Training in progress, step 480, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7df9a870142e76799658217988bde4bdceeb1eb7b38f9cd1fcf158c590e1733b
+oid sha256:d3f144fb2ab7f709b7d8d3f5984e577db1af7231bc78d4aafc8516809175ebcc
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c82bf2e06c1b05ad0b627f14d21d02546e267a84a8fc2529c471726baaf2149
+oid sha256:8956f0efcd4a5c8b06632bd4ba4031c9852d4e2fb5f0719b9013a55355f944fa
 size 18985850

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8194e71e120477ebbfe639125925f4a62d1e42c9a6f99094357e8fdf39b2f42b
+oid sha256:5660398d064aecb705ee00c8a0778aaec0bfc48803e50e93c9478794d252f4e1
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7b8e649b1da84fb4fe769ae3e4f7408311bd83e0755675d73e783bda5cd37f0
+oid sha256:41a65726963ec6fab44708be032f1ca48129dead8141c4a31de1936cc0473b34
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfabf363b9b29b8df259abe751aef2aabadfd0bfa689fd8f18bada7e936b12b9
+oid sha256:f680b2505ce9c730748c3e16ef567136db652d51e5ad473271bf16035c0b2792
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.98220640569395,
+  "epoch": 3.4056939501779357,
   "eval_steps": 500,
-  "global_step": 420,
+  "global_step": 480,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -128,6 +128,22 @@
       "eval_samples_per_second": 3.828,
       "eval_steps_per_second": 0.51,
       "step": 420
+    },
+    {
+      "epoch": 3.192170818505338,
+      "eval_loss": 0.5899730920791626,
+      "eval_runtime": 23.5114,
+      "eval_samples_per_second": 3.828,
+      "eval_steps_per_second": 0.51,
+      "step": 450
+    },
+    {
+      "epoch": 3.4056939501779357,
+      "eval_loss": 0.5798232555389404,
+      "eval_runtime": 23.4637,
+      "eval_samples_per_second": 3.836,
+      "eval_steps_per_second": 0.511,
+      "step": 480
     }
   ],
   "logging_steps": 30,
@@ -147,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6400205246313267e+17,
+  "total_flos": 1.872209810376622e+17,
   "train_batch_size": 12,
   "trial_name": null,
   "trial_params": null