Training in progress, step 420, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d3e26e45c6f8d91307191cead3486af199a51d9f5f486c316bbb5da9a31297f
+oid sha256:7df9a870142e76799658217988bde4bdceeb1eb7b38f9cd1fcf158c590e1733b
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:600a49db099fb52727f2f612933cff046fc0e30ea5825555ec40699ef5d0aaae
+oid sha256:8c82bf2e06c1b05ad0b627f14d21d02546e267a84a8fc2529c471726baaf2149
 size 18985850

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b511ac4741cdaeaa24032ce830a21ea2dc449285fb13169e19e7f01f918463cd
+oid sha256:8194e71e120477ebbfe639125925f4a62d1e42c9a6f99094357e8fdf39b2f42b
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:520a5bc102f58a1db348bd34d784e37b774aba2fbcdc048fdbe1c7ba6a16ed95
+oid sha256:c7b8e649b1da84fb4fe769ae3e4f7408311bd83e0755675d73e783bda5cd37f0
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbd6905bf066c21fb2a0e9b49665d1bfbf1878371eb3c6ba1a819445ead89c34
+oid sha256:dfabf363b9b29b8df259abe751aef2aabadfd0bfa689fd8f18bada7e936b12b9
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.5551601423487544,
+  "epoch": 2.98220640569395,
   "eval_steps": 500,
-  "global_step": 360,
+  "global_step": 420,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -112,6 +112,22 @@
       "eval_samples_per_second": 3.824,
       "eval_steps_per_second": 0.51,
       "step": 360
+    },
+    {
+      "epoch": 2.7686832740213525,
+      "eval_loss": 0.5559327006340027,
+      "eval_runtime": 23.4917,
+      "eval_samples_per_second": 3.831,
+      "eval_steps_per_second": 0.511,
+      "step": 390
+    },
+    {
+      "epoch": 2.98220640569395,
+      "eval_loss": 0.55695641040802,
+      "eval_runtime": 23.5128,
+      "eval_samples_per_second": 3.828,
+      "eval_steps_per_second": 0.51,
+      "step": 420
     }
   ],
   "logging_steps": 30,
@@ -131,7 +147,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4048921340031795e+17,
+  "total_flos": 1.6400205246313267e+17,
   "train_batch_size": 12,
   "trial_name": null,
   "trial_params": null