Training in progress, step 2000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f6699d01f8e164228a8dd52c97ad373cf8f385ea3db3cf918436dad5dc85d09
+oid sha256:70a32488c42d94bc68537838fd59bace50bad9a491961be86f3738a6910755e4
 size 386379

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97fd4ca2baf513dd7e640129586738e37fb64c9da14592e89cd1cb308bf9e40a
+oid sha256:47fd29bde813c33926e0c9c10cf9775d231d7930b7aa4abd47133c29f24ed7c5
 size 1540661735

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:934ae4672c85df4a03b901039c48484c6d48940b666eb9da6abdadd0bfd7ca2e
+oid sha256:2a2a4adad934312ea001cd84349883cb6c15698df9bb6c090af6bf88181fb06b
 size 14469

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8e7ba67417374f28eafc52fb09cd1635fb90aeae797c287fb344cf608c324f7
+oid sha256:649e8cc37e14e4911064da2b8cb9ef2ade87f6e78d1185d4b8e5b14453b1c83d
 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:f6403efa0c30bbacae871a7df874ec4bbdb5b528b6d86d3b5609a837c3eb80b9
 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:fedd614c5b3fb7e22cbb42e3d69fcde0d7a32f2e678c37f7c99bb5a167b975e8
 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:f72141908b3038f5d527be0a4afe331900fd2cd98b763078b556a00ecca0eca1
 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:c958787b74a3aefeefe565a04ee3471c563655a4aa29b37f82c1b78d0c1b5a6c
 size 14469

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83bfd9473be8368ac6ad0e43a10656820b148df93417308e1170b538c5843f29
+oid sha256:8a198a4edc5b0a0c0735b02620e42eae859d7b0a942bf7c1a21b08b1885eff98
 size 14469

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:319739ad7d60d541f5641918cc521dd6473e39cc771d09fd1d8985261cc880a0
+oid sha256:1403f69e2c99c4fcaf2999db32c4368d388bb9ac696855db926ab4209f647997
 size 14469

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c3db7392f9c6280c917a9b32f54db3418a51b7cc8ad693de700680693a06e6b
+oid sha256:19317e67cea234fe3e615230a11e75ee190fdec27b0f95904042181fcbf16742
 size 1465

