Training in progress, step 70, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e784acdeea8251a6336500366d312e683bd14e3b97f10fae082fa3d6941ae7c
+oid sha256:76772ee06a903bd15efd4b2fd9fc36d0faf385f175790d9a70c3dacd53d98b6d
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec526be729fc00766aa465a00eb2bf0692f28ce23edb3bf18d27f8d70b8a5d6c
+oid sha256:f5c5f7e41f4490e944abe5a6a3547140943ca926683af8d323045dbf8fcea737
 size 328468404

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4021ac42541c732a9edf05da0035fae77d4a41abb574781ede4fe889417988ba
+oid sha256:4abb57ca1f72f009b9be4857dae11d019440ab0298975d50e67fb7573f60fcfb
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41670b12d55b8b5e00e1702187eaf19a951a106909295e3bdb88a154dad660d3
+oid sha256:2c1308288c865a7e246846346cb393d1c1c6bab2f8d717efcedbc448fade90cd
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:357fa8adc33d4c6287c5a582578b54604c4e2ff77e822b43c331fe6a4113b76a
+oid sha256:504c85a167c11b557e977581fd1ef586d692ecc7c43cafdf2bd505727dfcb4ff
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1523cad77aebbc5c93094a08e19a912cbf5e034a61c053725fea450338236ccb
+oid sha256:986d90e567988c99934971e98eb512ed77085ce9e2c43a63013eb71bf16e1cb1
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e56d433c056f847cd62894fdc7d2cfac435f2db58e37ae7dede3f4334c0f5d0
+oid sha256:f801a7c0b9e4c4f6a78f72d23b03dd9d354b586ec68586ceb8cf7e0483d800d3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.495049504950495,
+  "epoch": 2.772277227722772,
   "eval_steps": 7,
-  "global_step": 63,
+  "global_step": 70,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -234,6 +234,28 @@
       "eval_samples_per_second": 65.322,
       "eval_steps_per_second": 4.611,
       "step": 63
+    },
+    {
+      "epoch": 2.613861386138614,
+      "grad_norm": 0.9128199815750122,
+      "learning_rate": 5.558227567253832e-06,
+      "loss": 1.023,
+      "step": 66
+    },
+    {
+      "epoch": 2.7326732673267324,
+      "grad_norm": 0.9300925731658936,
+      "learning_rate": 2.7499590642665774e-06,
+      "loss": 1.0016,
+      "step": 69
+    },
+    {
+      "epoch": 2.772277227722772,
+      "eval_loss": 1.3773143291473389,
+      "eval_runtime": 1.2839,
+      "eval_samples_per_second": 66.203,
+      "eval_steps_per_second": 4.673,
+      "step": 70
     }
   ],
   "logging_steps": 3,
@@ -253,7 +275,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.791579701253243e+17,
+  "total_flos": 1.9906441125036032e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null