Training in progress, step 1000, checkpoint

checkpoint-1000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d77271dfeac914592ae80d1cac46a4872784900d501e4221010decf535aca25a
+oid sha256:fc5245f8cdbea5c826d8b9a887ac8a7828b36dba882d4dcdc799489f312d2290
 size 1711848436

checkpoint-1000/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:049d6185c4beee466b106f9c1a5c1bf1d6ca950cd78b96fed55260e0ba6617ef
+oid sha256:3f55d6c44adaaad2397ab39cc5c94e54d5ac12b5e533704ebb33111501f21a36
 size 3424043887

checkpoint-1000/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea61eda4fc3f4aed708ac7b9d21b91622e686f1db27c0bbf90b9e719da830c6a
+oid sha256:3d1ae63fa18a0f8aa8f0eb94c3c38e88c952b9634ea1e5c9e033450f38a4d741
 size 623

checkpoint-1000/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 1.3416553735733032,
+  "best_metric": 1.3491536378860474,
   "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e4l58-l/checkpoint-1000",
-  "epoch": 0.1841959845275373,
+  "epoch": 0.18422991893883567,
   "eval_steps": 500,
   "global_step": 1000,
   "is_hyper_param_search": false,
@@ -9,38 +9,38 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.09209799226376865,
-      "grad_norm": 0.0014697719598188996,
-      "learning_rate": 4.884877509670289e-08,
-      "loss": 0.4588,
+      "epoch": 0.09211495946941783,
+      "grad_norm": 20.28152847290039,
+      "learning_rate": 4.8848563006632274e-08,
+      "loss": 0.3758,
       "step": 500
     },
     {
-      "epoch": 0.09209799226376865,
-      "eval_loss": 1.4194883108139038,
-      "eval_runtime": 78.7703,
-      "eval_samples_per_second": 15.31,
-      "eval_steps_per_second": 1.917,
+      "epoch": 0.09211495946941783,
+      "eval_loss": 1.418367862701416,
+      "eval_runtime": 73.4439,
+      "eval_samples_per_second": 16.434,
+      "eval_steps_per_second": 2.056,
       "step": 500
     },
     {
-      "epoch": 0.1841959845275373,
-      "grad_norm": 301.76043701171875,
-      "learning_rate": 4.769755019340578e-08,
-      "loss": 0.4255,
+      "epoch": 0.18422991893883567,
+      "grad_norm": 47.29538345336914,
+      "learning_rate": 4.7697126013264556e-08,
+      "loss": 0.4104,
       "step": 1000
     },
     {
-      "epoch": 0.1841959845275373,
-      "eval_loss": 1.3416553735733032,
-      "eval_runtime": 77.0051,
-      "eval_samples_per_second": 15.661,
-      "eval_steps_per_second": 1.961,
+      "epoch": 0.18422991893883567,
+      "eval_loss": 1.3491536378860474,
+      "eval_runtime": 74.3404,
+      "eval_samples_per_second": 16.236,
+      "eval_steps_per_second": 2.031,
       "step": 1000
     }
   ],
   "logging_steps": 500,
-  "max_steps": 21716,
+  "max_steps": 21712,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
   "save_steps": 500,

checkpoint-1000/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80d6f131f320de965fa9a783a60b2b8044e1bed4ee6dc17249153cae96f66b5c
+oid sha256:595bb6f39a89ec7030e395471c015665757cb5cacaafa6bba1613fd32b629686
 size 4847