Training in progress, step 1500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eac1cce5e5410e57d71489c02c27b3b2af6e3aa248217249170091e83a0f6878
+oid sha256:71fb000b904203220d022e331b69fe81deb5815b3a48bbe27b12ee5d31c51b3b
 size 268290900

run-11/checkpoint-1000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d6932a93af79c9e4747e455fda2d1176497efb879c59250b1e1b7bc52f350b2
+oid sha256:af68119ff3bb5bcc866e7c8d9118467f41e08f8d7b2b484776daa6a35e06a915
 size 268290900

run-11/checkpoint-1000/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d911fd34d2f3cb8dae21ef6011cf533414404b6592194a7926ffb47a5337b492
+oid sha256:edac4838f7f4fd230174eb238574f075ef04fbb12467be8f401c31e5969cdd5d
 size 536643898

run-11/checkpoint-1000/trainer_state.json

@@ -10,41 +10,41 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5929032258064516,
-      "eval_loss": 0.19686882197856903,
-      "eval_runtime": 5.2661,
-      "eval_samples_per_second": 588.67,
-      "eval_steps_per_second": 12.343,
+      "eval_accuracy": 0.597741935483871,
+      "eval_loss": 0.20127475261688232,
+      "eval_runtime": 5.5852,
+      "eval_samples_per_second": 555.041,
+      "eval_steps_per_second": 11.638,
       "step": 318
     },
     {
       "epoch": 1.57,
       "learning_rate": 1.685534591194969e-05,
-      "loss": 0.3149,
+      "loss": 0.3218,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8416129032258064,
-      "eval_loss": 0.09490782022476196,
-      "eval_runtime": 5.3608,
-      "eval_samples_per_second": 578.275,
-      "eval_steps_per_second": 12.125,
+      "eval_accuracy": 0.8429032258064516,
+      "eval_loss": 0.0963522419333458,
+      "eval_runtime": 5.674,
+      "eval_samples_per_second": 546.351,
+      "eval_steps_per_second": 11.456,
       "step": 636
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8938709677419355,
-      "eval_loss": 0.06310474872589111,
-      "eval_runtime": 5.4541,
-      "eval_samples_per_second": 568.382,
-      "eval_steps_per_second": 11.918,
+      "eval_accuracy": 0.8945161290322581,
+      "eval_loss": 0.0636168122291565,
+      "eval_runtime": 5.453,
+      "eval_samples_per_second": 568.492,
+      "eval_steps_per_second": 11.92,
       "step": 954
     },
     {
       "epoch": 3.14,
       "learning_rate": 1.371069182389937e-05,
-      "loss": 0.1093,
+      "loss": 0.111,
       "step": 1000
     }
   ],
@@ -52,11 +52,11 @@
   "max_steps": 3180,
   "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 259653090321324.0,
+  "total_flos": 353514894043500.0,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.015447886949790768,
+    "alpha": 0.8510017086349121,
     "num_train_epochs": 10,
-    "temperature": 14
+    "temperature": 11
   }
 }

run-11/checkpoint-1000/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb35f8dd4016b76d51232ce8b58b91b877adcb6c836af64b8e70048a18fdaae2
+oid sha256:ecf96d7fa8f7d2304812dddf41bd56b652e21c4ea0d68aad0ef98db6b20f0079
 size 4664

run-11/checkpoint-1500/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9edbd771b7fb84ea3e8f82fa1685fc0dba5eb395241a0e289c3e2609479c330
+oid sha256:71fb000b904203220d022e331b69fe81deb5815b3a48bbe27b12ee5d31c51b3b
 size 268290900

run-11/checkpoint-1500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c761dc90c89d08084f78b18c4915c010a87b9d0ccba04efecd2c4cd05990a73
+oid sha256:4e169807fcbafdbd24834d1aed0852e75f336d58f5227032ad9cfe420681ceb7
 size 536643898

