Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f071dd5c42804fed696496d523161d8cb84216a09596bb6044d9db4c1850888
+oid sha256:e4522a079c4a042db2b1e82067d732b883818340439689f0e4c7209b03f978a8
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22bd46da9e390ae96783b47cfd1546fb04cac513361c7e97b1c09bbb610469e4
+oid sha256:bba8c21b649d576e6fc0dadb64822dd464fe3c8333b328758ccb5da6450a35a1
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b67bd18c19d450b6e9540356d3dd1899dcc04f35f70c1cdcb528c1e2e8ee989
+oid sha256:3aa10da0a18ea67917350fb6e6f8db87ade3225f86b79930eb7ac553eb290db0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8712da1b2787df41952a507984ec77e0f72c59fac7ee6cf21606445686249de
+oid sha256:ccc7e73cc5879da996ace4c3a10d9efe08a100111973e801d61997747e95e982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2694300518134715,
+  "epoch": 0.40414507772020725,
   "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": 30.943,
       "eval_steps_per_second": 15.849,
       "step": 26
+    },
+    {
+      "epoch": 0.31088082901554404,
+      "grad_norm": 1.9059967994689941,
+      "learning_rate": 0.0001,
+      "loss": 1.283,
+      "step": 30
+    },
+    {
+      "epoch": 0.40414507772020725,
+      "eval_loss": 1.2791526317596436,
+      "eval_runtime": 1.3183,
+      "eval_samples_per_second": 31.1,
+      "eval_steps_per_second": 15.929,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4808867045179392.0,
+  "total_flos": 7213300567769088.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null