Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:241688fefffd9a5c1e22a44b7729f7c18865c59e0c7d3f84be94f06718b0d2f8
+oid sha256:cc44d30fb807194f934baa17018d2587be8833bd21c6d94bfbe68408be88674a
 size 63592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6461f1c93df81da1a8f04f39fd35710cc9ccfbaec810bcac37622646099c5f15
+oid sha256:3510b71b1abd0a9073de3f79a7a09084391d67f511e82e34350815c1b0e7a5e1
 size 132798

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9da3a42e0bbca9fd9039ff3229d3da85b8023636d66e5e57c5cb1b6b33b4b08
+oid sha256:03d057dd57daf31a4f83fa1f977b30587086adcd472d02db30db1ae091bd8ff0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4d20cdfdd80bd4f7336e0d1d85ea3a727e6acd58210dc60f9f2cd451325f653
+oid sha256:e7f75dad5b4fa698adb63b89c53682112a536ec6b4f570bd7793123dfd2a0133
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003068268984914344,
+  "epoch": 0.006136537969828688,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 487.81,
       "eval_steps_per_second": 61.013,
       "step": 9
+    },
+    {
+      "epoch": 0.004091025313219126,
+      "grad_norm": 0.4335339367389679,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 44.3549,
+      "step": 12
+    },
+    {
+      "epoch": 0.005113781641523907,
+      "grad_norm": 0.4942709803581238,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 44.3544,
+      "step": 15
+    },
+    {
+      "epoch": 0.006136537969828688,
+      "grad_norm": 0.4659290015697479,
+      "learning_rate": 4.9031542398457974e-05,
+      "loss": 44.3528,
+      "step": 18
+    },
+    {
+      "epoch": 0.006136537969828688,
+      "eval_loss": 11.08657455444336,
+      "eval_runtime": 10.2663,
+      "eval_samples_per_second": 481.283,
+      "eval_steps_per_second": 60.197,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 67381493760.0,
+  "total_flos": 134762987520.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null