Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edd2a62e517694ba82ba5fd318a60ccc78225d3d159fe182af63222a681c81a8
+oid sha256:b1886aca4427eb1d693e077216893332106bc683432586fa8c1db30611428e08
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7136dabe9f3a8dc23ad62f64a2edf2d16038b36e1cab6645f87cc837398ca961
+oid sha256:f6bc0e9700186ed892552a12e705b38007f9ba17a288867c5e21066177499b6a
 size 42545748

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddb152374ecc00ffd00671532ef4589ea73dfa9b4504c24cc618bbc6b573915f
+oid sha256:3136df5eb37f5f7e82df42e16e3196440d4109cbf317d9d90eeffceb8aa185ca
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c985bc45dfd59caf692fbd5c84334969cfb0e4697819c614e52df74968e1304
+oid sha256:0c0795562538be0bf7ad98ee609d0ddbfe96a9498f4818dfb41e4c4639319f7c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004,
+  "epoch": 0.008,
   "eval_steps": 1000,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -67,13 +67,73 @@
       "learning_rate": 0.00018947368421052632,
       "loss": 2.1115,
       "step": 10
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0001873684210526316,
+      "loss": 1.8284,
+      "step": 11
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00018526315789473685,
+      "loss": 2.1256,
+      "step": 12
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0001831578947368421,
+      "loss": 1.8958,
+      "step": 13
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00018105263157894739,
+      "loss": 1.8952,
+      "step": 14
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00017894736842105264,
+      "loss": 1.9093,
+      "step": 15
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0001768421052631579,
+      "loss": 1.6703,
+      "step": 16
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00017473684210526317,
+      "loss": 1.8382,
+      "step": 17
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00017263157894736842,
+      "loss": 2.6312,
+      "step": 18
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0001705263157894737,
+      "loss": 1.6544,
+      "step": 19
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00016842105263157895,
+      "loss": 2.0619,
+      "step": 20
     }
   ],
   "logging_steps": 1,
   "max_steps": 100,
   "num_train_epochs": 1,
   "save_steps": 10,
-  "total_flos": 639108298899456.0,
+  "total_flos": 1508853564260352.0,
   "trial_name": null,
   "trial_params": null
 }