Training in progress, step 2000, checkpoint

checkpoint-2000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5a542292908e95995677bd018537a79bc87dfc0fd4e57d82d2da10115e37da4
+oid sha256:7fdb18a042dcd3305c153dcd9471bf2150ecd00d25f7bf953637f56ea7528f5b
 size 1711848436

checkpoint-2000/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90425cbc2c5642170db9c1950eda1aead32d93a21ee967827c6a5425261d04e9
+oid sha256:ca505435ed45f8d33ebb0175a124cd9190456df5039e68756f09dfcf620e7623
 size 3424043887

checkpoint-2000/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd0cc501af0df1601264672dbfc6cf6040fc01ccafb00b41ccca22f726fbadf9
+oid sha256:62d41fa6662602ededfc4b7984d27ddf54962906079944f4a744895f11dfd2c3
 size 14503

checkpoint-2000/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 2.005213499069214,
+  "best_metric": 2.0721774101257324,
   "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e3l55-l/checkpoint-2000",
   "epoch": 0.3683919690550746,
   "eval_steps": 500,
@@ -10,62 +10,62 @@
   "log_history": [
     {
       "epoch": 0.09209799226376865,
-      "grad_norm": 0.24957604706287384,
+      "grad_norm": 0.009597355499863625,
       "learning_rate": 4.846503346227052e-05,
-      "loss": 0.7314,
+      "loss": 0.7336,
       "step": 500
     },
     {
       "epoch": 0.09209799226376865,
-      "eval_loss": 2.0805552005767822,
-      "eval_runtime": 77.1179,
-      "eval_samples_per_second": 15.638,
-      "eval_steps_per_second": 1.958,
+      "eval_loss": 2.0780556201934814,
+      "eval_runtime": 77.1404,
+      "eval_samples_per_second": 15.634,
+      "eval_steps_per_second": 1.957,
       "step": 500
     },
     {
       "epoch": 0.1841959845275373,
-      "grad_norm": 1.7965619564056396,
+      "grad_norm": 0.10049372166395187,
       "learning_rate": 4.693006692454105e-05,
-      "loss": 0.706,
+      "loss": 0.6953,
       "step": 1000
     },
     {
       "epoch": 0.1841959845275373,
-      "eval_loss": 2.083494186401367,
-      "eval_runtime": 77.6769,
-      "eval_samples_per_second": 15.526,
-      "eval_steps_per_second": 1.944,
+      "eval_loss": 2.0782744884490967,
+      "eval_runtime": 77.8965,
+      "eval_samples_per_second": 15.482,
+      "eval_steps_per_second": 1.938,
       "step": 1000
     },
     {
       "epoch": 0.27629397679130596,
-      "grad_norm": 2.3431804180145264,
+      "grad_norm": 0.0041180383414030075,
       "learning_rate": 4.539510038681157e-05,
-      "loss": 0.7413,
+      "loss": 0.6953,
       "step": 1500
     },
     {
       "epoch": 0.27629397679130596,
-      "eval_loss": 2.061879873275757,
-      "eval_runtime": 78.7083,
-      "eval_samples_per_second": 15.322,
-      "eval_steps_per_second": 1.918,
+      "eval_loss": 2.077699899673462,
+      "eval_runtime": 78.9586,
+      "eval_samples_per_second": 15.274,
+      "eval_steps_per_second": 1.912,
       "step": 1500
     },
     {
       "epoch": 0.3683919690550746,
-      "grad_norm": 6.339413166046143,
+      "grad_norm": 0.29397013783454895,
       "learning_rate": 4.386013384908209e-05,
-      "loss": 0.6927,
+      "loss": 0.6932,
       "step": 2000
     },
     {
       "epoch": 0.3683919690550746,
-      "eval_loss": 2.005213499069214,
-      "eval_runtime": 78.7325,
-      "eval_samples_per_second": 15.318,
-      "eval_steps_per_second": 1.918,
+      "eval_loss": 2.0721774101257324,
+      "eval_runtime": 77.349,
+      "eval_samples_per_second": 15.592,
+      "eval_steps_per_second": 1.952,
       "step": 2000
     }
   ],

checkpoint-2000/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c017d601dd60da346ba02ae21f67f028688537d76a3ec629ce40c1a26c428914
+oid sha256:b27d04bded9c10e64c471009a6518afb759cf80f4659553f45788f28a47bdf88
 size 4847