa6cf935c8c35e7961591184f7d
 size 28348936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57d9d4fd340db071154e35b1d938984112a5e764d589a38f87be3b9b966a0460
+oid sha256:d796ccb28000e5b63467ee3e2c162ce1634342ba73fae6277f5051e6df7d6a12
 size 14714068

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:239794f189f65bf0745ae2f09be34e81c5079b1768fc19d051489a49769828cc
+oid sha256:16175748798ebd7e55ba83d6c76d4f9b9828c7b45b2602fa6b62af224a20f7b0
 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": 0.00011641104740839906,
+  "epoch": 0.0001746165711125986,
   "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": 50.918,
       "eval_steps_per_second": 25.459,
       "step": 6
+    },
+    {
+      "epoch": 0.00013581288864313224,
+      "grad_norm": 0.460286408662796,
+      "learning_rate": 0.00014,
+      "loss": 0.9677,
+      "step": 7
+    },
+    {
+      "epoch": 0.0001552147298778654,
+      "grad_norm": 0.4825994372367859,
+      "learning_rate": 0.00016,
+      "loss": 0.7568,
+      "step": 8
+    },
+    {
+      "epoch": 0.0001746165711125986,
+      "grad_norm": 0.467182993888855,
+      "learning_rate": 0.00018,
+      "loss": 0.615,
+      "step": 9
+    },
+    {
+      "epoch": 0.0001746165711125986,
+      "eval_loss": 0.801249623298645,
+      "eval_runtime": 427.8714,
+      "eval_samples_per_second": 50.721,
+      "eval_steps_per_second": 25.36,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 283958386360320.0,
+  "total_flos": 421881031163904.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null