Training in progress, step 3920, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0391a43e44101ba1c8646a6094f6b65cec4318f22c74e9c2ae40b34185f7cc5d
+oid sha256:ce114ed028608c33fb14ff98f4580972cd31568f223be1d22613afcf3ea6009a
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09e8ffb13099b6ec8a1019bcdb942d10f9971ad077f0de806881fa51c83496d4
+oid sha256:3dd88d5a6388bdda64ace4a78c9f1d530f455e15ff96f35abfaa2c7aeed5a0c6
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81e66deaa7a6347bec6d2635166d3c92ba13107fc8c837f587e530f8f9f6413f
+oid sha256:e22d0a49f52c6eef0f435a0352f4ad22f617645d5bf3a854028fdf06254c9f5c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17f09240eb3a2df53c686d502e0925c2a9bbb6edcd515f95977492c20f85fc70
+oid sha256:f569d1656ee5e3c0d9963834d2eb1a257ab730529da22fb07a96bbbcaee7fe67
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.312,
+  "epoch": 0.3136,
   "eval_steps": 500,
-  "global_step": 3900,
+  "global_step": 3920,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1372,6 +1372,13 @@
       "learning_rate": 2.790865673705888e-05,
       "loss": 3.4588,
       "step": 3900
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 29.236722946166992,
+      "learning_rate": 2.7883845626740046e-05,
+      "loss": 3.5286,
+      "step": 3920
     }
   ],
   "logging_steps": 20,
@@ -1379,7 +1386,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 9202648983994368.0,
+  "total_flos": 9249627050803200.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null