Training in progress, step 700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13a6300c6c39b121f94d275c2c2a549c2c8ae61e533c269f2d4e6d11187a0ec4
+oid sha256:3e7b81ec9ed43677d16f24d7a4d92029b8ced9a784864dac28758e3271b72452
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91f1f9608b67ba55573445bc2166dc2391702aeb4acd1bbe8648dc3e1919b61a
+oid sha256:7db6549a943a3a507751369eaeef7bcad047b37ddcae52a21c1738418dc6bcdc
 size 18902665

last-checkpoint/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 2.451620578765869,
+  "best_metric": 2.4525136947631836,
   "best_model_checkpoint": "./outputs/checkpoint-700",
   "epoch": 0.5100182149362478,
   "eval_steps": 100,
@@ -16,94 +16,94 @@
     },
     {
       "epoch": 0.07,
-      "eval_loss": 2.6424810886383057,
-      "eval_runtime": 206.4108,
-      "eval_samples_per_second": 30.396,
-      "eval_steps_per_second": 3.803,
+      "eval_loss": 2.6424834728240967,
+      "eval_runtime": 206.3704,
+      "eval_samples_per_second": 30.402,
+      "eval_steps_per_second": 3.804,
       "step": 100
     },
     {
       "epoch": 0.15,
       "learning_rate": 0.0002,
-      "loss": 2.6061,
+      "loss": 2.6053,
       "step": 200
     },
     {
       "epoch": 0.15,
-      "eval_loss": 2.5929574966430664,
-      "eval_runtime": 206.2177,
-      "eval_samples_per_second": 30.424,
-      "eval_steps_per_second": 3.807,
+      "eval_loss": 2.592982053756714,
+      "eval_runtime": 206.2608,
+      "eval_samples_per_second": 30.418,
+      "eval_steps_per_second": 3.806,
       "step": 200
     },
     {
       "epoch": 0.22,
       "learning_rate": 0.0002,
-      "loss": 2.5643,
+      "loss": 2.5637,
       "step": 300
     },
     {
       "epoch": 0.22,
-      "eval_loss": 2.5578970909118652,
-      "eval_runtime": 206.509,
-      "eval_samples_per_second": 30.381,
-      "eval_steps_per_second": 3.801,
+      "eval_loss": 2.558687448501587,
+      "eval_runtime": 206.6302,
+      "eval_samples_per_second": 30.363,
+      "eval_steps_per_second": 3.799,
       "step": 300
     },
     {
       "epoch": 0.29,
       "learning_rate": 0.0002,
-      "loss": 2.5383,
+      "loss": 2.5384,
       "step": 400
     },
     {
       "epoch": 0.29,
-      "eval_loss": 2.5257716178894043,
-      "eval_runtime": 206.1349,
-      "eval_samples_per_second": 30.436,
-      "eval_steps_per_second": 3.808,
+      "eval_loss": 2.5261261463165283,
+      "eval_runtime": 206.3988,
+      "eval_samples_per_second": 30.397,
+      "eval_steps_per_second": 3.803,
       "step": 400
     },
     {
       "epoch": 0.36,
       "learning_rate": 0.0002,
-      "loss": 2.4959,
+      "loss": 2.4965,
       "step": 500
     },
     {
       "epoch": 0.36,
-      "eval_loss": 2.5014102458953857,
-      "eval_runtime": 282.6461,
-      "eval_samples_per_second": 22.197,
-      "eval_steps_per_second": 2.777,
+      "eval_loss": 2.5020904541015625,
+      "eval_runtime": 273.7006,
+      "eval_samples_per_second": 22.923,
+      "eval_steps_per_second": 2.868,
       "step": 500
     },
     {
       "epoch": 0.44,
       "learning_rate": 0.0002,
-      "loss": 2.4693,
+      "loss": 2.4706,
       "step": 600
     },
     {
       "epoch": 0.44,
-      "eval_loss": 2.475057601928711,
-      "eval_runtime": 205.7759,
-      "eval_samples_per_second": 30.489,
-      "eval_steps_per_second": 3.815,
+      "eval_loss": 2.474956512451172,
+      "eval_runtime": 206.4725,
+      "eval_samples_per_second": 30.387,
+      "eval_steps_per_second": 3.802,
       "step": 600
     },
     {
       "epoch": 0.51,
       "learning_rate": 0.0002,
-      "loss": 2.4523,
+      "loss": 2.4542,
       "step": 700
     },
     {
       "epoch": 0.51,
-      "eval_loss": 2.451620578765869,
-      "eval_runtime": 322.0554,
-      "eval_samples_per_second": 19.481,
-      "eval_steps_per_second": 2.437,
+      "eval_loss": 2.4525136947631836,
+      "eval_runtime": 307.0185,
+      "eval_samples_per_second": 20.435,
+      "eval_steps_per_second": 2.557,
       "step": 700
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a0ffd8c2b139f27950886c21bfa338a00634210331df117dcff8cd3df7ce8ad
+oid sha256:3618b713e8d14cca4d31f18e13bbc5304b540d431ee441c88df694b97c28653e
 size 4219