Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a421c9210a67edd20774a669b2a210575be32805253393af537a38f5ec4986a
+oid sha256:628dd037aed20dc2b3a91431730c20c702f77b37976597a8c01ee28401142765
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e21fdb6f6a3f89b91a5670b8376f6fe95bd41c70b8ea38095d1dfa5949972858
+oid sha256:b1ccc07e802293dcd4f5b9086e83b35f0009160a73e7497dd112f0c4e18b165d
 size 81730196

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfcdef8a8b916b711480982f753423d6133b7c4e35e662651b9da32ca0cd379f
+oid sha256:e79f6ba8fb7ffd48989487f6e68f93db591e92af3a69e568722794c031540f83
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea18bc07366a2f238e1591e2c8ffd4355de51a0adee25da04857a678c39dc63a
+oid sha256:ecf7ec282beb1f61e959b9e912d5b9b4c3128e903769f4f35493243fd1bdc61b
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
+oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0726764500349406,
+  "epoch": 0.1453529000698812,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -114,6 +114,105 @@
       "eval_samples_per_second": 11.814,
       "eval_steps_per_second": 2.961,
       "step": 13
+    },
+    {
+      "epoch": 0.07826694619147449,
+      "grad_norm": 0.37218666076660156,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.9066,
+      "step": 14
+    },
+    {
+      "epoch": 0.08385744234800839,
+      "grad_norm": 0.41769397258758545,
+      "learning_rate": 8.296729075500344e-05,
+      "loss": 1.8943,
+      "step": 15
+    },
+    {
+      "epoch": 0.08944793850454227,
+      "grad_norm": 0.4944588541984558,
+      "learning_rate": 8.043807145043604e-05,
+      "loss": 1.8743,
+      "step": 16
+    },
+    {
+      "epoch": 0.09503843466107617,
+      "grad_norm": 0.3327654004096985,
+      "learning_rate": 7.777851165098012e-05,
+      "loss": 1.8726,
+      "step": 17
+    },
+    {
+      "epoch": 0.10062893081761007,
+      "grad_norm": 0.4804844856262207,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.8517,
+      "step": 18
+    },
+    {
+      "epoch": 0.10621942697414395,
+      "grad_norm": 0.5033496022224426,
+      "learning_rate": 7.211443451095007e-05,
+      "loss": 1.8815,
+      "step": 19
+    },
+    {
+      "epoch": 0.11180992313067785,
+      "grad_norm": 0.4059678316116333,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.8633,
+      "step": 20
+    },
+    {
+      "epoch": 0.11740041928721175,
+      "grad_norm": 0.5624929070472717,
+      "learning_rate": 6.607197326515808e-05,
+      "loss": 1.8528,
+      "step": 21
+    },
+    {
+      "epoch": 0.12299091544374563,
+      "grad_norm": 0.30437928438186646,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 1.8548,
+      "step": 22
+    },
+    {
+      "epoch": 0.12858141160027953,
+      "grad_norm": 0.4757891297340393,
+      "learning_rate": 5.9754516100806423e-05,
+      "loss": 1.8662,
+      "step": 23
+    },
+    {
+      "epoch": 0.13417190775681342,
+      "grad_norm": 0.5576551556587219,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 1.8525,
+      "step": 24
+    },
+    {
+      "epoch": 0.13976240391334732,
+      "grad_norm": 0.301616907119751,
+      "learning_rate": 5.327015646150716e-05,
+      "loss": 1.8448,
+      "step": 25
+    },
+    {
+      "epoch": 0.1453529000698812,
+      "grad_norm": 0.3822285532951355,
+      "learning_rate": 5e-05,
+      "loss": 1.841,
+      "step": 26
+    },
+    {
+      "epoch": 0.1453529000698812,
+      "eval_loss": 1.8403270244598389,
+      "eval_runtime": 101.9955,
+      "eval_samples_per_second": 11.814,
+      "eval_steps_per_second": 2.961,
+      "step": 26
     }
   ],
   "logging_steps": 1,
@@ -133,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.7184129205128397e+17,
+  "total_flos": 5.4368258410256794e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null