Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:899698ddef476d7ffb742bc22950f9f90e5fdc0da705be93de830ae07adc3ff7
+oid sha256:2e402e5eab5c23aa11f39d9972826282faed36c93846e2f7b33eed3ab04edcdf
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75308877f425feba7ebe40e5aa0c35571dec0c34493170157b0c31b2b5f77e47
+oid sha256:a619e3fb5a37cb5f92255e53eec0a3d9ffa190dea8c930fa703195a41aff1415
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6be89b2cd2a89bc9a357c462211278505e1756ffdfc78ecf89b3010a0b8981e
+oid sha256:e6bf19e75a59ee8c6a96e9c63d30b78c698cbfef05ceb7eb28dd7602d0b1a826
 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": 0.010572687224669603,
+  "epoch": 0.021145374449339206,
   "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": 32.691,
       "eval_steps_per_second": 16.345,
       "step": 3
+    },
+    {
+      "epoch": 0.014096916299559472,
+      "grad_norm": 29.646787643432617,
+      "learning_rate": 8e-05,
+      "loss": 10.0704,
+      "step": 4
+    },
+    {
+      "epoch": 0.01762114537444934,
+      "grad_norm": 32.25894546508789,
+      "learning_rate": 0.0001,
+      "loss": 7.8373,
+      "step": 5
+    },
+    {
+      "epoch": 0.021145374449339206,
+      "grad_norm": 26.04344367980957,
+      "learning_rate": 0.00012,
+      "loss": 5.4309,
+      "step": 6
+    },
+    {
+      "epoch": 0.021145374449339206,
+      "eval_loss": 3.7627370357513428,
+      "eval_runtime": 3.7381,
+      "eval_samples_per_second": 32.102,
+      "eval_steps_per_second": 16.051,
+      "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