Training in progress, step 740, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c45456e15b715e832578812b0fb91f6d12ecbc982f37418d06778355c669ff0
+oid sha256:93877343ea984708c8af481d54c2f5a0b9248716e6346a610a5bf2c64939afa3
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c738e308e224171798b402d3a6ac45b253baab98b34c3df38c3ff42425b504b
+oid sha256:aba4b47b873917e65e1dcd70fc152cd2fa3b4ae149939091ba1ea672deb45b8c
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eeda755d8af1c86d4b713bb10ccad9341acf16a71464d9a966bcdbb17ea7bbc4
+oid sha256:851ed93799cb32c5bf12579542d6ae235fd7da0397d0d1a1bdf4b1c7ca570694
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b25c4cabb03cb09a4b2b9dff8deb04b1e269253acadef5d021452c833fa5d68c
+oid sha256:88feb8ebc7f4549d83b92c55b967a59a28e0a740df4fcaf7861caaa488246086
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0576,
+  "epoch": 0.0592,
   "eval_steps": 500,
-  "global_step": 720,
+  "global_step": 740,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -259,6 +259,13 @@
       "learning_rate": 2.999716791440959e-05,
       "loss": 3.679,
       "step": 720
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 36.432350158691406,
+      "learning_rate": 2.9996145260639812e-05,
+      "loss": 3.6796,
+      "step": 740
     }
   ],
   "logging_steps": 20,
@@ -266,7 +273,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1713780872970240.0,
+  "total_flos": 1767484151857152.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null