Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28b4444d895fa5a08ceb087871ee3fc6281105cd5c94240e89917ee899ba1122
+oid sha256:ed6bd37466d7f639a9f30071d56b68bf557fe2a58a3ab7504a35ad678ef1ee7b
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c453768a676d1e0b8e6a9091fc288277e4e9fa4fb7ff12156fbccfe8b33f02c4
+oid sha256:042182c79cacadd13814e5327872be7337cf226b413ccffac9b6d99f45da1d1d
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ec54827547718f4c97d4a5e121a3be903aca4b7e01859f0f8d62916134f2417
+oid sha256:d695f97327a3dac4265482719092954caef35467509931c881317e90ad4261f1
 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": 6.73863907568334e-05,
+  "epoch": 0.0001010795861352501,
   "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": 14.43,
       "eval_steps_per_second": 7.215,
       "step": 6
+    },
+    {
+      "epoch": 7.86174558829723e-05,
+      "grad_norm": 1.3429189920425415,
+      "learning_rate": 0.00014,
+      "loss": 3.6685,
+      "step": 7
+    },
+    {
+      "epoch": 8.98485210091112e-05,
+      "grad_norm": 1.129899263381958,
+      "learning_rate": 0.00016,
+      "loss": 4.254,
+      "step": 8
+    },
+    {
+      "epoch": 0.0001010795861352501,
+      "grad_norm": 1.9611945152282715,
+      "learning_rate": 0.00018,
+      "loss": 4.4935,
+      "step": 9
+    },
+    {
+      "epoch": 0.0001010795861352501,
+      "eval_loss": 0.952491819858551,
+      "eval_runtime": 2596.6683,
+      "eval_samples_per_second": 14.438,
+      "eval_steps_per_second": 7.219,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3166204172697600.0,
+  "total_flos": 4670151154728960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null