Training in progress, step 84, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a99d7f78b52249edf20c469f94fc92ba5405045f0b5bc6e8e3543f596bd9e262
+oid sha256:6294a9c9e421f26623f265d84c6b0618f883b9dd25deaca3c936e180cf07b24a
 size 93608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cac5d499230328f37d4ad412974ff703be657f6ac116459f445ebdebf9da4dbb
+oid sha256:e409bc2980559f98a0af9f1edbb4380dbf4021ebd0edbd6c8b2fb477f751ac94
 size 197158

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae29d58bf16735e2c97267cb1326c98535254440147a30c5f5efe8de40f5e1fc
+oid sha256:c5f286750a54eebdcf9549d6f63e6795fc731915bf6f7bf2b726b55b05f3f518
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a197cfd1ce30962a84a7f8b697f185f025e04f0dc3bfe78948ee2b4e26af0ada
+oid sha256:02fd229e57eac985f512ac99036360caf9e39dc610ee15dd6c9283a1b6c69b19
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd0b8bdc8b67a86cb8e5c48639a0fac513310f210e64cb481b087fc5447f70ed
+oid sha256:9db29deadf6ae74444d5e6208837d81f47dde9b75671d98526f2bf5be704e381
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:880ad6f59fd9b56e4d56f20bb5bb2d15b1c35ef6925bfadf1f6aa9fc59fb7126
+oid sha256:840bfe1128fcfee1e64ffedd09794dc200894ff330da30892753d28eb72056a6
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d24225e147d7b9425c760fd15a44cb007389a8d29dfe49f25bc43f19fd631f65
+oid sha256:2df224011d0e75c4a97901f6c1b2930bba4bc3a9aa7c877e6c91e796bec6013f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.10973220117570215,
+  "epoch": 0.2194644023514043,
   "eval_steps": 42,
-  "global_step": 42,
+  "global_step": 84,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -121,6 +121,112 @@
       "eval_samples_per_second": 774.195,
       "eval_steps_per_second": 24.325,
       "step": 42
+    },
+    {
+      "epoch": 0.11757021554539517,
+      "grad_norm": 0.03980684280395508,
+      "learning_rate": 9.874639560909117e-05,
+      "loss": 11.923,
+      "step": 45
+    },
+    {
+      "epoch": 0.12540822991508818,
+      "grad_norm": 0.030828900635242462,
+      "learning_rate": 9.852339101019574e-05,
+      "loss": 11.9232,
+      "step": 48
+    },
+    {
+      "epoch": 0.13324624428478118,
+      "grad_norm": 0.033988162875175476,
+      "learning_rate": 9.828243544427796e-05,
+      "loss": 11.922,
+      "step": 51
+    },
+    {
+      "epoch": 0.1410842586544742,
+      "grad_norm": 0.03058473765850067,
+      "learning_rate": 9.802361805155097e-05,
+      "loss": 11.9221,
+      "step": 54
+    },
+    {
+      "epoch": 0.14892227302416722,
+      "grad_norm": 0.02629922330379486,
+      "learning_rate": 9.774703458011453e-05,
+      "loss": 11.9221,
+      "step": 57
+    },
+    {
+      "epoch": 0.15676028739386022,
+      "grad_norm": 0.029390348121523857,
+      "learning_rate": 9.745278735053343e-05,
+      "loss": 11.9205,
+      "step": 60
+    },
+    {
+      "epoch": 0.16459830176355322,
+      "grad_norm": 0.02337743528187275,
+      "learning_rate": 9.714098521798465e-05,
+      "loss": 11.9216,
+      "step": 63
+    },
+    {
+      "epoch": 0.17243631613324625,
+      "grad_norm": 0.017651265487074852,
+      "learning_rate": 9.681174353198687e-05,
+      "loss": 11.9212,
+      "step": 66
+    },
+    {
+      "epoch": 0.18027433050293926,
+      "grad_norm": 0.018284769728779793,
+      "learning_rate": 9.64651840937276e-05,
+      "loss": 11.921,
+      "step": 69
+    },
+    {
+      "epoch": 0.18811234487263226,
+      "grad_norm": 0.014632761478424072,
+      "learning_rate": 9.610143511100354e-05,
+      "loss": 11.9212,
+      "step": 72
+    },
+    {
+      "epoch": 0.1959503592423253,
+      "grad_norm": 0.020750127732753754,
+      "learning_rate": 9.572063115079063e-05,
+      "loss": 11.9209,
+      "step": 75
+    },
+    {
+      "epoch": 0.2037883736120183,
+      "grad_norm": 0.012179220095276833,
+      "learning_rate": 9.53229130894619e-05,
+      "loss": 11.921,
+      "step": 78
+    },
+    {
+      "epoch": 0.2116263879817113,
+      "grad_norm": 0.014039278961718082,
+      "learning_rate": 9.490842806067095e-05,
+      "loss": 11.921,
+      "step": 81
+    },
+    {
+      "epoch": 0.2194644023514043,
+      "grad_norm": 0.015738265588879585,
+      "learning_rate": 9.44773294009206e-05,
+      "loss": 11.9204,
+      "step": 84
+    },
+    {
+      "epoch": 0.2194644023514043,
+      "eval_loss": 11.920842170715332,
+      "eval_runtime": 3.3087,
+      "eval_samples_per_second": 779.15,
+      "eval_steps_per_second": 24.481,
+      "step": 84
     }
   ],
   "logging_steps": 3,
@@ -140,7 +246,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 809899130880.0,
+  "total_flos": 1619798261760.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null