Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb4bdb455780f640f1732f6f42fbf472be01ef489b7bb3ff255da3581715a6b7
+oid sha256:f11d35ac3eaf8a4a3e7440183fca25b4732d174ee206dc800eea3f18343a83b3
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:043ac2b5ed7d3c7585ab012f706531abd8f0fa3042f9db6d78664f6f78440f4f
+oid sha256:b8f91301a897fb6c46a697999e93d02dca95b1a5bd7135c5fd37ae8fec052d82
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c54b1263e33f4122f1c769808e699b240af8adf0df9054b3e4eff55c7874f1b1
+oid sha256:1c7e8c0f7bb988751ccd9907b573ddb354edc6c4d1478341caae7f6c4a40c442
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:621519582414cbcc961b30cff113e8b1e10923f26e46ef8e0ad7c29a35554318
+oid sha256:d403ac4d7711325e0c8bec676128002b741c5058ffa34f8bfc8e7d7e4547c436
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.021636240703177823,
+  "epoch": 0.043272481406355645,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 8.955,
       "eval_steps_per_second": 4.478,
       "step": 9
+    },
+    {
+      "epoch": 0.02884832093757043,
+      "grad_norm": 1.1980935335159302,
+      "learning_rate": 0.00012,
+      "loss": 1.7996,
+      "step": 12
+    },
+    {
+      "epoch": 0.03606040117196304,
+      "grad_norm": 0.9815410375595093,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.6674,
+      "step": 15
+    },
+    {
+      "epoch": 0.043272481406355645,
+      "grad_norm": 1.1842740774154663,
+      "learning_rate": 0.00018,
+      "loss": 1.5861,
+      "step": 18
+    },
+    {
+      "epoch": 0.043272481406355645,
+      "eval_loss": 1.4581845998764038,
+      "eval_runtime": 156.5288,
+      "eval_samples_per_second": 8.957,
+      "eval_steps_per_second": 4.478,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.371275255585178e+16,
+  "total_flos": 1.0742550511170355e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null