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:efc27377460a604f7a1e97c22ae0a56d43b098fdfd326673d140e755f3bf78e0
+oid sha256:1c23d5ff48b7154fd37cd789d23a5e4cd540d2dcbcd9aa45dacf35b0c357318b
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71b4a6cf3e37b2ea1ff7dd9491477b78db1ff086c3d6ffd6db275b7be395a810
+oid sha256:c7a7ef63d8aff9c4ad47aee11109db0fda985304aeab4ae63ea4cb168d11737c
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5521b625944d72e89a1dbbd007a1eff43f44cc830dcbe937891ddc3c5defd65b
+oid sha256:05531349f6e2487143a7251afc8a645033108171aa1d481234785012b46d00ef
 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": 0.005934718100890208,
+  "epoch": 0.011869436201780416,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -36,6 +36,35 @@
       "eval_samples_per_second": 17.657,
       "eval_steps_per_second": 8.87,
       "step": 3
+    },
+    {
+      "epoch": 0.00791295746785361,
+      "grad_norm": 1.8003789186477661,
+      "learning_rate": 8e-05,
+      "loss": 3.35,
+      "step": 4
+    },
+    {
+      "epoch": 0.009891196834817012,
+      "grad_norm": 1.578134298324585,
+      "learning_rate": 0.0001,
+      "loss": 3.1165,
+      "step": 5
+    },
+    {
+      "epoch": 0.011869436201780416,
+      "grad_norm": 1.6146352291107178,
+      "learning_rate": 0.00012,
+      "loss": 3.1276,
+      "step": 6
+    },
+    {
+      "epoch": 0.011869436201780416,
+      "eval_loss": 3.161781072616577,
+      "eval_runtime": 14.4687,
+      "eval_samples_per_second": 14.721,
+      "eval_steps_per_second": 7.395,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -55,7 +84,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 554869274443776.0,
+  "total_flos": 1109738548887552.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null