Training in progress, step 336, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac8066d8618fb64be2b7faf41fa7b3d7fddf6534795172bb25bde20b59e6c4ff
+oid sha256:edce236ed9d28437ecbd25f57fa405e7811548ad06d25e7ee2e03e35cae474e7
 size 93608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e0e88d1e758b2d942c5d8dfb1b4aeae98139e8b2d7ef5f9e51eb4f00514fef3
+oid sha256:ecbd8daf8d8f6dadeaaf1894e705edcf7b4cb93a2fe07927e49405c98edc3627
 size 197158

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e958b5311b12f031b567f23b298951420ae35c9252f43db99115fccddb611c82
+oid sha256:585086fc4d882c3b00033d27af061feb3e3aba0472ded903abd7a66ec1908052
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:168cc6d91836120c82b575ebf5734abdb841b4263d9f2f41a03d08fad1f896b4
+oid sha256:06715ba1620389ca0b4addc4d3a5d2e99d004e57928b3fd13d4028448769c87c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:405794cde8faebc39bd31ecef58d05da57c890cf01b9aa621202411aa70597e3
+oid sha256:968865e3b0ca4449ed9a6d127f5f982867a1e9d962247cd559315d44137c3980
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa89b254c849b8c89c11fda2f7202c45b30deae097716d903b96cad962e9a032
+oid sha256:4861407560531aa131144dfce65910431552a00481de242fe5bff99a269dba47
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:318b114b83c26bcba11815378a88e0015bce044b0002c702e0a2627e1a1d1e56
+oid sha256:10affc9ced28dcfaf0d40e3497a97c8e7416bd057324538f99a7e1756fd84408
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.768125408229915,
+  "epoch": 0.8778576094056172,
   "eval_steps": 42,
-  "global_step": 294,
+  "global_step": 336,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -757,6 +757,112 @@
       "eval_samples_per_second": 775.653,
       "eval_steps_per_second": 24.371,
       "step": 294
+    },
+    {
+      "epoch": 0.7759634225996082,
+      "grad_norm": 0.03046645224094391,
+      "learning_rate": 3.6698157721666246e-05,
+      "loss": 11.917,
+      "step": 297
+    },
+    {
+      "epoch": 0.7838014369693012,
+      "grad_norm": 0.022532852366566658,
+      "learning_rate": 3.5773620668448384e-05,
+      "loss": 11.9169,
+      "step": 300
+    },
+    {
+      "epoch": 0.7916394513389942,
+      "grad_norm": 0.019215036183595657,
+      "learning_rate": 3.48543465876014e-05,
+      "loss": 11.9183,
+      "step": 303
+    },
+    {
+      "epoch": 0.7994774657086872,
+      "grad_norm": 0.02424040250480175,
+      "learning_rate": 3.3940675559617724e-05,
+      "loss": 11.9171,
+      "step": 306
+    },
+    {
+      "epoch": 0.8073154800783802,
+      "grad_norm": 0.013650625012814999,
+      "learning_rate": 3.303294559217063e-05,
+      "loss": 11.9176,
+      "step": 309
+    },
+    {
+      "epoch": 0.8151534944480732,
+      "grad_norm": 0.01347661204636097,
+      "learning_rate": 3.213149249506997e-05,
+      "loss": 11.9171,
+      "step": 312
+    },
+    {
+      "epoch": 0.8229915088177662,
+      "grad_norm": 0.02356456220149994,
+      "learning_rate": 3.12366497560313e-05,
+      "loss": 11.9175,
+      "step": 315
+    },
+    {
+      "epoch": 0.8308295231874592,
+      "grad_norm": 0.01948046311736107,
+      "learning_rate": 3.0348748417303823e-05,
+      "loss": 11.918,
+      "step": 318
+    },
+    {
+      "epoch": 0.8386675375571522,
+      "grad_norm": 0.015809211879968643,
+      "learning_rate": 2.9468116953203107e-05,
+      "loss": 11.9178,
+      "step": 321
+    },
+    {
+      "epoch": 0.8465055519268452,
+      "grad_norm": 0.01481384877115488,
+      "learning_rate": 2.8595081148593738e-05,
+      "loss": 11.9178,
+      "step": 324
+    },
+    {
+      "epoch": 0.8543435662965382,
+      "grad_norm": 0.02252669259905815,
+      "learning_rate": 2.772996397836704e-05,
+      "loss": 11.9174,
+      "step": 327
+    },
+    {
+      "epoch": 0.8621815806662312,
+      "grad_norm": 0.017606221139431,
+      "learning_rate": 2.687308548795825e-05,
+      "loss": 11.9176,
+      "step": 330
+    },
+    {
+      "epoch": 0.8700195950359242,
+      "grad_norm": 0.024705080315470695,
+      "learning_rate": 2.6024762674947313e-05,
+      "loss": 11.9166,
+      "step": 333
+    },
+    {
+      "epoch": 0.8778576094056172,
+      "grad_norm": 0.024166177958250046,
+      "learning_rate": 2.5185309371787513e-05,
+      "loss": 11.9176,
+      "step": 336
+    },
+    {
+      "epoch": 0.8778576094056172,
+      "eval_loss": 11.916953086853027,
+      "eval_runtime": 3.3243,
+      "eval_samples_per_second": 775.492,
+      "eval_steps_per_second": 24.366,
+      "step": 336
     }
   ],
   "logging_steps": 3,
@@ -776,7 +882,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5671704330240.0,
+  "total_flos": 6481603461120.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null