Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5331d1628d37d84f0d874ab2e26881e4ccc9d2c19a5873afc329940d718b4185
+oid sha256:bb3808db039136cd4caaccb1042ada32261ef3ae947df0a346a07922149fbb8c
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cce99f7fc5ae7aeae275d6447e52abb38d3254552daabde6e448947cfbdb3213
+oid sha256:5cc74c2f94acacd49d4250f2433ac3254bb9bee70c67c0bc9a4f9f4ba0c8302d
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa7f64ab8cf96f1118762f8652227986903e4e175b8bcf5e33b2a546271ec0ca
+oid sha256:8356e0eedb914506be9d6834a09dc3748c48d92697d3720f05ef898a38d1c12e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00026202413645410797,
+  "epoch": 0.0005240482729082159,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 11.104,
       "eval_steps_per_second": 5.552,
       "step": 10
+    },
+    {
+      "epoch": 0.0003023355420624323,
+      "grad_norm": 1.3025918006896973,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.166,
+      "step": 15
+    },
+    {
+      "epoch": 0.0004031140560832431,
+      "grad_norm": 0.7983736395835876,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.3881,
+      "step": 20
+    },
+    {
+      "epoch": 0.0004031140560832431,
+      "eval_loss": 1.1858701705932617,
+      "eval_runtime": 1883.6837,
+      "eval_samples_per_second": 11.09,
+      "eval_steps_per_second": 5.545,
+      "step": 20
+    },
+    {
+      "epoch": 0.0005038925701040538,
+      "grad_norm": 1.699404239654541,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.32,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3606650283884544.0,
+  "total_flos": 6982105036750848.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null