Training in progress, step 55

{checkpoint-35 → checkpoint-50}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc049c7bce76659278f0ec2f1065e8385dd93654acbf15893a3660073ae574eb
+oid sha256:d86d374b5fd5d0a5a4a9f01466feaed7536d145d760372ad8bc5a8cad85cd4b8
 size 866630597

{checkpoint-40 → checkpoint-50}/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18f61f228a0a4479db8f0e5bb9f08acbb94711ef432dffaa71c5c3df5547393b
+oid sha256:18d2b55007f104d6e60131af75395983b76aa1a6b95d2a0519cbaf88abdef22e
 size 433324849

{checkpoint-40 → checkpoint-50}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1055c587654acc02eaa22163425e8da981002e363d98770c40659c9ed39c0f4
+oid sha256:f176b317739721230b50f033fe07649e316185b4946b664c7a5694d860cbe468
 size 14575

{checkpoint-40 → checkpoint-50}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09fc7f0085d74ab93be960ca2e29dbb475e40eee232fbd47b09308a7385a7065
+oid sha256:ef735d7937d84cee8b4fc1381dbbd14305662bd1214671aaab273046cbfeeda4
 size 627

{checkpoint-40 → checkpoint-50}/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": 0.25,
   "best_model_checkpoint": "./trainer_test_checkpoint/checkpoint-10",
-  "epoch": 0.8,
-  "global_step": 40,
+  "epoch": 1.0,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -78,11 +78,29 @@
       "eval_samples_per_second": 26.865,
       "eval_steps_per_second": 13.432,
       "step": 40
+    },
+    {
+      "epoch": 0.9,
+      "eval_accuracy": 0.19,
+      "eval_loss": 1.6235827207565308,
+      "eval_runtime": 4.875,
+      "eval_samples_per_second": 20.513,
+      "eval_steps_per_second": 10.256,
+      "step": 45
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.19,
+      "eval_loss": 1.6140121221542358,
+      "eval_runtime": 4.2264,
+      "eval_samples_per_second": 23.661,
+      "eval_steps_per_second": 11.83,
+      "step": 50
     }
   ],
   "max_steps": 100,
   "num_train_epochs": 2,
-  "total_flos": 21049451397120.0,
+  "total_flos": 26311814246400.0,
   "trial_name": null,
   "trial_params": null
 }

{checkpoint-40 → checkpoint-55}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21f8eff5d005bbe0c85ef4ede8199d1dc726d5e5807ca89e3ec6dc9d9ea04234
+oid sha256:262467aa50094dddf79b063691057e322aacb02ae757073119375bdbe31007a5
 size 866630597

{checkpoint-35 → checkpoint-55}/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9aab825d6a6974498d7f094dfb4e5b96abeb3b4f573a526469f7909217559cdb
+oid sha256:11d3185830517df6f32f6770af1c9a95537bceef42d82fe902bc08a4b84439c4
 size 433324849

{checkpoint-35 → checkpoint-55}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf3a4443f6012651c2258b631f7252e6f31d20b176095e2d31df13eb725d579a
+oid sha256:676b651cd4e9fd484c0925e3416e72c1213165812b4c92b6107dc764ed9bb6da
 size 14575

{checkpoint-35 → checkpoint-55}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:848792089894c4e2ad6feb70f0ed4cdb619ffe5d9927a5d0582d2e0d29225f5b
+oid sha256:30a8fd04085db45ee9cb7ab46c5d7d1374132fbeab60e5d4e0eb1d11d8d4f5bd
 size 627

{checkpoint-35 → checkpoint-55}/trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 0.25,
-  "best_model_checkpoint": "./trainer_test_checkpoint/checkpoint-10",
-  "epoch": 0.7,
-  "global_step": 35,
+  "best_metric": 0.28,
+  "best_model_checkpoint": "./trainer_test_checkpoint/checkpoint-55",
+  "epoch": 1.1,
+  "global_step": 55,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -69,11 +69,47 @@
       "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
+    },
+    {
+      "epoch": 0.9,
+      "eval_accuracy": 0.19,
+      "eval_loss": 1.6235827207565308,
+      "eval_runtime": 4.875,
+      "eval_samples_per_second": 20.513,
+      "eval_steps_per_second": 10.256,
+      "step": 45
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.19,
+      "eval_loss": 1.6140121221542358,
+      "eval_runtime": 4.2264,
+      "eval_samples_per_second": 23.661,
+      "eval_steps_per_second": 11.83,
+      "step": 50
+    },
+    {
+      "epoch": 1.1,
+      "eval_accuracy": 0.28,
+      "eval_loss": 1.6068944931030273,
+      "eval_runtime": 3.6567,
+      "eval_samples_per_second": 27.347,
+      "eval_steps_per_second": 13.673,
+      "step": 55
     }
   ],
   "max_steps": 100,
   "num_train_epochs": 2,
-  "total_flos": 18418269972480.0,
+  "total_flos": 28942995671040.0,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18f61f228a0a4479db8f0e5bb9f08acbb94711ef432dffaa71c5c3df5547393b
+oid sha256:11d3185830517df6f32f6770af1c9a95537bceef42d82fe902bc08a4b84439c4
 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 sha256:3fa2d6ebe6b55a7ee27936e86bec4ac070458ee4e3440f0aae75d91f01208aac
-size 6832
+oid sha256:efde5795ba8c5dacdeb5b013bb1d1a53064a50602cc304e52ed10e9530c08735
+size 7783