Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c50c13655efd613a9f05f2649c2a474b992764c33872233579eda3b682abdac
+oid sha256:83c2d2f9df07bf70092d4bbf3900a621212aeba8157493d19d0d5ef5df5818e7
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49caf904ddd908b20f90917129deada971bab67c5918be30d0d3a1812c138e2a
+oid sha256:0279b77f7a65875e4b978c93ebbd2e9fe76fd0ea874d793d6f5f905ae000bccd
 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": 3.997388372929686e-05,
+  "epoch": 7.994776745859372e-05,
   "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": 32.171,
       "eval_steps_per_second": 16.086,
       "step": 3
+    },
+    {
+      "epoch": 5.329851163906248e-05,
+      "grad_norm": 6.9697370529174805,
+      "learning_rate": 8e-05,
+      "loss": 9.4804,
+      "step": 4
+    },
+    {
+      "epoch": 6.66231395488281e-05,
+      "grad_norm": 6.502429008483887,
+      "learning_rate": 0.0001,
+      "loss": 10.7664,
+      "step": 5
+    },
+    {
+      "epoch": 7.994776745859372e-05,
+      "grad_norm": 8.073918342590332,
+      "learning_rate": 0.00012,
+      "loss": 10.8971,
+      "step": 6
+    },
+    {
+      "epoch": 7.994776745859372e-05,
+      "eval_loss": 10.742100715637207,
+      "eval_runtime": 981.7601,
+      "eval_samples_per_second": 32.187,
+      "eval_steps_per_second": 16.094,
+      "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