Training in progress, step 700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e7b81ec9ed43677d16f24d7a4d92029b8ced9a784864dac28758e3271b72452
+oid sha256:6aae2e343ec94d6a3b128450cdab3184c3632ea88d300fcb2ba29ba104ab887b
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7db6549a943a3a507751369eaeef7bcad047b37ddcae52a21c1738418dc6bcdc
+oid sha256:643b33c272a85100a20b13c5c253bd0ee93735164f39e19b94147bc8866d5a05
 size 18902665

last-checkpoint/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 2.4525136947631836,
+  "best_metric": 2.444390296936035,
   "best_model_checkpoint": "./outputs/checkpoint-700",
   "epoch": 0.5100182149362478,
   "eval_steps": 100,
@@ -11,99 +11,99 @@
     {
       "epoch": 0.07,
       "learning_rate": 0.0002,
-      "loss": 2.7401,
+      "loss": 2.7406,
       "step": 100
     },
     {
       "epoch": 0.07,
-      "eval_loss": 2.6424834728240967,
-      "eval_runtime": 206.3704,
-      "eval_samples_per_second": 30.402,
-      "eval_steps_per_second": 3.804,
+      "eval_loss": 2.6424405574798584,
+      "eval_runtime": 206.8728,
+      "eval_samples_per_second": 30.328,
+      "eval_steps_per_second": 3.795,
       "step": 100
     },
     {
       "epoch": 0.15,
       "learning_rate": 0.0002,
-      "loss": 2.6053,
+      "loss": 2.6056,
       "step": 200
     },
     {
       "epoch": 0.15,
-      "eval_loss": 2.592982053756714,
-      "eval_runtime": 206.2608,
-      "eval_samples_per_second": 30.418,
-      "eval_steps_per_second": 3.806,
+      "eval_loss": 2.591430187225342,
+      "eval_runtime": 206.9647,
+      "eval_samples_per_second": 30.314,
+      "eval_steps_per_second": 3.793,
       "step": 200
     },
     {
       "epoch": 0.22,
       "learning_rate": 0.0002,
-      "loss": 2.5637,
+      "loss": 2.5631,
       "step": 300
     },
     {
       "epoch": 0.22,
-      "eval_loss": 2.558687448501587,
-      "eval_runtime": 206.6302,
-      "eval_samples_per_second": 30.363,
+      "eval_loss": 2.5565075874328613,
+      "eval_runtime": 206.6263,
+      "eval_samples_per_second": 30.364,
       "eval_steps_per_second": 3.799,
       "step": 300
     },
     {
       "epoch": 0.29,
       "learning_rate": 0.0002,
-      "loss": 2.5384,
+      "loss": 2.5363,
       "step": 400
     },
     {
       "epoch": 0.29,
-      "eval_loss": 2.5261261463165283,
-      "eval_runtime": 206.3988,
-      "eval_samples_per_second": 30.397,
-      "eval_steps_per_second": 3.803,
+      "eval_loss": 2.5222103595733643,
+      "eval_runtime": 234.7988,
+      "eval_samples_per_second": 26.721,
+      "eval_steps_per_second": 3.343,
       "step": 400
     },
     {
       "epoch": 0.36,
       "learning_rate": 0.0002,
-      "loss": 2.4965,
+      "loss": 2.4935,
       "step": 500
     },
     {
       "epoch": 0.36,
-      "eval_loss": 2.5020904541015625,
-      "eval_runtime": 273.7006,
-      "eval_samples_per_second": 22.923,
-      "eval_steps_per_second": 2.868,
+      "eval_loss": 2.4934604167938232,
+      "eval_runtime": 206.7039,
+      "eval_samples_per_second": 30.353,
+      "eval_steps_per_second": 3.798,
       "step": 500
     },
     {
       "epoch": 0.44,
       "learning_rate": 0.0002,
-      "loss": 2.4706,
+      "loss": 2.467,
       "step": 600
     },
     {
       "epoch": 0.44,
-      "eval_loss": 2.474956512451172,
-      "eval_runtime": 206.4725,
-      "eval_samples_per_second": 30.387,
-      "eval_steps_per_second": 3.802,
+      "eval_loss": 2.467857837677002,
+      "eval_runtime": 287.8992,
+      "eval_samples_per_second": 21.792,
+      "eval_steps_per_second": 2.727,
       "step": 600
     },
     {
       "epoch": 0.51,
       "learning_rate": 0.0002,
-      "loss": 2.4542,
+      "loss": 2.4494,
       "step": 700
     },
     {
       "epoch": 0.51,
-      "eval_loss": 2.4525136947631836,
-      "eval_runtime": 307.0185,
-      "eval_samples_per_second": 20.435,
-      "eval_steps_per_second": 2.557,
+      "eval_loss": 2.444390296936035,
+      "eval_runtime": 206.5306,
+      "eval_samples_per_second": 30.378,
+      "eval_steps_per_second": 3.801,
       "step": 700
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3618b713e8d14cca4d31f18e13bbc5304b540d431ee441c88df694b97c28653e
+oid sha256:f6bbb4e93666410d7a938dd3851f7194e97be075889249a5ac42f4cb3cfacdd3
 size 4219