Training in progress, step 16, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6240728159d513faa05abf6b5d7ed2406f17cba8a6ca15979a18ce62688bde0f
+oid sha256:3923c6c2d238cd3361024c80cac4a57bea4c1dd24732d212c7c0481b868aeeb4
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3647ec73c1e57bf25af24da7e11057a0a6dc36496110229d4e9f1d78ece690b
+oid sha256:ca49e2c253d38e24ae4972e1bc709e59f2e1296805f1052620ce8f42596247ac
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9273107ed22f2b0460ae677b61e5921af160c5c9d230441f93d948a850671aa
+oid sha256:e841c8d708d2d450b0eab7be6e2c4e08cbedd4e297878439ca4360fd0b733323
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68888158764ed5e658b457a541f86335ea31432325308674d2962aa98e037fa4
+oid sha256:5b52924c88c1c80163d374a6650253dd74b8b46052a3da6fc5e4076e57b5effa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003593083314619358,
+  "epoch": 0.00479077775282581,
   "eval_steps": 4,
-  "global_step": 12,
+  "global_step": 16,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -123,6 +123,42 @@
       "eval_samples_per_second": 8.264,
       "eval_steps_per_second": 8.264,
       "step": 12
+    },
+    {
+      "epoch": 0.003892506924170971,
+      "grad_norm": 17.937646865844727,
+      "learning_rate": 0.00019723699203976766,
+      "loss": 4.7382,
+      "step": 13
+    },
+    {
+      "epoch": 0.004191930533722584,
+      "grad_norm": 21.441980361938477,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 5.3976,
+      "step": 14
+    },
+    {
+      "epoch": 0.0044913541432741975,
+      "grad_norm": 32.05086898803711,
+      "learning_rate": 0.0001923879532511287,
+      "loss": 3.6275,
+      "step": 15
+    },
+    {
+      "epoch": 0.00479077775282581,
+      "grad_norm": 43.66167449951172,
+      "learning_rate": 0.0001891006524188368,
+      "loss": 2.7349,
+      "step": 16
+    },
+    {
+      "epoch": 0.00479077775282581,
+      "eval_loss": 4.855716705322266,
+      "eval_runtime": 83.6415,
+      "eval_samples_per_second": 8.417,
+      "eval_steps_per_second": 8.417,
+      "step": 16
     }
   ],
   "logging_steps": 1,
@@ -142,7 +178,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4451323701362688.0,
+  "total_flos": 5935098268483584.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null