Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:395735a6e96c5aeafdafa05b480dec5ba6765a1f6cfa5ae5ddec9166e67489d4
+oid sha256:3afc7018e29c21d30dec35657ae34358d0fb0f9abb809f70cd7e6ccbec83bdfb
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b41bb5e5634784fde2e81050cc44ce835821208b457099074d4d3efec1c2f75f
+oid sha256:41f89c1bb53ccdc38897acac4e2172a0d936cde38f6e445661d7b718e3fd6156
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:631dfb2aa9ae256eca5748a1b2ab04547dfc14e5e8346db748407ed5d049499d
+oid sha256:83e1d42fa3a43f0b49fecc1fb9869481eef60e0607192a6ff7e39173952f7302
 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": 0.056074766355140186,
+  "epoch": 0.11214953271028037,
   "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": 30.947,
       "eval_steps_per_second": 16.146,
       "step": 3
+    },
+    {
+      "epoch": 0.07476635514018691,
+      "grad_norm": 1.0428029298782349,
+      "learning_rate": 8e-05,
+      "loss": 2.0578,
+      "step": 4
+    },
+    {
+      "epoch": 0.09345794392523364,
+      "grad_norm": 1.082016944885254,
+      "learning_rate": 0.0001,
+      "loss": 1.9756,
+      "step": 5
+    },
+    {
+      "epoch": 0.11214953271028037,
+      "grad_norm": 1.079058289527893,
+      "learning_rate": 0.00012,
+      "loss": 2.1077,
+      "step": 6
+    },
+    {
+      "epoch": 0.11214953271028037,
+      "eval_loss": 2.4028377532958984,
+      "eval_runtime": 0.7562,
+      "eval_samples_per_second": 30.415,
+      "eval_steps_per_second": 15.868,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 554869274443776.0,
+  "total_flos": 1155977655091200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null