Training in progress, step 500, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1bec6ec99a667731fe1aa7983da44b603a59d00084d494468368dac327e4f5f
+oid sha256:1e018a196e11e9728021449b82e7214a32c0d53e48e4487bdf835eeaacaf4e76
 size 386379

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81991c2b0e15a487e2749181f5b291f079b7c882141303a8389439fba049e924
+oid sha256:351028c2121581b19074f8296d27ae228170a1a469e41080403091bd2454dea0
 size 1540661735

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:934ae4672c85df4a03b901039c48484c6d48940b666eb9da6abdadd0bfd7ca2e
+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:f8e7ba67417374f28eafc52fb09cd1635fb90aeae797c287fb344cf608c324f7
+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:b34aebebdff0fa5078105ea2165525a062f2af01267a2bc4a5277f926a1ddf87
+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:bbad142d3225fe2301edd7a4526b586614f8cdf35859a150aa76ce623d42e698
+oid sha256:ef44384c481d885f2114df6c79173cd8acc16cb1ee47046bf46031abdcc9c81b
 size 14469

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08730831ebd5924954c36016585e26ed2876b02574126a5a7953c60d82be5570
+oid sha256:c41a4b4c8c4b93050c780cbd4537fecb50bacfb6229c463432858be6d6a803f6
 size 14469

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d18edd5743601b28a2cec06aa40d0c6c594939906326809da6ebe1722314306
+oid sha256:d79aee2c3afea7ec6ffe3ac7b43481b7334a7abba51e0d4f2ed2312cd5550aeb
 size 14469

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83bfd9473be8368ac6ad0e43a10656820b148df93417308e1170b538c5843f29
+oid sha256:c918f0602d1108574e113fb8e32d725731b2c86339c03552c0229840eb091bf8
 size 14469

