Training in progress, step 9200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9af7b37f06d07ef70d4988ce1f6299893bace9d6a7ba0c9cd136d9ea3fd941fa
+oid sha256:c5c6ddbd467cafe220950cf580152d8dfc1bdb07232925e79788f7dd96cb33fc
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f921cb5d7c6f27660db1f17dd3595cd35f686682075ca581ae6001b538ec16f7
+oid sha256:727e3297fb3ca3decb10dfe35adb3d7cdcdeac5a3427385a8b576fe75394e384
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf5f888e89f291e2093e87569b5763db1fc85cbdf17ee5606bd0221a799e468a
+oid sha256:a29cde96a84a25696641294b8cd58e32b99c4aa9e19f850f31d8997de9906372
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aaf2bc4e5abc828d18795c4a133d46fc971f9c25b1fb81b66f19e661f16cda00
+oid sha256:9c622f42c50d23258470acf2574d6e28b534d24bb52c381f00d4152e998277d5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006692967550262327,
+  "epoch": 0.006841700162490379,
   "eval_steps": 2000,
-  "global_step": 9000,
+  "global_step": 9200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -322,6 +322,13 @@
       "learning_rate": 1.9999911792618627e-05,
       "loss": 1.5237,
       "step": 9000
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 3.4991722106933594,
+      "learning_rate": 1.9999907823833413e-05,
+      "loss": 1.5551,
+      "step": 9200
     }
   ],
   "logging_steps": 200,
@@ -329,7 +336,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 1.1786109336920064e+17,
+  "total_flos": 1.204562498630615e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null