Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72c4365c90e4673e37a4a2c158f4b3127797f0351d6eea9b8490f9b553c5b266
+oid sha256:0e9e00e00c215ffdf92be72fd53a14e0bd66fcc66f178b041e605d8f49e85aa4
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:290fb60611823f559a1778dd2e7fd99444caee266092dc9891526caca2f08df6
+oid sha256:7e847a7f0f2b7bcc1bb383a8be2e34d5a450ae70e26f7342f62739328b928e80
 size 42608388

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42dd685047e6d843f81d8c7a97b9fe8e3a8a836d0baa0ca1458618da98aab18c
+oid sha256:0facf3338e35fed3aa8b3aca0cf2da64c5da32895aac2f3f8e801c8e7b375af7
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c303d82f711309bdf0967f8f4652d2e044e68225e894969369a6e258f673387
+oid sha256:25c7b0b351bc503daa25d30efed64ec63ddc9211784a016b82910d2b20dc1594
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb886efaa016e515326abe05c4e04003a68e6a0c5f0758d9cac3926ffc093da1
+oid sha256:7a50aafb0b75e3d7565f4919496800f406afe868bb8e9e4f5b436535c2d73dfb
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89bbd9e9f39698108fc006d2cafcf2df8819db67c29ee6862b47f75b545174af
+oid sha256:25461652a2e14e143efd7d90db238b616244de8f3d007bf5de08ae47ca77c458
 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": 0.4032,
+  "epoch": 0.4608,
   "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": 227.405,
       "eval_steps_per_second": 7.133,
       "step": 63
+    },
+    {
+      "epoch": 0.4224,
+      "grad_norm": 0.7795498371124268,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.9806,
+      "step": 66
+    },
+    {
+      "epoch": 0.4416,
+      "grad_norm": 0.8645098209381104,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 2.0406,
+      "step": 69
+    },
+    {
+      "epoch": 0.4608,
+      "grad_norm": 0.9535412192344666,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 2.026,
+      "step": 72
+    },
+    {
+      "epoch": 0.4608,
+      "eval_loss": 1.9973247051239014,
+      "eval_runtime": 4.6137,
+      "eval_samples_per_second": 228.018,
+      "eval_steps_per_second": 7.153,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0163565512097792e+17,
+  "total_flos": 1.1621247991834214e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null