Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8e83e82304d93cfd449f178079cc3344684651d089e50e0548957df808f990a
+oid sha256:610e55096f1da125f1df84825d249b8109653808909e01cd3a587d7d157523a3
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82a4d8a52597fd98db42b5bbc8a000d2ead8caac057876ab38166359d21d1e60
+oid sha256:5f7735e853c7a0df3fe0dda1808c7785d5c7ad99ab57def927f2811184a9f9ac
 size 42608388

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cc430eab98049d80eb0384f5c1ba23aed2937bdb5f4807726e825212bc972e3
+oid sha256:0f2ae7796563de8707806556f3767ebfdf616adb061e5ceb7f9f970a57876ec6
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2975d7d46baeff645d2e6f0f86d7be145db90bf3fbb53a45b6e6a4d5eea42c6
+oid sha256:f020a27eca7ff90953e82532899c7d9cd3715cf48ee015ad662932d0be5fe643
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68c7c897b5ed1625323fa48d49e77bd6cb1241346b2e1c27d28b2edaebada7bf
+oid sha256:1940a318a83f821b72fa349a839b33b51f0dbfb4356182db57a54660938d1a2c
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:231ff6e08355287600ada4dab81dfdcf98a104528645cbebdaaec2f98ba021b9
+oid sha256:7044711c09638686dddd8afc36884335491e66001d1e4905e09e19e8021522b5
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
+oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0038893690579083835,
+  "epoch": 0.007778738115816767,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 117.988,
       "eval_steps_per_second": 3.694,
       "step": 9
+    },
+    {
+      "epoch": 0.005185825410544511,
+      "grad_norm": 1.3412178754806519,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 1.829,
+      "step": 12
+    },
+    {
+      "epoch": 0.00648228176318064,
+      "grad_norm": 1.5588266849517822,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 1.7529,
+      "step": 15
+    },
+    {
+      "epoch": 0.007778738115816767,
+      "grad_norm": 1.1395800113677979,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 1.7135,
+      "step": 18
+    },
+    {
+      "epoch": 0.007778738115816767,
+      "eval_loss": 1.6603822708129883,
+      "eval_runtime": 132.0674,
+      "eval_samples_per_second": 118.038,
+      "eval_steps_per_second": 3.695,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.834941159984333e+16,
+  "total_flos": 5.67993544254423e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null