Training in progress, step 430, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:630cf3c2bcece4a6f38060d2903813ff7a951cedd54e2bc72b9f2607b14a70fd
+oid sha256:323ac9a990a260a6372212572d00de1c6335b120a26d670f277cf60f2eff1b49
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea13f39701c5f79159d5868ea33377233b14b510a34125092be22e18107dee32
+oid sha256:6d885aeb20a118a140eab52274619974fd5368f618e0fa5eabb38a19b8d2e51d
 size 85723732

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d3301910976c38e17fe4c27ae989f885599778135e1335beb8e8e72e5c10e3c
+oid sha256:027ab1e02da1e657cb0e6e7794fa85bd909800b97027112d2b1f64c0e103d497
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af347bd6e9a64e9d103a4bd43a4757792a255b273b942d70aeddb5b7a243efa6
+oid sha256:87bfdda30185873c0a9cb229d25fc230d1146196d05e81747db223517c4eafcf
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a821a31a15e8c39e25415cc4954957cfbae7d4d73e706211955c475fdac1633
+oid sha256:2cd61f66c9dd6299c5f3f99f7ceb5a152a1d64c4909020bec811205c4243a070
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bcfbc84a1d987ab5465db7241354afa4d4494c36e9c1879e23aee4df617417f
+oid sha256:66172525291e0f467bfc09091521e14e32a3eaaef79955a2826a4348133fc8e0
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7957f0bede386b9e7dfa8afbce84db80049c290d0482836d6c77ca519d043dd
+oid sha256:79b607b3724fadd616761069f9d370b3b216d512a0fbae133eb5c1bd8e06f7d6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9486166007905138,
+  "epoch": 0.9712027103331451,
   "eval_steps": 222,
-  "global_step": 420,
+  "global_step": 430,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2963,6 +2963,76 @@
       "learning_rate": 7.63285913778733e-07,
       "loss": 1.3479,
       "step": 420
+    },
+    {
+      "epoch": 0.950875211744777,
+      "grad_norm": 0.5345094799995422,
+      "learning_rate": 6.985077338944657e-07,
+      "loss": 1.0433,
+      "step": 421
+    },
+    {
+      "epoch": 0.9531338226990401,
+      "grad_norm": 0.5211868286132812,
+      "learning_rate": 6.365822639327723e-07,
+      "loss": 1.2699,
+      "step": 422
+    },
+    {
+      "epoch": 0.9553924336533032,
+      "grad_norm": 0.5615488290786743,
+      "learning_rate": 5.775130870590783e-07,
+      "loss": 1.3819,
+      "step": 423
+    },
+    {
+      "epoch": 0.9576510446075663,
+      "grad_norm": 0.5540674924850464,
+      "learning_rate": 5.213036211664191e-07,
+      "loss": 1.4776,
+      "step": 424
+    },
+    {
+      "epoch": 0.9599096555618295,
+      "grad_norm": 0.5452410578727722,
+      "learning_rate": 4.6795711867766436e-07,
+      "loss": 1.6834,
+      "step": 425
+    },
+    {
+      "epoch": 0.9621682665160926,
+      "grad_norm": 0.7168639898300171,
+      "learning_rate": 4.1747666635733597e-07,
+      "loss": 1.315,
+      "step": 426
+    },
+    {
+      "epoch": 0.9644268774703557,
+      "grad_norm": 0.7299930453300476,
+      "learning_rate": 3.698651851329837e-07,
+      "loss": 1.4835,
+      "step": 427
+    },
+    {
+      "epoch": 0.9666854884246189,
+      "grad_norm": 0.5021476745605469,
+      "learning_rate": 3.251254299261874e-07,
+      "loss": 1.6941,
+      "step": 428
+    },
+    {
+      "epoch": 0.968944099378882,
+      "grad_norm": 0.707979679107666,
+      "learning_rate": 2.8325998949314536e-07,
+      "loss": 1.5867,
+      "step": 429
+    },
+    {
+      "epoch": 0.9712027103331451,
+      "grad_norm": 0.4714038372039795,
+      "learning_rate": 2.442712862748775e-07,
+      "loss": 1.7911,
+      "step": 430
     }
   ],
   "logging_steps": 1,
@@ -2982,7 +3052,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.4934831596440125e+18,
+  "total_flos": 2.5528341423288484e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null