Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c206b82a512d5a1db3068ce1048680b63a9ab0f082327b79015efd814e3d2a9
+oid sha256:e9f11be156356f414dd34923f20713c094208c1202abf9e98d5ec7fb79de3138
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae04534afc2ec22d379bacc5b057694903a6ffbf3dea11b959a1ffdba35d99d9
+oid sha256:33cafa734a71c5e4c4795ec6a3b8bfb4c46e21a0cfc1ce27753be79fd87927a2
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d261144361ea855362212b7f0dabe43e1421a9588798268bc613afe8fd7dd4d0
+oid sha256:b2fe91e4b71ad96971401f0069a1c0bd726c6e3d3f180c7c5724b4adc2dcccdc
 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": 0.010999083409715857,
+  "epoch": 0.021998166819431713,
   "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": 9.662,
       "eval_steps_per_second": 4.873,
       "step": 3
+    },
+    {
+      "epoch": 0.01466544454628781,
+      "grad_norm": 16.266033172607422,
+      "learning_rate": 8e-05,
+      "loss": 12.442,
+      "step": 4
+    },
+    {
+      "epoch": 0.01833180568285976,
+      "grad_norm": 14.242290496826172,
+      "learning_rate": 0.0001,
+      "loss": 9.6975,
+      "step": 5
+    },
+    {
+      "epoch": 0.021998166819431713,
+      "grad_norm": 19.96150779724121,
+      "learning_rate": 0.00012,
+      "loss": 9.8631,
+      "step": 6
+    },
+    {
+      "epoch": 0.021998166819431713,
+      "eval_loss": 8.199483871459961,
+      "eval_runtime": 12.1413,
+      "eval_samples_per_second": 9.472,
+      "eval_steps_per_second": 4.777,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 554869274443776.0,
+  "total_flos": 1109738548887552.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null