Training in progress, step 1000, checkpoint

checkpoint-1000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19f9e4330043a47d1d32e721b9f7c7c6f3dba29c87e223b1b7a4842ab8108c1d
+oid sha256:9f535573fbc0d3144205a0328f594a7864509822f29469fb9215ea5f0e9568af
 size 1711848436

checkpoint-1000/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7db75a6dd061f6dfb53b56af41f9e1f1c36027ba997975a0fd187e14cec1b246
+oid sha256:7d98f6cc449e6877f2cc482921c0ac34a04d1e06f35ba7e15a091f4b7a76431d
 size 3424043887

checkpoint-1000/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57a434636e35d18064e5beb9353d03bcd2031e7a06716659ce3a0d0c78155488
+oid sha256:5bbb70b1f37c82106b875b3d2ba55d0e1aaa83cd68bbd9ced3b25fda608e6570
 size 623

checkpoint-1000/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.9443553686141968,
+  "best_metric": 0.9684447646141052,
   "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e3l57-l/checkpoint-1000",
-  "epoch": 0.18422991893883567,
+  "epoch": 0.10665529010238908,
   "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": 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
     }
   ],
   "logging_steps": 500,
-  "max_steps": 16284,
+  "max_steps": 28128,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 500,

checkpoint-1000/training_args.bin

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