Training in progress, step 440, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:323ac9a990a260a6372212572d00de1c6335b120a26d670f277cf60f2eff1b49
+oid sha256:ae1251f05ef70724f2a5bd541621a60fbc4213fb961de0bb1cb6893899908ba9
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d885aeb20a118a140eab52274619974fd5368f618e0fa5eabb38a19b8d2e51d
+oid sha256:8802ed5407d8a8f2dac66a8b4608afa77de6a43e7ff92e2511b5faa6783d07c1
 size 85723732

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:027ab1e02da1e657cb0e6e7794fa85bd909800b97027112d2b1f64c0e103d497
+oid sha256:2cca9f96c96b922acaa204e7459a265396d5e1c98f1f296f230d8e331885b8ac
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87bfdda30185873c0a9cb229d25fc230d1146196d05e81747db223517c4eafcf
+oid sha256:62fb05d1751019ac24743a26e17e60ff4857e4af1f72362a4b410a6c8410a65b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cd61f66c9dd6299c5f3f99f7ceb5a152a1d64c4909020bec811205c4243a070
+oid sha256:54547a23ea029fe03b5f58871d4527a748e7ac8f837926dd1a6e08b721fbdc33
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66172525291e0f467bfc09091521e14e32a3eaaef79955a2826a4348133fc8e0
+oid sha256:bef39a40db1a483262af7570836839950da73fbe882edbfe93922ade4768db34
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79b607b3724fadd616761069f9d370b3b216d512a0fbae133eb5c1bd8e06f7d6
+oid sha256:8323834fccc4192732a390e4554f47c9681faaee6040082de0c2920fe02fd450
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9712027103331451,
+  "epoch": 0.9937888198757764,
   "eval_steps": 222,
-  "global_step": 430,
+  "global_step": 440,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3033,6 +3033,76 @@
       "learning_rate": 2.442712862748775e-07,
       "loss": 1.7911,
       "step": 430
+    },
+    {
+      "epoch": 0.9734613212874083,
+      "grad_norm": 0.6894488334655762,
+      "learning_rate": 2.0816157625706545e-07,
+      "loss": 1.3292,
+      "step": 431
+    },
+    {
+      "epoch": 0.9757199322416714,
+      "grad_norm": 0.5745245814323425,
+      "learning_rate": 1.749329488395124e-07,
+      "loss": 1.6429,
+      "step": 432
+    },
+    {
+      "epoch": 0.9779785431959345,
+      "grad_norm": 0.41620776057243347,
+      "learning_rate": 1.4458732671523977e-07,
+      "loss": 1.2864,
+      "step": 433
+    },
+    {
+      "epoch": 0.9802371541501976,
+      "grad_norm": 0.6913926005363464,
+      "learning_rate": 1.1712646575922637e-07,
+      "loss": 1.3542,
+      "step": 434
+    },
+    {
+      "epoch": 0.9824957651044608,
+      "grad_norm": 0.47786515951156616,
+      "learning_rate": 9.255195492685609e-08,
+      "loss": 1.4777,
+      "step": 435
+    },
+    {
+      "epoch": 0.9847543760587238,
+      "grad_norm": 0.6354619860649109,
+      "learning_rate": 7.086521616190279e-08,
+      "loss": 1.448,
+      "step": 436
+    },
+    {
+      "epoch": 0.987012987012987,
+      "grad_norm": 1.0017420053482056,
+      "learning_rate": 5.2067504314323723e-08,
+      "loss": 1.2179,
+      "step": 437
+    },
+    {
+      "epoch": 0.9892715979672502,
+      "grad_norm": 0.48319703340530396,
+      "learning_rate": 3.6159907067601085e-08,
+      "loss": 1.3664,
+      "step": 438
+    },
+    {
+      "epoch": 0.9915302089215132,
+      "grad_norm": 0.642812192440033,
+      "learning_rate": 2.3143344875831142e-08,
+      "loss": 1.3237,
+      "step": 439
+    },
+    {
+      "epoch": 0.9937888198757764,
+      "grad_norm": 0.5053473114967346,
+      "learning_rate": 1.3018570910466877e-08,
+      "loss": 1.1963,
+      "step": 440
     }
   ],
   "logging_steps": 1,
@@ -3052,7 +3122,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.5528341423288484e+18,
+  "total_flos": 2.6129270118945915e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null