Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b585f2a60f2db3a35c0d7b7cc533c321f1df235a63ff3c82b5892c8d16188c51
+oid sha256:fe0b51d3801301fd285d8935e73c4c39ddf8cea9ec47811ca5dfc7c75afc0413
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f60ddfaa146a3789227d36e98a430fffae6ea0fb1e931abcf889f6b5d501ccc
+oid sha256:d4b37725e1179334c82742350f948ccc5613b255eccb15e000c603fd79413c96
 size 42608388

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e63bb9f2bfa1d26eb38d32080d6d804f940903caf7fa15263f0ac5442895ee5
+oid sha256:88d2b406a767c6801ad391093f28887368b7510360baee58800c6e8a5f72f22a
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8a7ec145f15caf0713e5375f269873814104cd79c2cf739b59a1d8b677e03cc
+oid sha256:beb369fb44f96e72ebc6302d031c1853f5ce9886b4ef3a63b6f828a03e8692d0
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78a2b5a020cad2f971834c7b14e4df7bf8045ecc127082d0c15aa487f90c66ba
+oid sha256:7db41a3006c45f716ca4bd9b825898d905752cc0810b851a6e7bdfc2e711ce42
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbc60d99c48012f47aad5c29906cfb3e860cd7524e751af181350f61e372b80f
+oid sha256:9668948e08216a7797ddadf23fc4065f7cd19e7b55c77171f6052f586725884b
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e53b95eff99f2334cbf7ed4c962db83cb42e931305982518e928382563b5670d
+oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.027225583405358685,
+  "epoch": 0.03111495246326707,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,6 +218,35 @@
       "eval_samples_per_second": 118.003,
       "eval_steps_per_second": 3.694,
       "step": 63
+    },
+    {
+      "epoch": 0.028522039757994815,
+      "grad_norm": 0.8747905492782593,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.4359,
+      "step": 66
+    },
+    {
+      "epoch": 0.029818496110630942,
+      "grad_norm": 0.9813586473464966,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 1.5078,
+      "step": 69
+    },
+    {
+      "epoch": 0.03111495246326707,
+      "grad_norm": 0.9811728596687317,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.5199,
+      "step": 72
+    },
+    {
+      "epoch": 0.03111495246326707,
+      "eval_loss": 1.4821799993515015,
+      "eval_runtime": 132.105,
+      "eval_samples_per_second": 118.005,
+      "eval_steps_per_second": 3.694,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.992501267099812e+17,
+  "total_flos": 2.281021879961518e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null