last-checkpoint/trainer_state.json

@@ -2,179 +2,177 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0,
-  "eval_steps": 100,
-  "global_step": 1000,
+  "epoch": 0.08,
+  "eval_steps": 1000,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": false,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.1,
-      "grad_norm": 1.0674346685409546,
-      "learning_rate": 0.003920764340590609,
-      "loss": 59.4722705078125,
+      "epoch": 0.004,
+      "grad_norm": 0.6785533428192139,
+      "learning_rate": 0.003999874817760761,
+      "loss": 67.455439453125,
       "step": 100
     },
     {
-      "epoch": 0.1,
-      "eval_accuracy": 0.14505767350928642,
-      "eval_loss": 57.5521240234375,
-      "eval_runtime": 23.0144,
-      "eval_samples_per_second": 5.431,
-      "eval_steps_per_second": 0.174,
-      "step": 100
+      "epoch": 0.008,
+      "grad_norm": 0.7726423144340515,
+      "learning_rate": 0.00399943549159807,
+      "loss": 60.8977392578125,
+      "step": 200
     },
     {
-      "epoch": 0.2,
-      "grad_norm": 0.8365403413772583,
-      "learning_rate": 0.003650943793925548,
-      "loss": 57.0307275390625,
-      "step": 200
+      "epoch": 0.012,
+      "grad_norm": 0.5963970422744751,
+      "learning_rate": 0.003998680178657526,
+      "loss": 58.8469140625,
+      "step": 300
     },
     {
-      "epoch": 0.2,
-      "eval_accuracy": 0.14682111436950146,
-      "eval_loss": 56.763153076171875,
-      "eval_runtime": 6.889,
-      "eval_samples_per_second": 18.145,
-      "eval_steps_per_second": 0.581,
-      "step": 200
+      "epoch": 0.016,
+      "grad_norm": 0.5085615515708923,
+      "learning_rate": 0.003997608998307273,
+      "loss": 57.544306640625,
+      "step": 400
     },
     {
-      "epoch": 0.3,
-      "grad_norm": 0.6420626044273376,
-      "learning_rate": 0.0032162636906540357,
-      "loss": 56.4287109375,
-      "step": 300
+      "epoch": 0.02,
+      "grad_norm": 0.5642688870429993,
+      "learning_rate": 0.003996222119834506,
+      "loss": 56.976044921875,
+      "step": 500
     },
     {
-      "epoch": 0.3,
-      "eval_accuracy": 0.15105865102639296,
-      "eval_loss": 56.29315185546875,
-      "eval_runtime": 7.4741,
-      "eval_samples_per_second": 16.724,
-      "eval_steps_per_second": 0.535,
-      "step": 300
+      "epoch": 0.024,
+      "grad_norm": 0.47304418683052063,
+      "learning_rate": 0.003994519762418718,
+      "loss": 56.1641748046875,
+      "step": 600
     },
     {
-      "epoch": 0.4,
-      "grad_norm": 0.6022240519523621,
-      "learning_rate": 0.0026601302141692667,
-      "loss": 56.0290380859375,
-      "step": 400
+      "epoch": 0.028,
+      "grad_norm": 0.45104825496673584,
+      "learning_rate": 0.003992502195097064,
+      "loss": 55.4853173828125,
+      "step": 700
     },
     {
-      "epoch": 0.4,
-      "eval_accuracy": 0.1521642228739003,
-      "eval_loss": 55.97286605834961,
-      "eval_runtime": 6.9186,
-      "eval_samples_per_second": 18.067,
-      "eval_steps_per_second": 0.578,
-      "step": 400
+      "epoch": 0.032,
+      "grad_norm": 0.5336799621582031,
+      "learning_rate": 0.00399016973672184,
+      "loss": 54.9941357421875,
+      "step": 800
     },
     {
-      "epoch": 0.5,
-      "grad_norm": 0.6007410287857056,
-      "learning_rate": 0.002038077610206693,
-      "loss": 56.0603759765625,
-      "step": 500
+      "epoch": 0.036,
+      "grad_norm": 0.5774248242378235,
+      "learning_rate": 0.0039875227559100935,
+      "loss": 54.54736328125,
+      "step": 900
     },
     {
-      "epoch": 0.5,
-      "eval_accuracy": 0.15361681329423266,
-      "eval_loss": 55.698612213134766,
-      "eval_runtime": 6.7281,
-      "eval_samples_per_second": 18.579,
-      "eval_steps_per_second": 0.595,
-      "step": 500
+      "epoch": 0.04,
+      "grad_norm": 0.7312104105949402,
+      "learning_rate": 0.003984561670985366,
+      "loss": 54.2763134765625,
+      "step": 1000
     },
     {
-      "epoch": 0.6,
-      "grad_norm": 0.5756194591522217,
-      "learning_rate": 0.0014122226612106885,
-      "loss": 55.7325390625,
-      "step": 600
+      "epoch": 0.04,
+      "eval_accuracy": 0.1520635386119257,
+      "eval_loss": 53.98247146606445,
+      "eval_runtime": 23.3511,
+      "eval_samples_per_second": 5.353,
