Training in progress, step 500, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7863c571bd5ee58546f5cd45cf773f0c2e89e7e5305d1846307f037b788fb09b
+oid sha256:57bcf9aadb84dfa8897b2e4530b987a9c127fd8f62e36d334273f6f79ba49fd4
 size 386379

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14237bc7f1f79a32edc5378e5f6485c949dca1c7c053533db8b2e20e7944952f
+oid sha256:222f7b426772c1ffb9f700de36da891361e9e0f275abce60101e6d83da4257b2
 size 1540661735

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa11d09eaf39b79c4a9eb5ffaa5339e4718f77f477ed3d44c61a2c9c8d9c07e7
+oid sha256:1ffdf794aa37bf66c11fbf3a25c5c6e95b77bf37b30e60af016fc9124d0bcb99
 size 14469

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18e1ee6a6049b20a29c856e9e8749d38d39703bdb3fe8e7f34f78a52b4deb003
+oid sha256:81af6df700759cf275cafea0cdaf381ba3c2b41fab7e7379341c665c147ed0de
 size 14469

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bc6a538678bb8e80970d8dfd01591730e61d5c7ec87e9d733dcefc6ec26485b
+oid sha256:d55b42bedc0f28bff9c30b7bebe80ce64a5aa5c0c36daab2e46abff72980db18
 size 14469

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2159759ebb0b975fc2ccc44433d7ac272528ee3c15674681017cbe8bee3119fa
+oid sha256:ef44384c481d885f2114df6c79173cd8acc16cb1ee47046bf46031abdcc9c81b
 size 14469

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:549d83e6c1ee015edf8dde69807db4230d908ed09ad90cc2c6b307e538e9371f
+oid sha256:c41a4b4c8c4b93050c780cbd4537fecb50bacfb6229c463432858be6d6a803f6
 size 14469

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bae36f5d5d4c73ae082bef827ac5511e211272e5c36dbde3e5514507605dc09b
+oid sha256:d79aee2c3afea7ec6ffe3ac7b43481b7334a7abba51e0d4f2ed2312cd5550aeb
 size 14469

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2df63b6dcfad3a86ddaca85b94f45511e7c9c2bb895c9c280ec62cac7e7b0e1f
+oid sha256:c918f0602d1108574e113fb8e32d725731b2c86339c03552c0229840eb091bf8
 size 14469

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1b763f089b4afb6c5d8d853556630abbdc8dc1c480be4ffbeb16ccc68896cb7
+oid sha256:c2f462384e1628ac3068742a9ce939fc67956eb63350336c85c9bc3aee27af07
 size 14469

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c3db7392f9c6280c917a9b32f54db3418a51b7cc8ad693de700680693a06e6b
+oid sha256:9f532a77c9963a928cf7277c87e919c365cd36b1e11776f70173ba96ec9da717
 size 1465

