Training in progress, step 3760, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70fc65989648f7dc64734e8244e0e6879cfab6125b857d5586fade7a4f45ce0c
+oid sha256:d2eb339fca1743ce5981d75d94271aea8c49805aa8787cc062a2e480f02e91a8
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5f3e74dabdaf3ee4c5231da9311a563abc6cfd59391a593a38304bcd6053332
+oid sha256:819c50564431ec790e5c787d93b2db9cabbb70df63553d50a801172070601bd3
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98c6a86fe7a3ce61d0893ea3b91307b0a6fe853d64a359a291f505b9ac01cb7d
+oid sha256:e850e7ecc226d31ccfa0012c8cc354a952ec0a60022ef713d966322a18df683d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c2710cfbdebccda3472bd5dbf8574523b547a65e026efc1ddfdf0be454ac800
+oid sha256:c260417484aa6b4e9e662c09fdefa26287d404d4aaa654726d7eb8d7f1d0b789
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2992,
+  "epoch": 0.3008,
   "eval_steps": 500,
-  "global_step": 3740,
+  "global_step": 3760,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1316,6 +1316,13 @@
       "learning_rate": 2.8102249451758162e-05,
       "loss": 3.5619,
       "step": 3740
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 32.1122932434082,
+      "learning_rate": 2.8078528754588207e-05,
+      "loss": 3.5173,
+      "step": 3760
     }
   ],
   "logging_steps": 20,
@@ -1323,7 +1330,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 8827316538212352.0,
+  "total_flos": 8883020977766400.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null