Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:327e1fce2e63dae8a2d4099dffd9997a28c2000c73b4387b9c65f61f9cee75dd
+oid sha256:fa2ab53143a30f51c80d7761d59feac2e20eca0ae0b9b2b9528e9e59840eb935
 size 130583912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:256737b5651fa28d430bb2189d3606e1eeb73c220b5e6e809a4ef88ed8594f97
+oid sha256:71ddfb5e1737be553298fd1f7661b467e09fc0480c55fdaf2729acfd2a33fe2d
 size 66578772

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a109e0c9f38066f0989282257dd7eb9449c1052dcada1f7051f628fab81dd162
+oid sha256:c3cb51c865de749e1c981ae84c7a4541c12d5f3faba169695b5eaed850549ba2
 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": 0.001122940376185026,
+  "epoch": 0.001684410564277539,
   "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": 21.236,
       "eval_steps_per_second": 10.62,
       "step": 26
+    },
+    {
+      "epoch": 0.0012957004340596453,
+      "grad_norm": 1.3415583372116089,
+      "learning_rate": 0.0002,
+      "loss": 4.4065,
+      "step": 30
+    },
+    {
+      "epoch": 0.001684410564277539,
+      "eval_loss": 2.131037473678589,
+      "eval_runtime": 230.2945,
+      "eval_samples_per_second": 21.169,
+      "eval_steps_per_second": 10.586,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4213957775327232.0,
+  "total_flos": 6300480557285376.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null