Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be1fb77db4247526c95c1ab58619666c1bf7faa2827e1fe6c57c720a3b728244
+oid sha256:81c66ef5ab5b8781606e28540ecf3df42f3ddd06679f37da49546b1ac02a2f98
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50bef9780a0b8e01e67d167274ac833b81280857791324c2a6c596ee660d5ff2
+oid sha256:e1e1726b63e5b9741c46cc88421acb3867aaeebc0441472927b0a2b9840d6f26
 size 148047722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06fccdcbc9936009eb2f352e0be2954b0ca27af350abe425d6a05cc38e05cef3
+oid sha256:6be021fdd8df982fc338b86ca131cb94cea4b6c7fd8feb56712e7bdd4631a3d1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.014776505356483192,
+  "epoch": 0.029553010712966385,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 0.00018,
       "loss": 2.2392,
       "step": 9
+    },
+    {
+      "epoch": 0.01773180642777983,
+      "grad_norm": 0.8991310596466064,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 2.0468,
+      "step": 12
+    },
+    {
+      "epoch": 0.02216475803472479,
+      "grad_norm": 1.0070017576217651,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 1.9515,
+      "step": 15
+    },
+    {
+      "epoch": 0.023642408570373107,
+      "eval_loss": 1.9984503984451294,
+      "eval_runtime": 6.9326,
+      "eval_samples_per_second": 41.11,
+      "eval_steps_per_second": 20.627,
+      "step": 16
+    },
+    {
+      "epoch": 0.026597709641669746,
+      "grad_norm": 1.078281044960022,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.9955,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 653134418411520.0,
+  "total_flos": 1306268836823040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null