Training in progress, step 700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afb7ef1ec82241fd009b0e3fba2bb9ab103b17a1db82970ea238901a8ac4812e
+oid sha256:f32a7da569772a48bc4bb44fe20f233dca22633d11b16cf63087b282dddb2144
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f42dc44073a48dac19f32e76f64eb608346ac531bb737ea8e05ae9762b3d7bf8
+oid sha256:5d00ad25407bfc484a9ce4c8f74640bca88681b85cb09120253451ba448ae67e
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96c115c7c9e612e3051941839195c9a04f1487acc5d657beb82249cc8517ab93
+oid sha256:86531503e92b314a02b947133ec6d6690797fb0906ab3cb8928fbc10aa585f3c
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e6544bc2a8c1702c364c1a0f85d998607374f0fe5fac06edca83a199f838d44
+oid sha256:57de5461484f9447d2927990c26a0e884578829d0cc740a7dbeb47b20108cb08
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.199812529292298,
+  "epoch": 1.3997812841743478,
   "eval_steps": 500,
-  "global_step": 600,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -57,6 +57,13 @@
       "learning_rate": 9.6e-05,
       "loss": 1.3505,
       "step": 600
+    },
+    {
+      "epoch": 1.3997812841743478,
+      "grad_norm": 0.10571713745594025,
+      "learning_rate": 9.533333333333334e-05,
+      "loss": 1.3431,
+      "step": 700
     }
   ],
   "logging_steps": 100,
@@ -76,7 +83,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.364406702587249e+17,
+  "total_flos": 1.0925156414468915e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null