Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6782d9c18e4e4e4fea29ba54749f63f0db722c70f467d0023eda72bf9219a558
+oid sha256:35d8b0c08e6d1236d6d1df387e330c4fc78d9035e4f24cdf950b7e5fd90c730e
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cdec188575dbf0eb2185e60afba725a3f99ba20ca9de25a0270611c216398c3
+oid sha256:99d182410428985d3b71fcdf58b58a8786a514dfdb5b3248ef44124015d29b5a
 size 42608388

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d84ff24272829488712f1989a7155b45cfe23d2e4fa9c1135e2fa3ea3593371d
+oid sha256:84fea08a6e2b5141b80cda9f6c2bd7a3e1dcb46a0a8514d0c790b1f8a3832958
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:562360b448a53e7366b8643d15ad250a0f706aaefd28e30d76b7f5f4480c7196
+oid sha256:e2ff6f184064d83b8d06f27cab522b7fa1e27d3258094d54e6a8c251936b5ccb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0006502194490640591,
+  "epoch": 0.0009753291735960887,
   "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": 37.594,
       "eval_steps_per_second": 18.799,
       "step": 26
+    },
+    {
+      "epoch": 0.0007502532104585297,
+      "grad_norm": 4.003726005554199,
+      "learning_rate": 0.0002,
+      "loss": 2.0594,
+      "step": 30
+    },
+    {
+      "epoch": 0.0009753291735960887,
+      "eval_loss": 2.1543338298797607,
+      "eval_runtime": 223.7647,
+      "eval_samples_per_second": 37.624,
+      "eval_steps_per_second": 18.814,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 678576346103808.0,
+  "total_flos": 1068129433681920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null