Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca7e26554e6e5033f1f7b770adea583fc2db8cc4929fe3fcebc0a7722f56c7d3
+oid sha256:81aa585871023ed118436bbe1f86b78109808e3fa693f9ef35345e0f4414f3f0
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b418bf7c4c6f29842bcd99ac3db501a5e925844dcbdf0fa7a794de52066bd03d
+oid sha256:2aa0ca9ef890d5d7060ee9ba9a60c83169e2dd854e7049cd3a386c1c71e95f8b
 size 61926

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:424d06375131df3df5d4883391c61f995c66d877e893fd245f2c624058954297
+oid sha256:652365ff63294ffff01ffedb52e831cc2560ab06b5699bca21d63e81dd0efbe7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
+oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01703800786369594,
+  "epoch": 0.025557011795543906,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -213,6 +213,105 @@
       "eval_samples_per_second": 205.357,
       "eval_steps_per_second": 102.718,
       "step": 26
+    },
+    {
+      "epoch": 0.017693315858453473,
+      "grad_norm": 0.014943009242415428,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 11.9304,
+      "step": 27
+    },
+    {
+      "epoch": 0.01834862385321101,
+      "grad_norm": 0.02193116582930088,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 11.9322,
+      "step": 28
+    },
+    {
+      "epoch": 0.019003931847968544,
+      "grad_norm": 0.012562782503664494,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 11.9306,
+      "step": 29
+    },
+    {
+      "epoch": 0.019659239842726082,
+      "grad_norm": 0.013389959931373596,
+      "learning_rate": 5e-05,
+      "loss": 11.9316,
+      "step": 30
+    },
+    {
+      "epoch": 0.020314547837483616,
+      "grad_norm": 0.01724652200937271,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 11.9305,
+      "step": 31
+    },
+    {
+      "epoch": 0.020969855832241154,
+      "grad_norm": 0.018411165103316307,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 11.9313,
+      "step": 32
+    },
+    {
+      "epoch": 0.02162516382699869,
+      "grad_norm": 0.013785377144813538,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 11.9316,
+      "step": 33
+    },
+    {
+      "epoch": 0.022280471821756225,
+      "grad_norm": 0.018790163099765778,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 11.9323,
+      "step": 34
+    },
+    {
+      "epoch": 0.022935779816513763,
+      "grad_norm": 0.015211019665002823,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 11.9303,
+      "step": 35
+    },
+    {
+      "epoch": 0.023591087811271297,
+      "grad_norm": 0.01657300628721714,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 11.9292,
+      "step": 36
+    },
+    {
+      "epoch": 0.024246395806028834,
+      "grad_norm": 0.01142768282443285,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 11.9314,
+      "step": 37
+    },
+    {
+      "epoch": 0.02490170380078637,
+      "grad_norm": 0.021842923015356064,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 11.9316,
+      "step": 38
+    },
+    {
+      "epoch": 0.025557011795543906,
+      "grad_norm": 0.019510934129357338,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 11.9325,
+      "step": 39
+    },
+    {
+      "epoch": 0.025557011795543906,
+      "eval_loss": 11.930744171142578,
+      "eval_runtime": 12.5232,
+      "eval_samples_per_second": 205.298,
+      "eval_steps_per_second": 102.689,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 155889696768.0,
+  "total_flos": 233834545152.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null