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:319739ad7d60d541f5641918cc521dd6473e39cc771d09fd1d8985261cc880a0
+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": 0.7426957488059998,
+      "grad_norm": 0.7302449345588684,
       "learning_rate": 0.003920764340590609,
-      "loss": 72.8711376953125,
+      "loss": 67.6101513671875,
       "step": 100
     },
     {
       "epoch": 0.1,
-      "eval_accuracy": 0.14167057673509287,
-      "eval_loss": 67.97270202636719,
-      "eval_runtime": 22.8453,
-      "eval_samples_per_second": 5.472,
+      "eval_accuracy": 0.14093548387096774,
+      "eval_loss": 62.60755157470703,
+      "eval_runtime": 22.8701,
+      "eval_samples_per_second": 5.466,
       "eval_steps_per_second": 0.175,
       "step": 100
     },
     {
       "epoch": 0.2,
-      "grad_norm": 0.8975178003311157,
+      "grad_norm": 0.8270155787467957,
       "learning_rate": 0.003650943793925548,
-      "loss": 66.589296875,
+      "loss": 61.0553955078125,
       "step": 200
     },
     {
       "epoch": 0.2,
-      "eval_accuracy": 0.14497360703812318,
-      "eval_loss": 65.53248596191406,
-      "eval_runtime": 6.8987,
-      "eval_samples_per_second": 18.119,
-      "eval_steps_per_second": 0.58,
+      "eval_accuracy": 0.14555327468230694,
+      "eval_loss": 59.78960418701172,
+      "eval_runtime": 7.035,
+      "eval_samples_per_second": 17.768,
+      "eval_steps_per_second": 0.569,
       "step": 200
     },
     {
       "epoch": 0.3,
-      "grad_norm": 0.7394354939460754,
+      "grad_norm": 0.6493133306503296,
       "learning_rate": 0.0032162636906540357,
-      "loss": 64.9186376953125,
+      "loss": 58.9980078125,
       "step": 300
     },
     {
       "epoch": 0.3,
-      "eval_accuracy": 0.14910752688172044,
-      "eval_loss": 64.25424194335938,
-      "eval_runtime": 6.8571,
-      "eval_samples_per_second": 18.229,
-      "eval_steps_per_second": 0.583,
+      "eval_accuracy": 0.15011827956989246,
+      "eval_loss": 58.25105285644531,
+      "eval_runtime": 6.9492,
+      "eval_samples_per_second": 17.988,
+      "eval_steps_per_second": 0.576,
       "step": 300
     },
     {
       "epoch": 0.4,
-      "grad_norm": 0.6404462456703186,
+      "grad_norm": 0.5908206105232239,
       "learning_rate": 0.0026601302141692667,
-      "loss": 63.8567431640625,
+      "loss": 57.7524462890625,
       "step": 400
     },
     {
       "epoch": 0.4,
-      "eval_accuracy": 0.1506871945259042,
-      "eval_loss": 63.51411056518555,
-      "eval_runtime": 6.8447,
-      "eval_samples_per_second": 18.262,
-      "eval_steps_per_second": 0.584,
+      "eval_accuracy": 0.15085630498533725,
+      "eval_loss": 57.304725646972656,
+      "eval_runtime": 6.82,
+      "eval_samples_per_second": 18.329,
+      "eval_steps_per_second": 0.587,
       "step": 400
     },
     {
       "epoch": 0.5,
-      "grad_norm": 0.809869110584259,
+      "grad_norm": 0.6619788408279419,
       "learning_rate": 0.002038077610206693,
-      "loss": 63.562841796875,
+      "loss": 57.25951171875,
       "step": 500
     },
     {
       "epoch": 0.5,
-      "eval_accuracy": 0.15301075268817205,
-      "eval_loss": 63.00912857055664,
-      "eval_runtime": 6.7809,
-      "eval_samples_per_second": 18.434,
-      "eval_steps_per_second": 0.59,
+      "eval_accuracy": 0.15302541544477027,
+      "eval_loss": 56.62392807006836,
+      "eval_runtime": 6.8533,
+      "eval_samples_per_second": 18.239,
+      "eval_steps_per_second": 0.584,
       "step": 500
-    },
-    {
-      "epoch": 0.6,
-      "grad_norm": 0.6269385814666748,
-      "learning_rate": 0.0014122226612106885,
-      "loss": 63.0276708984375,
-      "step": 600
-    },
-    {
-      "epoch": 0.6,
-      "eval_accuracy": 0.15443108504398828,
-      "eval_loss": 62.62724304199219,
-      "eval_runtime": 95.1076,
-      "eval_samples_per_second": 1.314,
-      "eval_steps_per_second": 0.042,
-      "step": 600
-    },
-    {
-      "epoch": 0.7,
-      "grad_norm": 0.6459055542945862,
-      "learning_rate": 0.0008450618433005865,
-      "loss": 62.63228515625,
-      "step": 700
-    },
-    {
-      "epoch": 0.7,
-      "eval_accuracy": 0.155544477028348,
-      "eval_loss": 62.38304138183594,
-      "eval_runtime": 6.7343,
-      "eval_samples_per_second": 18.562,
-      "eval_steps_per_second": 0.594,
-      "step": 700
-    },
-    {
-      "epoch": 0.8,
-      "grad_norm": 0.6378853917121887,
-      "learning_rate": 0.0003932305678751549,
-      "loss": 62.4295849609375,
-      "step": 800
-    },
-    {
-      "epoch": 0.8,
-      "eval_accuracy": 0.15716617790811338,
-      "eval_loss": 62.20732879638672,
-      "eval_runtime": 6.7158,
-      "eval_samples_per_second": 18.613,
-      "eval_steps_per_second": 0.596,
-      "step": 800
-    },
-    {
-      "epoch": 0.9,
-      "grad_norm": 0.7337735295295715,
-      "learning_rate": 0.00010184769603774147,
-      "loss": 62.2299755859375,
-      "step": 900
-    },
-    {
-      "epoch": 0.9,
-      "eval_accuracy": 0.15733919843597263,
-      "eval_loss": 62.13604736328125,
-      "eval_runtime": 6.7382,
-      "eval_samples_per_second": 18.551,
-      "eval_steps_per_second": 0.594,
-      "step": 900
-    },
-    {
-      "epoch": 1.0,
-      "grad_norm": 0.7058423161506653,
-      "learning_rate": 1.0069988897853933e-08,
-      "loss": 62.29814453125,
-      "step": 1000
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.1575034213098729,
-      "eval_loss": 62.122802734375,
-      "eval_runtime": 6.7003,
-      "eval_samples_per_second": 18.656,
-      "eval_steps_per_second": 0.597,
-      "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": {}
     }