Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65ed248e803e133d9b60d15f467cfdbf3f2cc70b9efa9a4e716838019e63b6bc
+oid sha256:47ed86c4db1c3259c50821fc2f6aba36cda977723e4f3d0da59b8e9093a6764c
 size 28348936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4a60ebe40a59f86941bd85b219f1a642195de7e4fd32c44e398aa80fa2b9f9b
+oid sha256:57d9d4fd340db071154e35b1d938984112a5e764d589a38f87be3b9b966a0460
 size 14714068

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2850b5df1e1f1b204c74e915d93cbd87d4431877c8c685ae8517a1f47e5af7b8
+oid sha256:239794f189f65bf0745ae2f09be34e81c5079b1768fc19d051489a49769828cc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.820552370419953e-05,
+  "epoch": 0.00011641104740839906,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 51.004,
       "eval_steps_per_second": 25.502,
       "step": 3
+    },
+    {
+      "epoch": 7.76073649389327e-05,
+      "grad_norm": 0.5039064288139343,
+      "learning_rate": 8e-05,
+      "loss": 0.8399,
+      "step": 4
+    },
+    {
+      "epoch": 9.700920617366589e-05,
+      "grad_norm": 0.428009957075119,
+      "learning_rate": 0.0001,
+      "loss": 1.0134,
+      "step": 5
+    },
+    {
+      "epoch": 0.00011641104740839906,
+      "grad_norm": 0.35810595750808716,
+      "learning_rate": 0.00012,
+      "loss": 0.7088,
+      "step": 6
+    },
+    {
+      "epoch": 0.00011641104740839906,
+      "eval_loss": 0.9613136649131775,
+      "eval_runtime": 426.2184,
+      "eval_samples_per_second": 50.918,
+      "eval_steps_per_second": 25.459,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 137922644803584.0,
+  "total_flos": 283958386360320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null