Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:899bff3567366bb4f7c84b0eb83832d403b17f61d07d60094156146ac6f35293
+oid sha256:28c7d0f6519969486d1e8b3dc92cbd5ba86896f3de04ab61aa918e2f73f009ff
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca147e24ceddd8ae928082c2cb6e77d35b039d96a397d6f4eb70b82f321acc9c
+oid sha256:4362974c0ec4d7eba105a5b3d3ec28b5d397a797be6f67aef0a833c70c5d80fb
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77d7eb4126c28640529f2ce4a22d6db17c1470033cc6aed0cb9270f79956de2c
+oid sha256:c785dbbd444bac9b4b9a6a2e8cf281fbcdc0727670030891e88bcc1bba168274
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
+oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.028769017980636236,
+  "epoch": 0.043153526970954356,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "eval_samples_per_second": 24.187,
       "eval_steps_per_second": 12.125,
       "step": 26
+    },
+    {
+      "epoch": 0.03319502074688797,
+      "grad_norm": 0.3897157907485962,
+      "learning_rate": 5e-05,
+      "loss": 0.3741,
+      "step": 30
+    },
+    {
+      "epoch": 0.043153526970954356,
+      "eval_loss": 0.332000195980072,
+      "eval_runtime": 15.7368,
+      "eval_samples_per_second": 24.211,
+      "eval_steps_per_second": 12.137,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6658431293325312.0,
+  "total_flos": 1.0218842471006208e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null