Training in progress, step 5000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8136d419b8890434688f361ff9055f226cad86b60136d37a16ab511ecdb95732
+oid sha256:d3898deded357ae3f624f6da11d5a240cdabb03ebb6c20aaa1514ff2afc28f42
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ae7ca943292c1885fd2fa8fc4a0d7048e58e847fa6978c2dee6a1669f1d7daf
+oid sha256:8b6589201aabf4474a11e89f074f30710b9c14f130975414126d44fac37ab285
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:450d4161861142b0c607b082cb7975db64bce31f3c9c4ed471faa6a87cc3c651
+oid sha256:6c2a46d21812f033b59f8253d10c55fd001488b63093ce2c9a28dd3b2087601c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf6116349e1acbc51c06feeb07eabf38596d13779c8b6455b06cf034d85b895b
+oid sha256:dadb6c8212cca45778812f2e418e14e8bb1e227cbf578c8c3f0b8b32adfef7b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003569582693473241,
+  "epoch": 0.0037183153057012927,
   "eval_steps": 2000,
-  "global_step": 4800,
+  "global_step": 5000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -175,6 +175,13 @@
       "learning_rate": 1.9999974953119e-05,
       "loss": 1.597,
       "step": 4800
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 2.4163918495178223,
+      "learning_rate": 1.999997281785647e-05,
+      "loss": 1.5405,
+      "step": 5000
     }
   ],
   "logging_steps": 200,
@@ -182,7 +189,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 6.297651302741606e+16,
+  "total_flos": 6.541947938699674e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null