Training in progress, step 4000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34ccd5de3dc33e2c7424dc7cf4b85a5a709fca9096fa4a9e57d5b285ff6b3114
+oid sha256:01f28a2cfbe46097b889037d6b49a6e9fd13b1f3c6281953c1196fd2f452dd65
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc942e4306700121c17e3615d588416b659b676b78b9a8f8eb5c18bf77158d0d
+oid sha256:2651424c1fdfdc11a3bfdbea30b0cfe6bae128a603d41ce6e825540d816c8f42
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddf16c50a5456b7ba636d92d279525e70ed7b592671b1bae1bbab7d4cde9be07
+oid sha256:d3a39bddaf232d4db7d809a03ebb90c92c83cae3d986f3b765a883d612586eae
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da2c93534b46f49cffb916f9acfdfa62706aa3d860ab98491bfe244dd7da6c9a
+oid sha256:584b957a5a99de554e78faf65e8297adcd8494b36ac89577e07e7716be571248
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.798781440399938,
+  "epoch": 7.998750195281987,
   "eval_steps": 500,
-  "global_step": 3900,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -336,6 +336,21 @@
       "learning_rate": 7.4e-05,
       "loss": 1.2611,
       "step": 3900
+    },
+    {
+      "epoch": 7.998750195281987,
+      "grad_norm": 0.18334655463695526,
+      "learning_rate": 7.333333333333333e-05,
+      "loss": 1.2651,
+      "step": 4000
+    },
+    {
+      "epoch": 7.998750195281987,
+      "eval_loss": 1.1447893381118774,
+      "eval_runtime": 781.963,
+      "eval_samples_per_second": 19.85,
+      "eval_steps_per_second": 2.482,
+      "step": 4000
     }
   ],
   "logging_steps": 100,
@@ -355,7 +370,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.086859778246574e+18,
+  "total_flos": 6.242934749434741e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null