Training in progress, step 7000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae50fb16913624ef3c6c3e417ad92f5263de849d4297b7a9b7855b7c1a90aa12
+oid sha256:37156ed458c0af06e67a3fd0f0efc5939e7cd439534e0a49f4109f30a2afe3a7
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b529112831d3ef3c0a1c58d46db3375d9c615744e36fc10560f30c02e5a59332
+oid sha256:233f034f74b1dd500246a432e28e753d13148fd4fd1e8af06cb8b841b1ad0ce8
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06051ff2563f6929a52be1f2a6173daac8bdf2ae58052429e1cd974260b79ebf
+oid sha256:b2a13e635ed6b5c2c06343ba390423efe0872067f1279a43aecb1730f878b366
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:344062337e3a13dab9ea0f70913ee0c41826ffaef2b21b1cfec0d360964d9faa
+oid sha256:4b86eafe1c95adc1f462ce0c55f1d3cf874f92c526c0737d22821cd92cddcb9b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 13.797844086861428,
+  "epoch": 13.997812841743478,
   "eval_steps": 500,
-  "global_step": 6900,
+  "global_step": 7000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -594,6 +594,21 @@
       "learning_rate": 5.4000000000000005e-05,
       "loss": 1.236,
       "step": 6900
+    },
+    {
+      "epoch": 13.997812841743478,
+      "grad_norm": 0.22089041769504547,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 1.242,
+      "step": 7000
+    },
+    {
+      "epoch": 13.997812841743478,
+      "eval_loss": 1.1090010404586792,
+      "eval_runtime": 781.1131,
+      "eval_samples_per_second": 19.872,
+      "eval_steps_per_second": 2.485,
+      "step": 7000
     }
   ],
   "logging_steps": 100,
@@ -613,7 +628,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0769053972669923e+19,
+  "total_flos": 1.092512894385809e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null