Training in progress, step 24, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83f95ac312a53b2b1e37a2a1a0e6bc5cddbc7bc08eca720057376c302fd1a8e9
+oid sha256:1308ab5b004737cda37c6f011533f981173cee903cd2ccf6c1b76fed4bc8922e
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0c8161e8e5681b86049a052bac0f569052ade09319433589f7aa50cceefee2f
+oid sha256:0f7d32e659796260eb80ee744578b61feb131752c58c91330bd88c49794e6421
 size 212298

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2eee07d3fc4d8a0abcc37fc9f663b2748ef62d5b07c21e50a8324927531b82b1
+oid sha256:9da8f5d493f0f752036f2ae2fae7ea8749d37cf1119ef3a2c45408ef763d8466
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:605d23f463d574da26fdafa2a2fc396d0b00160053ea75ca175c5c8e6f2990e2
+oid sha256:4293e50fb3c9f4c5f80a712103de6c5deaef7eaac0675ada5b61f2e11e3e6a04
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5601750547045952,
+  "epoch": 0.8402625820568927,
   "eval_steps": 8,
-  "global_step": 16,
+  "global_step": 24,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -66,6 +66,35 @@
       "eval_samples_per_second": 134.683,
       "eval_steps_per_second": 68.036,
       "step": 16
+    },
+    {
+      "epoch": 0.6301969365426696,
+      "grad_norm": 0.12901803851127625,
+      "learning_rate": 0.00018,
+      "loss": 10.3699,
+      "step": 18
+    },
+    {
+      "epoch": 0.7352297592997812,
+      "grad_norm": 0.13586793839931488,
+      "learning_rate": 0.0001998867339183008,
+      "loss": 10.366,
+      "step": 21
+    },
+    {
+      "epoch": 0.8402625820568927,
+      "grad_norm": 0.18823161721229553,
+      "learning_rate": 0.00019819286972627066,
+      "loss": 10.3635,
+      "step": 24
+    },
+    {
+      "epoch": 0.8402625820568927,
+      "eval_loss": 10.358380317687988,
+      "eval_runtime": 0.7207,
+      "eval_samples_per_second": 134.583,
+      "eval_steps_per_second": 67.985,
+      "step": 24
     }
   ],
   "logging_steps": 3,
@@ -85,7 +114,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6856254554112.0,
+  "total_flos": 10291064340480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null