Training in progress, step 1000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69ca6905e70e7a92d02eeddbdeb7103009b83d9f0f234789efb4904d68ed5838
+oid sha256:4f6699d01f8e164228a8dd52c97ad373cf8f385ea3db3cf918436dad5dc85d09
 size 386379

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82cc3acf680d85a95964b4366417613a590457a2020ce3a7574762bb50f5df4d
+oid sha256:97fd4ca2baf513dd7e640129586738e37fb64c9da14592e89cd1cb308bf9e40a
 size 1540661735

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88b48f43625e8919759a700846736ad1c67a9fb02b424ca27c045fdf11ebec4d
+oid sha256:934ae4672c85df4a03b901039c48484c6d48940b666eb9da6abdadd0bfd7ca2e
 size 14469

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3df8bbf0aa54958cebb063d8843254a6ca7fa9a4ecc3a91470b305106963beb
+oid sha256:f8e7ba67417374f28eafc52fb09cd1635fb90aeae797c287fb344cf608c324f7
 size 14469

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c2aba2784b08e863f59f03cfa3309c63893fb49cde8f0070f10410339e4d7fd
+oid sha256:b34aebebdff0fa5078105ea2165525a062f2af01267a2bc4a5277f926a1ddf87
 size 14469

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:827e90af5517da4bb9113a66cb2136b09f8d4c852d96861d993b1d3b68201f38
+oid sha256:bbad142d3225fe2301edd7a4526b586614f8cdf35859a150aa76ce623d42e698
 size 14469

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4db1556f9cda170711f81bfb9343feab14e545a26997a7968c5820a578a542c7
+oid sha256:08730831ebd5924954c36016585e26ed2876b02574126a5a7953c60d82be5570
 size 14469

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:165ab5fc90c8c3dd2e6e924be06814806faf1d60acb8d14cc4b0676f6f5737f1
+oid sha256:7d18edd5743601b28a2cec06aa40d0c6c594939906326809da6ebe1722314306
 size 14469

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:017ce61066c39ae46b1e2925435311fe07b1d409bfd8cdcf79a1c7f1a9b9127b
+oid sha256:83bfd9473be8368ac6ad0e43a10656820b148df93417308e1170b538c5843f29
 size 14469

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64b97a485d2b1a72ff869a0ba55eed82c522e3229735d8894bfab7c67a78fe16
+oid sha256:319739ad7d60d541f5641918cc521dd6473e39cc771d09fd1d8985261cc880a0
 size 14469

last-checkpoint/scheduler.pt

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

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5,
+  "epoch": 1.0,
   "eval_steps": 100,
-  "global_step": 500,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": false,
   "is_world_process_zero": true,
@@ -88,6 +88,86 @@
       "eval_samples_per_second": 18.579,
       "eval_steps_per_second": 0.595,
       "step": 500
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.5756194591522217,
+      "learning_rate": 0.0014122226612106885,
+      "loss": 55.7325390625,
+      "step": 600
+    },
+    {
+      "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": 0.7,
+      "grad_norm": 0.5742236375808716,
+      "learning_rate": 0.0008450618433005865,
+      "loss": 55.4351513671875,
+      "step": 700
+    },
+    {
+      "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": 0.8,
+      "grad_norm": 0.5711455345153809,
+      "learning_rate": 0.0003932305678751549,
+      "loss": 55.313212890625,
+      "step": 800
+    },
+    {
+      "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": 0.9,
+      "grad_norm": 0.65065997838974,
+      "learning_rate": 0.00010184769603774147,
+      "loss": 55.213203125,
+      "step": 900
+    },
+    {
+      "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": 1.0,
+      "grad_norm": 0.6348595023155212,
+      "learning_rate": 1.0069988897853933e-08,
+      "loss": 55.2790576171875,
+      "step": 1000
+    },
+    {
+      "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
     }
   ],
   "logging_steps": 100,
@@ -102,7 +182,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }