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:e4c397e1dacf79381e26a65cc252df9419e18dc4d2dfac68b849284b2d5629b5
+oid sha256:4d3ba5086ce4b071bc0e61258fede3cb675f908fdf0b227c570164f76257ba4f
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5a9d8b58b514e90931d13ff31b0472dbd611be2e02642408d0b6442565c37c4
+oid sha256:2d55cd2522d2b55926e75d9c47359b6dd3a0981ef04edae59d4eb16e3c59d1bf
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d93d600975602b7dc557ea6bf2be1af32b3a49c58755d50746f1058367b602f
+oid sha256:d68d2a8ec68d97e9f6781386cdc5d11673589bf128caf93d024b660045d53f99
 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": 0.0016029922522041143,
+  "epoch": 0.0032059845044082286,
   "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": 17.741,
       "eval_steps_per_second": 8.871,
       "step": 3
+    },
+    {
+      "epoch": 0.0021373230029388193,
+      "grad_norm": 2.0583109855651855,
+      "learning_rate": 8e-05,
+      "loss": 4.3992,
+      "step": 4
+    },
+    {
+      "epoch": 0.0026716537536735237,
+      "grad_norm": 3.2414333820343018,
+      "learning_rate": 0.0001,
+      "loss": 5.074,
+      "step": 5
+    },
+    {
+      "epoch": 0.0032059845044082286,
+      "grad_norm": 2.703151226043701,
+      "learning_rate": 0.00012,
+      "loss": 4.2035,
+      "step": 6
+    },
+    {
+      "epoch": 0.0032059845044082286,
+      "eval_loss": 1.16398286819458,
+      "eval_runtime": 49.8632,
+      "eval_samples_per_second": 15.803,
+      "eval_steps_per_second": 7.902,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 977239881547776.0,
+  "total_flos": 1954479763095552.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null