Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:254ff33416f948c0a5ab730b1f92b1195f7cd96c0833948ddd154fc99ef19875
+oid sha256:5e32ea8fc338d99e4e0c13688e72a59216b557fc2acf70623158aa87abae95a0
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4de86b08df661954295c9be641d5c5855adc59b2992c231abd3108ebd6b176ed
+oid sha256:7f725303b41f6995c7b8ecf7a946e767717a1a6ae7815ce9b26dea67c1fce26b
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5644a0717f1231448981eced6544705649d1cd238d725b15969f77f29be3b8e
+oid sha256:ab1d35b7b08d2869ce54f82448af01693fcbfcf11fc2ad8a25dbf70409dac1df
 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": 0.028399781540142,
+  "epoch": 0.056799563080284,
   "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": 13.003,
       "eval_steps_per_second": 6.535,
       "step": 10
+    },
+    {
+      "epoch": 0.03276897870016385,
+      "grad_norm": 17.777523040771484,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.1332,
+      "step": 15
+    },
+    {
+      "epoch": 0.04369197160021846,
+      "grad_norm": 9.074566841125488,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.9946,
+      "step": 20
+    },
+    {
+      "epoch": 0.04369197160021846,
+      "eval_loss": 0.9706413149833679,
+      "eval_runtime": 14.9005,
+      "eval_samples_per_second": 12.953,
+      "eval_steps_per_second": 6.51,
+      "step": 20
+    },
+    {
+      "epoch": 0.054614964500273075,
+      "grad_norm": 16.745901107788086,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.95,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2484418841149440.0,
+  "total_flos": 4968837682298880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null