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:cf4c29f7ca4ab4ca0ed29492d9ae946daedd37a10ac40e6c73b70a0af9082683
+oid sha256:906311f59b2d5808186516cb29795c1732b0c11557e1c906a2cd3f3297f9c050
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:750d40252e5d4a2daaed9eb91515eed822cb3226def0ceed65517884e2c7bf25
+oid sha256:bb59008d312605db7eac976453c06ac9240d390e7d48e05fe85e01a0b58b54c7
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ae0cadfe94dcf48c698c1b451b2c6352615de93dbee1916133fa523284b0d46
+oid sha256:846bd39cc273fc2a35b5e89b9652c3cc5e49916161614410ea6639542b3c3a59
 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": 0.000507292327203551,
+  "epoch": 0.001014584654407102,
   "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": 50.619,
       "eval_steps_per_second": 25.31,
       "step": 3
+    },
+    {
+      "epoch": 0.0006763897696047348,
+      "grad_norm": 8.91230297088623,
+      "learning_rate": 8e-05,
+      "loss": 4.5228,
+      "step": 4
+    },
+    {
+      "epoch": 0.0008454872120059184,
+      "grad_norm": 11.815821647644043,
+      "learning_rate": 0.0001,
+      "loss": 4.0529,
+      "step": 5
+    },
+    {
+      "epoch": 0.001014584654407102,
+      "grad_norm": 9.638334274291992,
+      "learning_rate": 0.00012,
+      "loss": 3.8741,
+      "step": 6
+    },
+    {
+      "epoch": 0.001014584654407102,
+      "eval_loss": 3.29811429977417,
+      "eval_runtime": 49.4464,
+      "eval_samples_per_second": 50.358,
+      "eval_steps_per_second": 25.179,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 28937403236352.0,
+  "total_flos": 64552668758016.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null