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:b0ae931074b4cdc10e681e6408db864afb290581680cbf43fd0988a6d0a41a21
+oid sha256:41b1e8935eeb71a8e2ef09959e8a18d5f45d0a0eba868e3b51eaf6b64b11e4a4
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5f006cdf53c378022fae3ac04c2bd0706fa84ab0842c79cdf71bcab368a5f65
+oid sha256:fb8ee3d5d1dbcbceb3473208670f18b4344dc916d09a9c1f39b9edbf45b17e25
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e2355e43fd44f1d9860c59f45b4d1039afaad0a42f79d076c0667863cd27cb0
+oid sha256:73aa535a34327d8ff7e12fc9f716f24d876cbdb9f9fc9bc13d972c1b7c68dd32
 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": 0.0024650780608052587,
+  "epoch": 0.0049301561216105174,
   "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": 28.147,
       "eval_steps_per_second": 14.101,
       "step": 3
+    },
+    {
+      "epoch": 0.003286770747740345,
+      "grad_norm": 5.882843017578125,
+      "learning_rate": 8e-05,
+      "loss": 13.6395,
+      "step": 4
+    },
+    {
+      "epoch": 0.004108463434675432,
+      "grad_norm": 7.812251567840576,
+      "learning_rate": 0.0001,
+      "loss": 14.5091,
+      "step": 5
+    },
+    {
+      "epoch": 0.0049301561216105174,
+      "grad_norm": 9.07049560546875,
+      "learning_rate": 0.00012,
+      "loss": 12.8213,
+      "step": 6
+    },
+    {
+      "epoch": 0.0049301561216105174,
+      "eval_loss": 3.0105860233306885,
+      "eval_runtime": 18.4472,
+      "eval_samples_per_second": 27.809,
+      "eval_steps_per_second": 13.932,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 488619940773888.0,
+  "total_flos": 977239881547776.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null