Training in progress, step 1000, checkpoint

checkpoint-1000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9265324a873c7814694f1c9b317af056563d2038d35aa8b38545e0d7ffe62574
+oid sha256:de4f0f16864b1067d54276933e69fec46ec093fab2fcf8e71c66c06ae6298920
 size 1711848436

checkpoint-1000/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da7c1d632f64df4f7bdad2f7c7f3a40a2c074ded671e514056e449d6e3a0545f
+oid sha256:8f563923907ca6b8b7c8a7450fbc31c166d2a965dfe85800c5c7b49b007c9619
 size 3424043887

checkpoint-1000/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ea34848885fd539f78925237fe9d6c1a322aa374db26350561e62d877472bf9
+oid sha256:ee5399c4f6e4a2e2c6513d2d5f800f2319cd6309dd8cc6ec5578f329b64b44c1
 size 623

checkpoint-1000/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.9427077770233154,
+  "best_metric": 0.9742079377174377,
   "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e4l57-l/checkpoint-1000",
-  "epoch": 0.18422991893883567,
+  "epoch": 0.11257458065968705,
   "eval_steps": 500,
   "global_step": 1000,
   "is_hyper_param_search": false,
@@ -9,38 +9,38 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.09211495946941783,
-      "grad_norm": 3.0293657779693604,
-      "learning_rate": 4.884856300663227e-07,
-      "loss": 0.271,
+      "epoch": 0.056287290329843524,
+      "grad_norm": 150.1642303466797,
+      "learning_rate": 4.929640887087696e-07,
+      "loss": 0.3486,
       "step": 500
     },
     {
-      "epoch": 0.09211495946941783,
-      "eval_loss": 1.069305419921875,
-      "eval_runtime": 75.1409,
-      "eval_samples_per_second": 16.063,
-      "eval_steps_per_second": 2.01,
+      "epoch": 0.056287290329843524,
+      "eval_loss": 1.1265727281570435,
+      "eval_runtime": 123.7806,
+      "eval_samples_per_second": 15.948,
+      "eval_steps_per_second": 1.995,
       "step": 500
     },
     {
-      "epoch": 0.18422991893883567,
-      "grad_norm": 7.3040852546691895,
-      "learning_rate": 4.769712601326456e-07,
-      "loss": 0.2493,
+      "epoch": 0.11257458065968705,
+      "grad_norm": 366.6913146972656,
+      "learning_rate": 4.859281774175391e-07,
+      "loss": 0.2733,
       "step": 1000
     },
     {
-      "epoch": 0.18422991893883567,
-      "eval_loss": 0.9427077770233154,
-      "eval_runtime": 74.8926,
-      "eval_samples_per_second": 16.116,
-      "eval_steps_per_second": 2.016,
+      "epoch": 0.11257458065968705,
+      "eval_loss": 0.9742079377174377,
+      "eval_runtime": 125.8047,
+      "eval_samples_per_second": 15.691,
+      "eval_steps_per_second": 1.963,
       "step": 1000
     }
   ],
   "logging_steps": 500,
-  "max_steps": 21712,
+  "max_steps": 35532,
   "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:bf76416e4a857628175385db7f617e54451cd7ffb62c1f9590ee9f30268f8c5b
+oid sha256:319be2a769ef7117b6826908976f080f9082f159f4f0ad75da1a151ad29d9bff
 size 4847