Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c3ea0842634f63d3b9eeda082114554349eebaa3102b50f9da04d176b3824de
+oid sha256:6d5b7f97cf00e1585267ce7f91f2ddf74da03538fe19cb79201c42cb6435d14e
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c109f90ade67b38f207eea07c743c389e86360277bcb5402c7ef3e76c8c1905
+oid sha256:a40862ced1da18c4fbea67ed6e36bca0aa2ccce45c097d0c289b2e5ba303b65e
 size 52046596

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cf48ebff1809dd3fb72fb3bc573a07a5cb9499b91ea352d39d4db9ad4f3321f
+oid sha256:6f208a1b133e23db562910dd8d62af91a871a98625f1d43795785b962555b165
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ed4d324b462d47d9d1bc6c0d98e6a2567ef6b436aadc1a2d6fa3ff783eb1767
+oid sha256:998470fa5c8115b8d249e96e18986f84612a0e6cf47a8a9cd2a28321abea763f
 size 14512

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": 0.0022030475491096016,
+  "epoch": 0.004406095098219203,
   "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": 6.701,
       "eval_steps_per_second": 1.677,
       "step": 3
+    },
+    {
+      "epoch": 0.0029373967321461355,
+      "grad_norm": 0.6414063572883606,
+      "learning_rate": 8e-05,
+      "loss": 0.5886,
+      "step": 4
+    },
+    {
+      "epoch": 0.0036717459151826694,
+      "grad_norm": 0.6509028673171997,
+      "learning_rate": 0.0001,
+      "loss": 0.5753,
+      "step": 5
+    },
+    {
+      "epoch": 0.004406095098219203,
+      "grad_norm": 0.73858243227005,
+      "learning_rate": 0.00012,
+      "loss": 0.5315,
+      "step": 6
+    },
+    {
+      "epoch": 0.004406095098219203,
+      "eval_loss": 0.4672764241695404,
+      "eval_runtime": 171.3975,
+      "eval_samples_per_second": 6.692,
+      "eval_steps_per_second": 1.674,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3951230460100608.0,
+  "total_flos": 7902460920201216.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null