last-checkpoint/trainer_state.json

@@ -2,172 +2,92 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0,
+  "epoch": 0.5,
   "eval_steps": 100,
-  "global_step": 1000,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": false,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.1,
-      "grad_norm": 1.026106834411621,
+      "grad_norm": 0.7191144824028015,
       "learning_rate": 0.003920764340590609,
-      "loss": 68.1809814453125,
+      "loss": 67.510126953125,
       "step": 100
     },
     {
       "epoch": 0.1,
-      "eval_accuracy": 0.13532681017612525,
-      "eval_loss": 63.20947265625,
-      "eval_runtime": 14.9666,
-      "eval_samples_per_second": 8.352,
-      "eval_steps_per_second": 0.267,
+      "eval_accuracy": 0.1416715542521994,
+      "eval_loss": 62.5124397277832,
+      "eval_runtime": 23.2064,
+      "eval_samples_per_second": 5.386,
+      "eval_steps_per_second": 0.172,
       "step": 100
     },
     {
       "epoch": 0.2,
-      "grad_norm": 1.1686949729919434,
+      "grad_norm": 0.7917912006378174,
       "learning_rate": 0.003650943793925548,
-      "loss": 61.33072265625,
+      "loss": 60.964296875,
       "step": 200
     },
     {
       "epoch": 0.2,
-      "eval_accuracy": 0.14370254403131116,
-      "eval_loss": 60.317352294921875,
-      "eval_runtime": 3.2913,
-      "eval_samples_per_second": 37.979,
-      "eval_steps_per_second": 1.215,
+      "eval_accuracy": 0.14520723362658847,
+      "eval_loss": 59.7275390625,
+      "eval_runtime": 7.0415,
+      "eval_samples_per_second": 17.752,
+      "eval_steps_per_second": 0.568,
       "step": 200
     },
     {
       "epoch": 0.3,
-      "grad_norm": 0.9769435524940491,
+      "grad_norm": 0.6012804508209229,
       "learning_rate": 0.0032162636906540357,
-      "loss": 59.6425439453125,
+      "loss": 58.9265185546875,
       "step": 300
     },
     {
       "epoch": 0.3,
-      "eval_accuracy": 0.14733463796477494,
-      "eval_loss": 58.926719665527344,
-      "eval_runtime": 3.3852,
-      "eval_samples_per_second": 36.925,
-      "eval_steps_per_second": 1.182,
+      "eval_accuracy": 0.14982697947214077,
+      "eval_loss": 58.20082092285156,
+      "eval_runtime": 6.9154,
+      "eval_samples_per_second": 18.076,
+      "eval_steps_per_second": 0.578,
       "step": 300
     },
     {
       "epoch": 0.4,
-      "grad_norm": 0.6136718392372131,
+      "grad_norm": 0.5591040849685669,
       "learning_rate": 0.0026601302141692667,
-      "loss": 58.5160546875,
+      "loss": 57.6960791015625,
       "step": 400
     },
     {
       "epoch": 0.4,
-      "eval_accuracy": 0.149293542074364,
-      "eval_loss": 57.94895935058594,
-      "eval_runtime": 3.1596,
-      "eval_samples_per_second": 39.562,
-      "eval_steps_per_second": 1.266,
+      "eval_accuracy": 0.15061388074291301,
+      "eval_loss": 57.27326965332031,
+      "eval_runtime": 6.7764,
+      "eval_samples_per_second": 18.446,
+      "eval_steps_per_second": 0.59,
       "step": 400
     },
     {
       "epoch": 0.5,
-      "grad_norm": 0.6485599875450134,
+      "grad_norm": 0.6106539368629456,
       "learning_rate": 0.002038077610206693,
-      "loss": 57.5463623046875,
+      "loss": 57.197861328125,
       "step": 500
     },
     {
       "epoch": 0.5,
-      "eval_accuracy": 0.15155577299412915,
-      "eval_loss": 57.233314514160156,
-      "eval_runtime": 3.1982,
-      "eval_samples_per_second": 39.085,
-      "eval_steps_per_second": 1.251,
+      "eval_accuracy": 0.15304692082111437,
+      "eval_loss": 56.594947814941406,
+      "eval_runtime": 6.936,
+      "eval_samples_per_second": 18.022,
+      "eval_steps_per_second": 0.577,
       "step": 500
-    },
-    {
-      "epoch": 0.6,
-      "grad_norm": 0.7341565489768982,
-      "learning_rate": 0.0014122226612106885,
-      "loss": 56.99380859375,
-      "step": 600
-    },
-    {
-      "epoch": 0.6,
-      "eval_accuracy": 0.15327788649706459,
-      "eval_loss": 56.73516082763672,
-      "eval_runtime": 3.0941,
-      "eval_samples_per_second": 40.399,
-      "eval_steps_per_second": 1.293,
-      "step": 600
-    },
-    {
-      "epoch": 0.7,
-      "grad_norm": 0.6851957440376282,
-      "learning_rate": 0.0008450618433005865,
-      "loss": 56.550751953125,
-      "step": 700
-    },
-    {
-      "epoch": 0.7,
-      "eval_accuracy": 0.1546183953033268,
-      "eval_loss": 56.412452697753906,
-      "eval_runtime": 3.1685,
-      "eval_samples_per_second": 39.45,
-      "eval_steps_per_second": 1.262,
-      "step": 700
-    },
-    {
-      "epoch": 0.8,
-      "grad_norm": 0.7154708504676819,
-      "learning_rate": 0.0003932305678751549,
-      "loss": 56.2383203125,
-      "step": 800
-    },
-    {
-      "epoch": 0.8,
-      "eval_accuracy": 0.15636399217221136,
-      "eval_loss": 56.198299407958984,
-      "eval_runtime": 3.1695,
-      "eval_samples_per_second": 39.438,
-      "eval_steps_per_second": 1.262,
-      "step": 800
-    },
-    {
-      "epoch": 0.9,
-      "grad_norm": 0.6124030351638794,
-      "learning_rate": 0.00010184769603774147,
-      "loss": 56.5553125,
-      "step": 900
-    },
-    {
-      "epoch": 0.9,
-      "eval_accuracy": 0.1569628180039139,
-      "eval_loss": 56.1020622253418,
-      "eval_runtime": 3.1581,
-      "eval_samples_per_second": 39.58,
-      "eval_steps_per_second": 1.267,
-      "step": 900
-    },
-    {
-      "epoch": 1.0,
-      "grad_norm": 0.7291918992996216,
-      "learning_rate": 1.0069988897853933e-08,
-      "loss": 56.4785693359375,
-      "step": 1000
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.15711350293542076,
-      "eval_loss": 56.08707046508789,
-      "eval_runtime": 3.2592,
-      "eval_samples_per_second": 38.353,
-      "eval_steps_per_second": 1.227,
-      "step": 1000
     }
   ],
   "logging_steps": 100,
@@ -182,7 +102,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }