Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcd66902054a93e8e0d714260f2f2075546de0d24e2a40f74a9cc256211f182a
+oid sha256:e9ea66dd4489f55c292edd6ab8d9352d70360f9ad5a4ceab786a717ee5fd7974
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c463401ffa91e44167009cab353d2f77a0606563274e968235352e5ed588f26
+oid sha256:0aeca6749dd845c34cfa3cdf59a1bc387ddede928591cc424678f55715fb2f2f
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d11172069d3809e4b1d435d13824f7b7bfef9c55e762daff1ad8efa9119dcca
+oid sha256:d1bf24cd4bf25e308928bff2034c8266e5fe111aaec9b6d5c14e665ac843e0bc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16178af669793c21eac8710459f1cc10bcf09af1984c5f2d80e76b26b329c8ba
+oid sha256:67680b8b35ea230d53acee387012f8809825a2c511bd41340f42320f849e349d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0024451372333272204,
+  "epoch": 0.004890274466654441,
   "eval_steps": 34,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -50,6 +50,41 @@
       "learning_rate": 3.3333333333333335e-05,
       "loss": 1.1686,
       "step": 5
+    },
+    {
+      "epoch": 0.0029341646799926646,
+      "grad_norm": 0.44767728447914124,
+      "learning_rate": 4e-05,
+      "loss": 1.2578,
+      "step": 6
+    },
+    {
+      "epoch": 0.0034231921266581087,
+      "grad_norm": 0.4529785215854645,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 1.2452,
+      "step": 7
+    },
+    {
+      "epoch": 0.0039122195733235525,
+      "grad_norm": 0.6146576404571533,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 1.5423,
+      "step": 8
+    },
+    {
+      "epoch": 0.004401247019988997,
+      "grad_norm": 0.42456191778182983,
+      "learning_rate": 6e-05,
+      "loss": 1.1323,
+      "step": 9
+    },
+    {
+      "epoch": 0.004890274466654441,
+      "grad_norm": 0.4658707082271576,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 1.2595,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -69,7 +104,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.219477097775104e+16,
+  "total_flos": 4.438954195550208e+16,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null