run-11/checkpoint-1500/trainer_state.json

@@ -10,56 +10,56 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5929032258064516,
-      "eval_loss": 0.19686882197856903,
-      "eval_runtime": 5.2661,
-      "eval_samples_per_second": 588.67,
-      "eval_steps_per_second": 12.343,
+      "eval_accuracy": 0.597741935483871,
+      "eval_loss": 0.20127475261688232,
+      "eval_runtime": 5.5852,
+      "eval_samples_per_second": 555.041,
+      "eval_steps_per_second": 11.638,
       "step": 318
     },
     {
       "epoch": 1.57,
       "learning_rate": 1.685534591194969e-05,
-      "loss": 0.3149,
+      "loss": 0.3218,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8416129032258064,
-      "eval_loss": 0.09490782022476196,
-      "eval_runtime": 5.3608,
-      "eval_samples_per_second": 578.275,
-      "eval_steps_per_second": 12.125,
+      "eval_accuracy": 0.8429032258064516,
+      "eval_loss": 0.0963522419333458,
+      "eval_runtime": 5.674,
+      "eval_samples_per_second": 546.351,
+      "eval_steps_per_second": 11.456,
       "step": 636
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8938709677419355,
-      "eval_loss": 0.06310474872589111,
-      "eval_runtime": 5.4541,
-      "eval_samples_per_second": 568.382,
-      "eval_steps_per_second": 11.918,
+      "eval_accuracy": 0.8945161290322581,
+      "eval_loss": 0.0636168122291565,
+      "eval_runtime": 5.453,
+      "eval_samples_per_second": 568.492,
+      "eval_steps_per_second": 11.92,
       "step": 954
     },
     {
       "epoch": 3.14,
       "learning_rate": 1.371069182389937e-05,
-      "loss": 0.1093,
+      "loss": 0.111,
       "step": 1000
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.9032258064516129,
-      "eval_loss": 0.04744185879826546,
-      "eval_runtime": 5.4951,
-      "eval_samples_per_second": 564.135,
-      "eval_steps_per_second": 11.829,
+      "eval_accuracy": 0.9041935483870968,
+      "eval_loss": 0.04760991781949997,
+      "eval_runtime": 6.1888,
+      "eval_samples_per_second": 500.906,
+      "eval_steps_per_second": 10.503,
       "step": 1272
     },
     {
       "epoch": 4.72,
       "learning_rate": 1.0566037735849058e-05,
-      "loss": 0.0689,
+      "loss": 0.0696,
       "step": 1500
     }
   ],
@@ -67,11 +67,11 @@
   "max_steps": 3180,
   "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 389479376069112.0,
+  "total_flos": 483341179791288.0,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.015447886949790768,
+    "alpha": 0.8510017086349121,
     "num_train_epochs": 10,
-    "temperature": 14
+    "temperature": 11
   }
 }

run-11/checkpoint-1500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb35f8dd4016b76d51232ce8b58b91b877adcb6c836af64b8e70048a18fdaae2
+oid sha256:ecf96d7fa8f7d2304812dddf41bd56b652e21c4ea0d68aad0ef98db6b20f0079
 size 4664

run-11/checkpoint-500/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5c5a7ee255f1cb326dd52602cee96add5d67240ad1bb87ba8c17efcf7df8ea4
+oid sha256:8b38da463b6bde9b84fba1337286f6155c7648f03b6be4806a2eb326ea78e04c
 size 268290900

run-11/checkpoint-500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d174eab804765ed333282a71e14f91d5db751e50cd88cc4c551cef932b09efe
+oid sha256:f16a08b35e6bac8a1b949b6127e6a1bb43e8d796f921c57e85ca43426991dcb1
 size 536643898

run-11/checkpoint-500/trainer_state.json

@@ -10,17 +10,17 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5929032258064516,
-      "eval_loss": 0.19686882197856903,
-      "eval_runtime": 5.2661,
-      "eval_samples_per_second": 588.67,
-      "eval_steps_per_second": 12.343,
+      "eval_accuracy": 0.597741935483871,
+      "eval_loss": 0.20127475261688232,
+      "eval_runtime": 5.5852,
+      "eval_samples_per_second": 555.041,
+      "eval_steps_per_second": 11.638,
       "step": 318
     },
     {
       "epoch": 1.57,
       "learning_rate": 1.685534591194969e-05,
-      "loss": 0.3149,
+      "loss": 0.3218,
       "step": 500
     }
   ],
@@ -28,11 +28,11 @@
   "max_steps": 3180,
   "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 130007874759588.0,
+  "total_flos": 223869678481764.0,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.015447886949790768,
+    "alpha": 0.8510017086349121,
     "num_train_epochs": 10,
-    "temperature": 14
+    "temperature": 11
   }
 }

run-11/checkpoint-500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb35f8dd4016b76d51232ce8b58b91b877adcb6c836af64b8e70048a18fdaae2
+oid sha256:ecf96d7fa8f7d2304812dddf41bd56b652e21c4ea0d68aad0ef98db6b20f0079
 size 4664

runs/Jan25_17-40-54_c146da53f02f/events.out.tfevents.1706209619.c146da53f02f.3236.12

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe37c300ea4d436d50a231df15ec84ae3377c1a97731b4c109f7251db9a0811e
+size 15534

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4877bbd4bf8c3b4c2d0a169a9c195b85ebd557cc55dabfa43eadab9c9abe3fd
+oid sha256:ecf96d7fa8f7d2304812dddf41bd56b652e21c4ea0d68aad0ef98db6b20f0079
 size 4664