Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cd33aea19cbb90f74c06f190b1d08a7a9620953d6f1e68e25beb49e043baca9
+oid sha256:f287704ce4ebf2723f3cb77530d91e120091e1877fb36265728dd30e022a672b
 size 228140600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b95fd79ef5b53b2c2e71fb2f72ac7e0e257a5ee768030138c53a80985d102f07
+oid sha256:8436a6ad617f54ee3426a5292c09564806ba8ee9afcfc38c72bd391511febbca
 size 116472340

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8a101fd84c84fefaca841c30a726da3b20f369daabcca14bb9de1ca1b1b54fe
+oid sha256:07fd69d00474f7452dfa2874201aa85c7ba86db9ba98cc2657ecdee75796730c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
+oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.030927835051546393,
+  "epoch": 0.061855670103092786,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 6.804,
       "eval_steps_per_second": 0.861,
       "step": 9
+    },
+    {
+      "epoch": 0.041237113402061855,
+      "grad_norm": 3.4861974716186523,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 3.3622,
+      "step": 12
+    },
+    {
+      "epoch": 0.05154639175257732,
+      "grad_norm": 2.4739320278167725,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 3.4222,
+      "step": 15
+    },
+    {
+      "epoch": 0.061855670103092786,
+      "grad_norm": 2.656764507293701,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 3.3192,
+      "step": 18
+    },
+    {
+      "epoch": 0.061855670103092786,
+      "eval_loss": 0.781949520111084,
+      "eval_runtime": 72.0068,
+      "eval_samples_per_second": 6.805,
+      "eval_steps_per_second": 0.861,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.14501064818688e+16,
+  "total_flos": 6.29002129637376e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null