Training in progress, step 420, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3589878ef8c0ccabc0dfaf9fc1f2093bf0b9e36f86facf8e0d277a263a6fbe1
+oid sha256:630cf3c2bcece4a6f38060d2903813ff7a951cedd54e2bc72b9f2607b14a70fd
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c82faa383347f9a66cc669f03b87baec13337b2db57e610e3deb7405a5e82ad
+oid sha256:ea13f39701c5f79159d5868ea33377233b14b510a34125092be22e18107dee32
 size 85723732

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eba64919589245b61d7fdff757f934e96ccc4e53bfe4f67aa18658ed422c3f73
+oid sha256:6d3301910976c38e17fe4c27ae989f885599778135e1335beb8e8e72e5c10e3c
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9432da3919ae09332aefc4d1aaa6096141e1756766415ba5bba478d58a6c8edd
+oid sha256:af347bd6e9a64e9d103a4bd43a4757792a255b273b942d70aeddb5b7a243efa6
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0af7110163e9993572ed4e63f812642004987cdabb74edc789bc7391e1ab0f15
+oid sha256:7a821a31a15e8c39e25415cc4954957cfbae7d4d73e706211955c475fdac1633
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4174c84ac9512d0ebb0c57b6ee4e9def3943b7376106f0123b689d81dee53fc5
+oid sha256:3bcfbc84a1d987ab5465db7241354afa4d4494c36e9c1879e23aee4df617417f
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa2f50ba8ccd569e36bb5b9125e41b80ac00866bb3946942d8b5dd6a6e75f034
+oid sha256:d7957f0bede386b9e7dfa8afbce84db80049c290d0482836d6c77ca519d043dd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9260304912478825,
+  "epoch": 0.9486166007905138,
   "eval_steps": 222,
-  "global_step": 410,
+  "global_step": 420,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2893,6 +2893,76 @@
       "learning_rate": 1.567060735921344e-06,
       "loss": 1.5086,
       "step": 410
+    },
+    {
+      "epoch": 0.9282891022021457,
+      "grad_norm": 0.6804593801498413,
+      "learning_rate": 1.4739887303249877e-06,
+      "loss": 1.4831,
+      "step": 411
+    },
+    {
+      "epoch": 0.9305477131564088,
+      "grad_norm": 0.5399026274681091,
+      "learning_rate": 1.383724563345451e-06,
+      "loss": 1.6713,
+      "step": 412
+    },
+    {
+      "epoch": 0.932806324110672,
+      "grad_norm": 0.6251387596130371,
+      "learning_rate": 1.2962734578973568e-06,
+      "loss": 1.3986,
+      "step": 413
+    },
+    {
+      "epoch": 0.935064935064935,
+      "grad_norm": 0.6313952803611755,
+      "learning_rate": 1.2116404741244203e-06,
+      "loss": 1.4082,
+      "step": 414
+    },
+    {
+      "epoch": 0.9373235460191982,
+      "grad_norm": 0.5223222970962524,
+      "learning_rate": 1.1298305091066664e-06,
+      "loss": 1.3455,
+      "step": 415
+    },
+    {
+      "epoch": 0.9395821569734614,
+      "grad_norm": 0.6576501131057739,
+      "learning_rate": 1.0508482965770505e-06,
+      "loss": 1.5945,
+      "step": 416
+    },
+    {
+      "epoch": 0.9418407679277244,
+      "grad_norm": 0.5625395774841309,
+      "learning_rate": 9.746984066475729e-07,
+      "loss": 1.3081,
+      "step": 417
+    },
+    {
+      "epoch": 0.9440993788819876,
+      "grad_norm": 0.7256038188934326,
+      "learning_rate": 9.013852455448335e-07,
+      "loss": 1.2728,
+      "step": 418
+    },
+    {
+      "epoch": 0.9463579898362507,
+      "grad_norm": 0.9706465005874634,
+      "learning_rate": 8.309130553550815e-07,
+      "loss": 1.4802,
+      "step": 419
+    },
+    {
+      "epoch": 0.9486166007905138,
+      "grad_norm": 0.41532036662101746,
+      "learning_rate": 7.63285913778733e-07,
+      "loss": 1.3479,
+      "step": 420
     }
   ],
   "logging_steps": 1,
@@ -2912,7 +2982,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.4341321769591767e+18,
+  "total_flos": 2.4934831596440125e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null