Training in progress, step 940, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:824b0482f65c54d780bf8cab1640646068f4412a35e93bf84312042275c949aa
+oid sha256:ca9ff2623ebc59ce1f05948fb7f333347562f31720ea83bd9c654d07132bc456
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd7608b89dafbdc3e9ff64304083584d3644129f923c4a985f1eb00d503b9fd9
+oid sha256:5979893651a6ad117a2ca79acc918df76f51b5615316af74b15fc3790d5db672
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a88d647ecb4240893f5936ba5eb3da134925ec105812fc12c4afbef4944427f9
+oid sha256:175dfe02b8f41adb5d4468faa982ed5a51b1c1cd012483cfc61f70c9241471b4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:799790dec230733f2507fb25ac7c0f3b89a16d8c9935acbdd39b641fa24a7e12
+oid sha256:6f1c7c4b3a6117ae282f791966d823034e6914b8063785569ba52a491b2ee826
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0736,
+  "epoch": 0.0752,
   "eval_steps": 500,
-  "global_step": 920,
+  "global_step": 940,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -329,6 +329,13 @@
       "learning_rate": 2.9979864597363846e-05,
       "loss": 3.6716,
       "step": 920
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 22.791175842285156,
+      "learning_rate": 2.9977269673842554e-05,
+      "loss": 3.6172,
+      "step": 940
     }
   ],
   "logging_steps": 20,
@@ -336,7 +343,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 2178771877822464.0,
+  "total_flos": 2230933278818304.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null