+      "eval_steps_per_second": 0.171,
+      "step": 1000
     },
     {
-      "epoch": 0.6,
-      "eval_accuracy": 0.15486021505376343,
-      "eval_loss": 55.48189163208008,
-      "eval_runtime": 6.8292,
-      "eval_samples_per_second": 18.304,
-      "eval_steps_per_second": 0.586,
-      "step": 600
+      "epoch": 0.044,
+      "grad_norm": 0.6063086986541748,
+      "learning_rate": 0.003981286949911586,
+      "loss": 53.98443359375,
+      "step": 1100
     },
     {
-      "epoch": 0.7,
-      "grad_norm": 0.5742236375808716,
-      "learning_rate": 0.0008450618433005865,
-      "loss": 55.4351513671875,
-      "step": 700
+      "epoch": 0.048,
+      "grad_norm": 0.39948800206184387,
+      "learning_rate": 0.003977699110219106,
+      "loss": 53.585517578125,
+      "step": 1200
     },
     {
-      "epoch": 0.7,
-      "eval_accuracy": 0.15646823069403715,
-      "eval_loss": 55.330833435058594,
-      "eval_runtime": 6.8567,
-      "eval_samples_per_second": 18.23,
-      "eval_steps_per_second": 0.583,
-      "step": 700
+      "epoch": 0.052,
+      "grad_norm": 0.5279461145401001,
+      "learning_rate": 0.0039737987189229235,
+      "loss": 53.4054736328125,
+      "step": 1300
     },
     {
-      "epoch": 0.8,
-      "grad_norm": 0.5711455345153809,
-      "learning_rate": 0.0003932305678751549,
-      "loss": 55.313212890625,
-      "step": 800
+      "epoch": 0.056,
+      "grad_norm": 0.7522546648979187,
+      "learning_rate": 0.00396958639243306,
+      "loss": 53.0430322265625,
+      "step": 1400
     },
     {
-      "epoch": 0.8,
-      "eval_accuracy": 0.1573030303030303,
-      "eval_loss": 55.21982192993164,
-      "eval_runtime": 6.7731,
-      "eval_samples_per_second": 18.455,
-      "eval_steps_per_second": 0.591,
-      "step": 800
+      "epoch": 0.06,
+      "grad_norm": 0.7735885381698608,
+      "learning_rate": 0.003965062796457152,
+      "loss": 52.7428564453125,
+      "step": 1500
     },
     {
-      "epoch": 0.9,
-      "grad_norm": 0.65065997838974,
-      "learning_rate": 0.00010184769603774147,
-      "loss": 55.213203125,
-      "step": 900
+      "epoch": 0.064,
+      "grad_norm": 0.7539300322532654,
+      "learning_rate": 0.0039602286458952415,
+      "loss": 52.66658203125,
+      "step": 1600
     },
     {
-      "epoch": 0.9,
-      "eval_accuracy": 0.15794916911045942,
-      "eval_loss": 55.16655731201172,
-      "eval_runtime": 6.6852,
-      "eval_samples_per_second": 18.698,
-      "eval_steps_per_second": 0.598,
-      "step": 900
+      "epoch": 0.068,
+      "grad_norm": 0.49980393052101135,
+      "learning_rate": 0.0039550847047267945,
+      "loss": 52.561875,
+      "step": 1700
     },
     {
-      "epoch": 1.0,
-      "grad_norm": 0.6348595023155212,
-      "learning_rate": 1.0069988897853933e-08,
-      "loss": 55.2790576171875,
-      "step": 1000
+      "epoch": 0.072,
+      "grad_norm": 0.8233217000961304,
+      "learning_rate": 0.0039496317858899645,
+      "loss": 52.1762646484375,
+      "step": 1800
     },
     {
-      "epoch": 1.0,
-      "eval_accuracy": 0.15813000977517105,
-      "eval_loss": 55.15705490112305,
-      "eval_runtime": 6.7487,
-      "eval_samples_per_second": 18.522,
-      "eval_steps_per_second": 0.593,
-      "step": 1000
+      "epoch": 0.076,
+      "grad_norm": 0.5626161098480225,
+      "learning_rate": 0.003943870751153116,
+      "loss": 51.989736328125,
+      "step": 1900
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.6408643126487732,
+      "learning_rate": 0.003937802510978631,
+      "loss": 51.8978759765625,
+      "step": 2000
+    },
+    {
+      "epoch": 0.08,
+      "eval_accuracy": 0.15603128054740958,
+      "eval_loss": 51.726192474365234,
+      "eval_runtime": 7.2542,
+      "eval_samples_per_second": 17.231,
+      "eval_steps_per_second": 0.551,
+      "step": 2000
     }
   ],
   "logging_steps": 100,
-  "max_steps": 1000,
+  "max_steps": 25000,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 9223372036854775807,
-  "save_steps": 500,
+  "save_steps": 2000,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -182,7 +180,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ca316f954a0e91646cfe7cc48ead82990c29283d2e6825936de0377c3707c2e
+oid sha256:249f6f32e73d3d59f6736409b63eee22371849afb3a7101dfad4569505bfb4ec
 size 5265