Training in progress, step 500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:232eaf6924b640670e424f121b0308a7c44eba675a1105736c179b9e656b4fc8
+oid sha256:c523e1752fda46381be0344a31afc01362450b48bbf8705a2c2bdc36cbf5d0d2
 size 268290900

run-13/checkpoint-2500/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecd7bb18dc112a2febe521e6b29f5a5b9eec145154d2663152f38803378acdc7
+oid sha256:2cf50cbd134a3066e0d74687b39b2bba0fc2a0cdb34238e44082bdf70216c841
 size 268290900

run-13/checkpoint-2500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35b446bce357ee567754d20950f94c6d79ce4513715384de5924fb4b00b7966d
+oid sha256:0fac8f5ce1a1a762a78650e0ad4773833a79e3d301a367a8ab899a2adfbd9404
 size 536643898

run-13/checkpoint-2500/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d116f7be47ce88249a782ce7aafaf5b673a05bfa0ebdf9f14ab4c327c94c6b04
+oid sha256:b7c943a77651a184c6653dd4706c14c9a27d52136e81942a2b361c74acb9f665
 size 1064

run-13/checkpoint-2500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f62c7b1cdbc5f04f78a333fc7ad899d41a314edecf47ae9022088c79c529b2e
+oid sha256:825ce3dae72879e90f1e7c8bf9db5978e39cf9b4e9cf4d01acbdb15f1075ac03
 size 5176

run-15/checkpoint-1000/trainer_state.json

@@ -12,9 +12,9 @@
       "epoch": 1.0,
       "eval_accuracy": 0.62,
       "eval_loss": 0.249518021941185,
-      "eval_runtime": 1.3697,
-      "eval_samples_per_second": 2263.294,
-      "eval_steps_per_second": 47.456,
+      "eval_runtime": 1.2519,
+      "eval_samples_per_second": 2476.275,
+      "eval_steps_per_second": 51.922,
       "step": 318
     },
     {
@@ -28,18 +28,18 @@
       "epoch": 2.0,
       "eval_accuracy": 0.8422580645161291,
       "eval_loss": 0.11037396639585495,
-      "eval_runtime": 1.3637,
-      "eval_samples_per_second": 2273.273,
-      "eval_steps_per_second": 47.665,
+      "eval_runtime": 1.2525,
+      "eval_samples_per_second": 2475.052,
+      "eval_steps_per_second": 51.896,
       "step": 636
     },
     {
       "epoch": 3.0,
       "eval_accuracy": 0.8883870967741936,
       "eval_loss": 0.0677555724978447,
-      "eval_runtime": 1.3669,
-      "eval_samples_per_second": 2267.902,
-      "eval_steps_per_second": 47.553,
+      "eval_runtime": 1.2545,
+      "eval_samples_per_second": 2471.149,
+      "eval_steps_per_second": 51.814,
       "step": 954
     },
     {
@@ -67,11 +67,11 @@
       "attributes": {}
     }
   },
-  "total_flos": 319943755193412.0,
+  "total_flos": 343945671947388.0,
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.9970515290608379,
+    "alpha": 0.9969607810126598,
     "num_train_epochs": 9,
     "temperature": 4
   }

run-15/checkpoint-1500/trainer_state.json

@@ -12,9 +12,9 @@
       "epoch": 1.0,
       "eval_accuracy": 0.62,
       "eval_loss": 0.249518021941185,
-      "eval_runtime": 1.3697,
-      "eval_samples_per_second": 2263.294,
-      "eval_steps_per_second": 47.456,
+      "eval_runtime": 1.2519,
+      "eval_samples_per_second": 2476.275,
+      "eval_steps_per_second": 51.922,
       "step": 318
     },
     {
@@ -28,18 +28,18 @@
       "epoch": 2.0,
       "eval_accuracy": 0.8422580645161291,
       "eval_loss": 0.11037396639585495,
-      "eval_runtime": 1.3637,
-      "eval_samples_per_second": 2273.273,
-      "eval_steps_per_second": 47.665,
+      "eval_runtime": 1.2525,
+      "eval_samples_per_second": 2475.052,
+      "eval_steps_per_second": 51.896,
       "step": 636
     },
     {
       "epoch": 3.0,
       "eval_accuracy": 0.8883870967741936,
       "eval_loss": 0.0677555724978447,
-      "eval_runtime": 1.3669,
-      "eval_samples_per_second": 2267.902,
-      "eval_steps_per_second": 47.553,
+      "eval_runtime": 1.2545,
+      "eval_samples_per_second": 2471.149,
+      "eval_steps_per_second": 51.814,
       "step": 954
     },
     {
@@ -53,9 +53,9 @@
       "epoch": 4.0,
       "eval_accuracy": 0.902258064516129,
       "eval_loss": 0.04977014288306236,
-      "eval_runtime": 1.3624,
-      "eval_samples_per_second": 2275.356,
-      "eval_steps_per_second": 47.709,
+      "eval_runtime": 1.2559,
+      "eval_samples_per_second": 2468.428,
+      "eval_steps_per_second": 51.757,
       "step": 1272
     },
     {
@@ -83,11 +83,11 @@
       "attributes": {}
     }
   },
-  "total_flos": 450371359983132.0,
+  "total_flos": 474373276737108.0,
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.9970515290608379,
+    "alpha": 0.9969607810126598,
     "num_train_epochs": 9,
     "temperature": 4
   }

run-15/checkpoint-500/trainer_state.json

@@ -12,9 +12,9 @@
       "epoch": 1.0,
       "eval_accuracy": 0.62,
       "eval_loss": 0.249518021941185,
-      "eval_runtime": 1.3697,
-      "eval_samples_per_second": 2263.294,
-      "eval_steps_per_second": 47.456,
+      "eval_runtime": 1.2519,
+      "eval_samples_per_second": 2476.275,
+      "eval_steps_per_second": 51.922,
       "step": 318
     },
     {
@@ -42,11 +42,11 @@
       "attributes": {}
     }
   },
-  "total_flos": 189074629692144.0,
+  "total_flos": 213076546446120.0,
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.9970515290608379,
+    "alpha": 0.9969607810126598,
     "num_train_epochs": 9,
     "temperature": 4
   }

run-15/checkpoint-500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:920ec89dc47e401d4efb361d0fd82b37959f7734e045af2043ed258600a2854b
+oid sha256:9b2e73103b9db907e09d098899dc83e3dbf1869ac8fe958d6aec7beb5cf0db0d
 size 5176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:825ce3dae72879e90f1e7c8bf9db5978e39cf9b4e9cf4d01acbdb15f1075ac03
+oid sha256:9b2e73103b9db907e09d098899dc83e3dbf1869ac8fe958d6aec7beb5cf0db0d
 size 5176