Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:352cb958343b0f5f486dc57cfdbc174aef5d6ae1df8a6a9376d36fe9c1f9874a
+oid sha256:e6032b80e870c19eb5346f983a00e5fd9df26ffcb4aab1c1dac0290262ddc703
 size 119801528

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d20f1b49dd0756ed294a4529748f483145c584930986eb2d74bb1ff3447f4868
+oid sha256:bf5f81d0008a0bb825b308ed6ad95847405927d7e5ac4f965d62621631ae8294
 size 61392180

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f0e67546519d04a90eca7b5709de9611b5d8f703f726d61fbfe8c60594ec0c9
+oid sha256:e6da2047a274c755c0067350f90a87d4e4999db848b8acad267ac54dfc400ebe
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ac4c2e2deadbecd4adc4686da76b7b463c4cd1f6081017831221912cac089b2
+oid sha256:cde5fb7acaa58cb5d1bf245cbac19a2d14b6a5da8d01ac17393e693e1f46f42d
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc78163c347c258a17d5fa38a4e22e79b63c35d2cfce0e026e30c38b9ae55f80
+oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2831858407079646,
+  "epoch": 0.5663716814159292,
   "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": 15.407,
       "eval_steps_per_second": 3.852,
       "step": 3
+    },
+    {
+      "epoch": 0.3775811209439528,
+      "grad_norm": 0.18228459358215332,
+      "learning_rate": 4e-05,
+      "loss": 0.6263,
+      "step": 4
+    },
+    {
+      "epoch": 0.471976401179941,
+      "grad_norm": 0.18348485231399536,
+      "learning_rate": 5e-05,
+      "loss": 0.6098,
+      "step": 5
+    },
+    {
+      "epoch": 0.5663716814159292,
+      "grad_norm": 0.1853514462709427,
+      "learning_rate": 6e-05,
+      "loss": 0.6469,
+      "step": 6
+    },
+    {
+      "epoch": 0.5663716814159292,
+      "eval_loss": 0.8376555442810059,
+      "eval_runtime": 4.6732,
+      "eval_samples_per_second": 15.407,
+      "eval_steps_per_second": 3.852,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.646853912048435e+16,
+  "total_flos": 5.29370782409687e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null