Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60ef1cdd5f1be94c2e3f8eb4e579675d7bfbd7ffd643c4438b803f2dd046ddae
+oid sha256:73774fe393a3853cd56fea5b547c17ec8c14b2a8ee65b41b52166c5d5d9f229f
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dd428a7fd0d68e315750e3ff8f87daeeaf310f9b46db7b1a5f61122a024b078
+oid sha256:f5516f57bbe2e9aef508500fcba56342789be439bb63c5620fb9c7210b188b3a
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f9d63457fb0762bec521007b4b65dfde2dbfedf3cf13f579982482514a7d902
+oid sha256:094837089fa2ed1c4f9dc6c25bac04422ed41c22630725ca5cdf86ffa65f03cf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
+oid sha256:8bdda546a1390be3b85a90dd4ef31050dfb7b691765ffc12ed691b6786ed6e3d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00016021682677223176,
+  "epoch": 0.00024032524015834764,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 4.22,
       "eval_steps_per_second": 4.22,
       "step": 6
+    },
+    {
+      "epoch": 0.00018691963123427038,
+      "grad_norm": 9.651495933532715,
+      "learning_rate": 0.0001,
+      "loss": 3.8852,
+      "step": 7
+    },
+    {
+      "epoch": 0.000213622435696309,
+      "grad_norm": 8.860259056091309,
+      "learning_rate": 0.00012,
+      "loss": 3.537,
+      "step": 8
+    },
+    {
+      "epoch": 0.00024032524015834764,
+      "grad_norm": 7.234774112701416,
+      "learning_rate": 0.00014,
+      "loss": 2.4743,
+      "step": 9
+    },
+    {
+      "epoch": 0.00024032524015834764,
+      "eval_loss": 2.026648759841919,
+      "eval_runtime": 1650.4991,
+      "eval_samples_per_second": 4.777,
+      "eval_steps_per_second": 4.777,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4451323701362688.0,
+  "total_flos": 6676985552044032.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null