Training in progress, step 40

{checkpoint-15 → checkpoint-35}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ba475c8d36049d825dc710ded8480d6d8fae3b32e0490f721ed506ed88a2da9
+oid sha256:fc049c7bce76659278f0ec2f1065e8385dd93654acbf15893a3660073ae574eb
 size 866630597

{checkpoint-20 → checkpoint-35}/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0daebb71a520050584a0bd9e86481eb4fc646f7ea888e9af22035e1cca5702e6
+oid sha256:9aab825d6a6974498d7f094dfb4e5b96abeb3b4f573a526469f7909217559cdb
 size 433324849

{checkpoint-20 → checkpoint-35}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c77f772a2ba9b5c0359e4c7dbaf1704b9f015e0cf13e2cc0d1557ec51f97467
+oid sha256:cf3a4443f6012651c2258b631f7252e6f31d20b176095e2d31df13eb725d579a
 size 14575

{checkpoint-20 → checkpoint-35}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee02d9816945c904e881ed0c62a97354f538c50c767dfe7cddb585bcb191b22d
+oid sha256:848792089894c4e2ad6feb70f0ed4cdb619ffe5d9927a5d0582d2e0d29225f5b
 size 627

{checkpoint-20 → checkpoint-35}/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": 0.25,
   "best_model_checkpoint": "./trainer_test_checkpoint/checkpoint-10",
-  "epoch": 0.4,
-  "global_step": 20,
+  "epoch": 0.7,
+  "global_step": 35,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -42,11 +42,38 @@
       "eval_samples_per_second": 28.47,
       "eval_steps_per_second": 14.235,
       "step": 20
+    },
+    {
+      "epoch": 0.5,
+      "eval_accuracy": 0.2,
+      "eval_loss": 1.6978241205215454,
+      "eval_runtime": 3.6422,
+      "eval_samples_per_second": 27.456,
+      "eval_steps_per_second": 13.728,
+      "step": 25
+    },
+    {
+      "epoch": 0.6,
+      "eval_accuracy": 0.2,
+      "eval_loss": 1.676612138748169,
+      "eval_runtime": 8.5564,
+      "eval_samples_per_second": 11.687,
+      "eval_steps_per_second": 5.844,
+      "step": 30
+    },
+    {
+      "epoch": 0.7,
+      "eval_accuracy": 0.2,
+      "eval_loss": 1.634315848350525,
+      "eval_runtime": 4.8041,
+      "eval_samples_per_second": 20.815,
+      "eval_steps_per_second": 10.408,
+      "step": 35
     }
   ],
   "max_steps": 100,
   "num_train_epochs": 2,
-  "total_flos": 10524725698560.0,
+  "total_flos": 18418269972480.0,
   "trial_name": null,
   "trial_params": null
 }

{checkpoint-20 → checkpoint-40}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b750a1285cf5d7330e810312588bf1673397d3409d08adf477c6d477a3f8648
+oid sha256:21f8eff5d005bbe0c85ef4ede8199d1dc726d5e5807ca89e3ec6dc9d9ea04234
 size 866630597

{checkpoint-15 → checkpoint-40}/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73546efd274884c910649f24f056089ff97f31d0bf3f3b12ed86f615860f3ac8
+oid sha256:18f61f228a0a4479db8f0e5bb9f08acbb94711ef432dffaa71c5c3df5547393b
 size 433324849

{checkpoint-15 → checkpoint-40}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f76d54f18626b1e6a8c0c08bd80df27682d642ae62e823afbd857e1580073ffe
+oid sha256:e1055c587654acc02eaa22163425e8da981002e363d98770c40659c9ed39c0f4
 size 14575

{checkpoint-15 → checkpoint-40}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1342d5172800147e9ebe25b8a1c9f4694b69157df8117f38d3567999ad3a36e5
+oid sha256:09fc7f0085d74ab93be960ca2e29dbb475e40eee232fbd47b09308a7385a7065
 size 627

{checkpoint-15 → checkpoint-40}/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": 0.25,
   "best_model_checkpoint": "./trainer_test_checkpoint/checkpoint-10",
-  "epoch": 0.3,
-  "global_step": 15,
+  "epoch": 0.8,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -33,11 +33,56 @@
       "eval_samples_per_second": 18.276,
       "eval_steps_per_second": 9.138,
       "step": 15
+    },
+    {
+      "epoch": 0.4,
+      "eval_accuracy": 0.2,
+      "eval_loss": 1.7414228916168213,
+      "eval_runtime": 3.5124,
+      "eval_samples_per_second": 28.47,
+      "eval_steps_per_second": 14.235,
+      "step": 20
+    },
+    {
+      "epoch": 0.5,
+      "eval_accuracy": 0.2,
+      "eval_loss": 1.6978241205215454,
+      "eval_runtime": 3.6422,
+      "eval_samples_per_second": 27.456,
+      "eval_steps_per_second": 13.728,
+      "step": 25
+    },
+    {
+      "epoch": 0.6,
+      "eval_accuracy": 0.2,
+      "eval_loss": 1.676612138748169,
+      "eval_runtime": 8.5564,
+      "eval_samples_per_second": 11.687,
+      "eval_steps_per_second": 5.844,
+      "step": 30
+    },
+    {
+      "epoch": 0.7,
+      "eval_accuracy": 0.2,
+      "eval_loss": 1.634315848350525,
+      "eval_runtime": 4.8041,
+      "eval_samples_per_second": 20.815,
+      "eval_steps_per_second": 10.408,
+      "step": 35
+    },
+    {
+      "epoch": 0.8,
+      "eval_accuracy": 0.19,
+      "eval_loss": 1.6438544988632202,
+      "eval_runtime": 3.7224,
+      "eval_samples_per_second": 26.865,
+      "eval_steps_per_second": 13.432,
+      "step": 40
     }
   ],
   "max_steps": 100,
   "num_train_epochs": 2,
-  "total_flos": 7893544273920.0,
+  "total_flos": 21049451397120.0,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0daebb71a520050584a0bd9e86481eb4fc646f7ea888e9af22035e1cca5702e6
+oid sha256:18f61f228a0a4479db8f0e5bb9f08acbb94711ef432dffaa71c5c3df5547393b
 size 433324849

runs/Aug01_08-59-35_bf9c8dab34e2/events.out.tfevents.1690880484.bf9c8dab34e2.4319.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d603590c421b8ccf248f628cbf3f8941e0e00bc2543c3ef99689d9fdb6289aea
-size 5564
+oid sha256:3fa2d6ebe6b55a7ee27936e86bec4ac070458ee4e3440f0aae75d91f01208aac
+size 6832