Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88603b45b11d99e4e86c4f539cda5e2dbc19e0252e0f670f33088f7e6af8e253
+oid sha256:0c282c34ebc01431d5b60cc0659f2d15a30e8621b2c400c750a7c276a35d5cec
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74cccb85c4ab1fa228f737890ed061b25c8663063d3f518c0522a169a3e8fdac
+oid sha256:38a280c301f831d9193e6e7e722f6ded30e9eb11e77666321648df584951abfc
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02c5fd8138c740194f70b268d048773555e70d025e165ecc026d15ff4300315b
+oid sha256:4ce9ec22e0051f976ac081d26951edb3de92acba5c29f4c684fe32b805e5bc15
 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": 0.0994263862332696,
+  "epoch": 0.1988527724665392,
   "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": 173.599,
       "eval_steps_per_second": 88.378,
       "step": 10
+    },
+    {
+      "epoch": 0.1147227533460803,
+      "grad_norm": 0.07909376919269562,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 10.3621,
+      "step": 15
+    },
+    {
+      "epoch": 0.15296367112810708,
+      "grad_norm": 0.055342454463243484,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 10.3562,
+      "step": 20
+    },
+    {
+      "epoch": 0.15296367112810708,
+      "eval_loss": 10.362905502319336,
+      "eval_runtime": 0.3155,
+      "eval_samples_per_second": 174.326,
+      "eval_steps_per_second": 88.748,
+      "step": 20
+    },
+    {
+      "epoch": 0.19120458891013384,
+      "grad_norm": 0.07391843944787979,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 10.3575,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 168101806080.0,
+  "total_flos": 336203612160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null