Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8089242bb645865869841df37a93bdc6480804e7b717ea477e5b0331c343d7e4
+oid sha256:e48cbbfb68c68037e2930f194b50ddb00dc55d9ec0586f632bf3ca618fe35add
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d183cd4162ddce5ca62872d99403a0e9d909d8ed90e40e3a344ed10d68ca8c81
+oid sha256:35143f204c8684b9d4050fb640f49028cd531f1dbdace25958e722df4cf466df
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:151e353028597ac3bbcb27a88e2d4f6b066dcfb6ec28e51e087826b0b1cba8f6
+oid sha256:b662ea765df97f7a66a71911b10015a5f23a5c3fa96a62cecc3bf454b4bc880d
 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": 0.024051803885291396,
+  "epoch": 0.04810360777058279,
   "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": 15.188,
       "eval_steps_per_second": 7.594,
       "step": 10
+    },
+    {
+      "epoch": 0.027752081406105456,
+      "grad_norm": 2.6269290447235107,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.1259,
+      "step": 15
+    },
+    {
+      "epoch": 0.03700277520814061,
+      "grad_norm": 2.55375075340271,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.6842,
+      "step": 20
+    },
+    {
+      "epoch": 0.03700277520814061,
+      "eval_loss": 1.6327600479125977,
+      "eval_runtime": 15.1801,
+      "eval_samples_per_second": 15.02,
+      "eval_steps_per_second": 7.51,
+      "step": 20
+    },
+    {
+      "epoch": 0.04625346901017576,
+      "grad_norm": 1.9848346710205078,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.6157,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2132126528962560.0,
+  "total_flos": 4264253057925120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null