Training in progress, step 1000, checkpoint

checkpoint-1000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5425aa0fd08ecdb0f5834a9debc99767944b37c6e44c8d271c37a77eeaa54c6
+oid sha256:8e0e03f6da37f6f8a899b713fcee42642f39746765a0122d89d6ec5da824b560
 size 1711848436

checkpoint-1000/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45eb811b1531db51dd0b27607aa5ec611a673a7dc679f94e04ea5cd9fbd71009
+oid sha256:cfe4bb3ba95f08d3f7bbdd5e9532beb26d5309c7752d8082607241f6c9e9116f
 size 3424043887

checkpoint-1000/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83ebac2cb31599eebab04e974fac484f5a3ffe3617ab7ab3ffa2850bc4e94901
+oid sha256:cddea61a11092e69e3973a4562c205fe8dcda2586b2bbd0ebc4aa156d7fa3663
 size 623

checkpoint-1000/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.9449871182441711,
-  "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e2l57-l/checkpoint-1000",
+  "best_metric": 2.078129768371582,
+  "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e2l57-l/checkpoint-500",
   "epoch": 0.18422991893883567,
   "eval_steps": 500,
   "global_step": 1000,
@@ -10,32 +10,32 @@
   "log_history": [
     {
       "epoch": 0.09211495946941783,
-      "grad_norm": 2.838374137878418,
-      "learning_rate": 4.769712601326456e-07,
-      "loss": 0.2712,
+      "grad_norm": 0.016798699274659157,
+      "learning_rate": 4.769712601326456e-05,
+      "loss": 0.7088,
       "step": 500
     },
     {
       "epoch": 0.09211495946941783,
-      "eval_loss": 1.0726110935211182,
-      "eval_runtime": 77.3241,
-      "eval_samples_per_second": 15.61,
-      "eval_steps_per_second": 1.953,
+      "eval_loss": 2.078129768371582,
+      "eval_runtime": 73.0941,
+      "eval_samples_per_second": 16.513,
+      "eval_steps_per_second": 2.066,
       "step": 500
     },
     {
       "epoch": 0.18422991893883567,
-      "grad_norm": 6.35071325302124,
-      "learning_rate": 4.5394252026529107e-07,
-      "loss": 0.2554,
+      "grad_norm": 0.04167987406253815,
+      "learning_rate": 4.539425202652911e-05,
+      "loss": 0.6951,
       "step": 1000
     },
     {
       "epoch": 0.18422991893883567,
-      "eval_loss": 0.9449871182441711,
-      "eval_runtime": 75.1068,
-      "eval_samples_per_second": 16.07,
-      "eval_steps_per_second": 2.01,
+      "eval_loss": 2.0785396099090576,
+      "eval_runtime": 73.8136,
+      "eval_samples_per_second": 16.352,
+      "eval_steps_per_second": 2.046,
       "step": 1000
     }
   ],

checkpoint-1000/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cd5d7856a0d40c1aa83893e8a456fbbee3c7b8b2995fa667c213e700eef2e98
+oid sha256:7588393cee90272352197a3703ab9af7b35cfce4eb9f372fcb0594562d7e5f44
 size 4847