Training in progress, step 4, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a04904412e2b2ea1fb21b7ca89ee1bd5cabeefc178e4cfe6a14adba304641b7
+oid sha256:d0377084e920f882898468f770bcee66dfdcf59151bbac0fc9fae511d61793e7
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45e5e6bcfe3344e7e2c67970898cd86f60234f5ed4c54234ea0b4075166f7af0
+oid sha256:9bf11e88e41e1cf1051bb0adcd26238baf798b4a205fac560a371d4d3914468a
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ff1a5a76862bbee56a9275ee6a5621dff6f0928cd044fcf7d46b0f5941256ac
+oid sha256:b8d6b9a0e9e9502751def1097143074ef257eab24506a0f12d159e188fa21987
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60f8f27a9d76e31d3721bb37f2f4c76e866b8dedf8d4315f175dac906a4a966d
+oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00019259125515332069,
+  "epoch": 0.00038518251030664137,
   "eval_steps": 2,
-  "global_step": 2,
+  "global_step": 4,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,28 @@
       "eval_samples_per_second": 17.535,
       "eval_steps_per_second": 8.767,
       "step": 2
+    },
+    {
+      "epoch": 0.00028888688272998104,
+      "grad_norm": 0.4915663003921509,
+      "learning_rate": 3e-05,
+      "loss": 0.8137,
+      "step": 3
+    },
+    {
+      "epoch": 0.00038518251030664137,
+      "grad_norm": 0.47559481859207153,
+      "learning_rate": 4e-05,
+      "loss": 0.8081,
+      "step": 4
+    },
+    {
+      "epoch": 0.00038518251030664137,
+      "eval_loss": 0.9481819868087769,
+      "eval_runtime": 996.2168,
+      "eval_samples_per_second": 17.556,
+      "eval_steps_per_second": 8.778,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3232519947288576.0,
+  "total_flos": 6465039894577152.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null