Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fa58117a4938924a25486a199a69555062fb74688718d07080784fe386c8706
+oid sha256:f371e69118aa24af46b3112fdf48a413b931380bd21e38f71b480e6b25d9db12
 size 390888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b358b9cadf63f5321a8c3ef3926457906cd7f98e1a5eafcf55276fe0f90f2dc7
+oid sha256:61d6b93c04f9bb567ade70b1e83dbf10414462ce2db099f60e015501adefc646
 size 819770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:638f0e887c7eab30601fcd15f109e577ce9025b567cf9228ffde08282c0e880e
+oid sha256:bebbe731bd9094c7ae8f274487d73bb48b05017603343298a02474cb28c07b94
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
+oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.029612756264236904,
+  "epoch": 0.04441913439635535,
   "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": 147.037,
       "eval_steps_per_second": 73.518,
       "step": 26
+    },
+    {
+      "epoch": 0.03416856492027335,
+      "grad_norm": 2.010549545288086,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 7.197,
+      "step": 30
+    },
+    {
+      "epoch": 0.04441913439635535,
+      "eval_loss": 7.120815277099609,
+      "eval_runtime": 2.5391,
+      "eval_samples_per_second": 145.724,
+      "eval_steps_per_second": 72.862,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2900965588992.0,
+  "total_flos": 4376032837632.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null