Training in progress, step 140, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27c29bc43948c63a0f226cc87ab0660cea4ab6cd6ae33f4b3a1386449f13e33c
+oid sha256:0e959f2bedd4d1c06f7560c91048e25cb09d9cd0bf6f1c8ec525e1b2a50b2be5
 size 4725640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac748cfb6f2f2d9146a22f9e90943f89a69ac611b4ace36f0cd0825509a80ec0
+oid sha256:7ea726ba9fc9c9eb1066b46bde05b501eb2ebeaedc9625cd740c2148848db790
 size 2423738

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd836bde9e7de00360c353ed3595fa24ed6d63347354818295fc73e9837134fc
+oid sha256:840146a001ff48fd14f9176d2551e18a68e4936bbf1b797f6c21c89adb36c9a6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6977daaeb422e8aea5fd23309b89c0087d980bd2e3b8f44821aa562f12801c8d
+oid sha256:7d82c151815973da3ac2e374434a38a206899c333d88de9e900733b7877b8460
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.339030141719783e-05,
+  "epoch": 0.00010895535165339746,
   "eval_steps": 500,
-  "global_step": 120,
+  "global_step": 140,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -49,6 +49,13 @@
       "learning_rate": 1.9833333333333335e-05,
       "loss": 3.1903,
       "step": 120
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 3.08722186088562,
+      "learning_rate": 2.3166666666666666e-05,
+      "loss": 3.5379,
+      "step": 140
     }
   ],
   "logging_steps": 20,
@@ -56,7 +63,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 637410213568512.0,
+  "total_flos": 721108975951872.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null