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:da36c610c7afb020ca963142dde4eb5e066bdef3dffc5f5c6b47b4c628f3f328
+oid sha256:2a9724da798d93aca41571752974ece97ce653fdf94ee113c089f9565f2cc786
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:626e94483417bd1dfb0c6067f4d5306d63d9feeab1410e3bdc4c052f265d7c6f
+oid sha256:bc986c9caeb0c517ddfe515ca0ec0fab07bff05a17cff5e8fe2cc921517761e7
 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": 7.101936461341793e-05,
+  "epoch": 0.00014203872922683586,
   "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": 35.765,
       "eval_steps_per_second": 17.884,
       "step": 3
+    },
+    {
+      "epoch": 9.46924861512239e-05,
+      "grad_norm": 1.921068787574768,
+      "learning_rate": 8e-05,
+      "loss": 1.6894,
+      "step": 4
+    },
+    {
+      "epoch": 0.00011836560768902987,
+      "grad_norm": 1.6738073825836182,
+      "learning_rate": 0.0001,
+      "loss": 1.5135,
+      "step": 5
+    },
+    {
+      "epoch": 0.00014203872922683586,
+      "grad_norm": 2.0782992839813232,
+      "learning_rate": 0.00012,
+      "loss": 1.9861,
+      "step": 6
+    },
+    {
+      "epoch": 0.00014203872922683586,
+      "eval_loss": 1.6642322540283203,
+      "eval_runtime": 497.4037,
+      "eval_samples_per_second": 35.76,
+      "eval_steps_per_second": 17.881,
+      "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