Training in progress, step 1500, checkpoint

checkpoint-1500/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdb2610f0090830875031d5b2f7541b22191d3e523ca3242c97915530e4d147b
+oid sha256:5e1499347370132b36fde07882df12dc3fe925f5b0204828eea109b24e665e7b
 size 1711848436

checkpoint-1500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4c7dd68d5c2ba44f99215c116eb1c19196ae5a2109a75cef1e1878b3493beb6
+oid sha256:751541a17b89c50fa7bb3a8b8d7199f210d2082c192d14bf90e05f45d3c874fb
 size 3424043887

checkpoint-1500/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59ba95a7508f13dd110cd3ae3ee3112a037c265b3633652a6fd9b713ee5ed82c
+oid sha256:f3490602a2a0756221621f06d7a74678b670c1a06692a0beea170ca8b08053a5
 size 623

checkpoint-1500/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.876915693283081,
+  "best_metric": 0.9099885821342468,
   "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e3l57-l/checkpoint-1500",
-  "epoch": 0.2763448784082535,
+  "epoch": 0.1599829351535836,
   "eval_steps": 500,
   "global_step": 1500,
   "is_hyper_param_search": false,
@@ -9,53 +9,53 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.09211495946941783,
-      "grad_norm": 2.6780805587768555,
-      "learning_rate": 4.84647506755097e-07,
-      "loss": 0.2705,
+      "epoch": 0.05332764505119454,
+      "grad_norm": 414.62841796875,
+      "learning_rate": 4.911120591581342e-07,
+      "loss": 0.3812,
       "step": 500
     },
     {
-      "epoch": 0.09211495946941783,
-      "eval_loss": 1.0680681467056274,
-      "eval_runtime": 74.5723,
-      "eval_samples_per_second": 16.186,
-      "eval_steps_per_second": 2.025,
+      "epoch": 0.05332764505119454,
+      "eval_loss": 1.1163015365600586,
+      "eval_runtime": 61.8962,
+      "eval_samples_per_second": 15.946,
+      "eval_steps_per_second": 2.003,
       "step": 500
     },
     {
-      "epoch": 0.18422991893883567,
-      "grad_norm": 8.301130294799805,
-      "learning_rate": 4.69295013510194e-07,
-      "loss": 0.2545,
+      "epoch": 0.10665529010238908,
+      "grad_norm": 34.08418655395508,
+      "learning_rate": 4.822241183162685e-07,
+      "loss": 0.2683,
       "step": 1000
     },
     {
-      "epoch": 0.18422991893883567,
-      "eval_loss": 0.9443553686141968,
-      "eval_runtime": 74.9643,
-      "eval_samples_per_second": 16.101,
-      "eval_steps_per_second": 2.014,
+      "epoch": 0.10665529010238908,
+      "eval_loss": 0.9684447646141052,
+      "eval_runtime": 61.821,
+      "eval_samples_per_second": 15.965,
+      "eval_steps_per_second": 2.006,
       "step": 1000
     },
     {
-      "epoch": 0.2763448784082535,
-      "grad_norm": 0.018898434937000275,
-      "learning_rate": 4.5394252026529107e-07,
-      "loss": 0.234,
+      "epoch": 0.1599829351535836,
+      "grad_norm": 350.4574890136719,
+      "learning_rate": 4.733361774744027e-07,
+      "loss": 0.2119,
       "step": 1500
     },
     {
-      "epoch": 0.2763448784082535,
-      "eval_loss": 0.876915693283081,
-      "eval_runtime": 75.6401,
-      "eval_samples_per_second": 15.957,
-      "eval_steps_per_second": 1.996,
+      "epoch": 0.1599829351535836,
+      "eval_loss": 0.9099885821342468,
+      "eval_runtime": 61.9606,
+      "eval_samples_per_second": 15.929,
+      "eval_steps_per_second": 2.001,
       "step": 1500
     }
   ],
   "logging_steps": 500,
-  "max_steps": 16284,
+  "max_steps": 28128,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 500,

checkpoint-1500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea34fd4333686a44a60d290faa4ae8e00df783131842d9ae3ef1b9e874a39349
+oid sha256:bd16a1abd112ae60a2700f590eb3bd73e96acd9a0a37b30bbfa3f8ee2dc23bc1
 size 4847