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:e6032b80e870c19eb5346f983a00e5fd9df26ffcb4aab1c1dac0290262ddc703
+oid sha256:91527ce9e1bbfb1241dcd4e7627eadd7f5e7026991668efa26a777030e06ea1b
 size 119801528

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf5f81d0008a0bb825b308ed6ad95847405927d7e5ac4f965d62621631ae8294
+oid sha256:91d4705008320b4f3f10a90b200f2a87a0c74f8f9461d5d07955797a9a322ca9
 size 61392180

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6da2047a274c755c0067350f90a87d4e4999db848b8acad267ac54dfc400ebe
+oid sha256:22b986e54a9ba46b51f7d6a35d3aa00182e3eb1b57d986d578ac1c6971eed5b2
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cde5fb7acaa58cb5d1bf245cbac19a2d14b6a5da8d01ac17393e693e1f46f42d
+oid sha256:4cde64ac1e1b9a70fb43c9454e33d9256395fcbae080aa7b98e7e1a9794306bf
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
+oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5663716814159292,
+  "epoch": 0.8495575221238938,
   "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": 15.407,
       "eval_steps_per_second": 3.852,
       "step": 6
+    },
+    {
+      "epoch": 0.6607669616519174,
+      "grad_norm": 0.1833762377500534,
+      "learning_rate": 7e-05,
+      "loss": 0.7417,
+      "step": 7
+    },
+    {
+      "epoch": 0.7551622418879056,
+      "grad_norm": 0.2062716782093048,
+      "learning_rate": 8e-05,
+      "loss": 0.6748,
+      "step": 8
+    },
+    {
+      "epoch": 0.8495575221238938,
+      "grad_norm": 0.17450149357318878,
+      "learning_rate": 9e-05,
+      "loss": 0.6331,
+      "step": 9
+    },
+    {
+      "epoch": 0.8495575221238938,
+      "eval_loss": 0.7961457371711731,
+      "eval_runtime": 4.6683,
+      "eval_samples_per_second": 15.423,
+      "eval_steps_per_second": 3.856,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.29370782409687e+16,
+  "total_flos": 7.940561736145306e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null