Training in progress, step 145000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c6c980ace5ce0a4fd3625a02e163df067832f4ff0cce1c1c305ee9d44e17b3b
+oid sha256:dcc52c805127340a99efe5ce4634aa8da5f6e99e5d84b192bcdfc15db598aaa1
 size 1410301944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd3b39bcee85f2c89b3dd95a7ec3fbeee713f0e76059470f8cf9bb3b9084c3b2
+oid sha256:812ced3f153ff459210c79eeaaaf6df9526ae07f07422480db83a62f6a3959ea
 size 2820185786

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d150d74b6234978f1de50d9684bb41dd3c162274dba720cabd22f3c0df64b646
+oid sha256:e715b06ff1678ef9784950709f202e66ee53f0a61201e7828fbeb571b860f735
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62e501f63b681f89119727a00e92acc6c6fd02c59ff9044b7e19b90a76e351b2
+oid sha256:9f13aa126d87289d9b7a69890efa6e557270dd33d7688495b067f1fc28a57da6
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.1631638812103025,
+  "epoch": 3.18512993953156,
   "eval_steps": 500,
-  "global_step": 144000,
+  "global_step": 145000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -25640,11 +25640,189 @@
       "eval_steps_per_second": 15.602,
       "num_input_tokens_seen": 77582650016,
       "step": 144000
+    },
+    {
+      "epoch": 3.164262184126365,
+      "grad_norm": 0.11045259982347488,
+      "learning_rate": 0.0001,
+      "loss": 2.3539,
+      "num_input_tokens_seen": 77635078816,
+      "step": 144050
+    },
+    {
+      "epoch": 3.1653604870424283,
+      "grad_norm": 0.09217249602079391,
+      "learning_rate": 0.0001,
+      "loss": 2.343,
+      "num_input_tokens_seen": 77687507616,
+      "step": 144100
+    },
+    {
+      "epoch": 3.166458789958491,
+      "grad_norm": 0.09735982865095139,
+      "learning_rate": 0.0001,
+      "loss": 2.3519,
+      "num_input_tokens_seen": 77739935872,
+      "step": 144150
+    },
+    {
+      "epoch": 3.167557092874554,
+      "grad_norm": 0.08962323516607285,
+      "learning_rate": 0.0001,
+      "loss": 2.3473,
+      "num_input_tokens_seen": 77792364672,
+      "step": 144200
+    },
+    {
+      "epoch": 3.168655395790617,
+      "grad_norm": 0.09209229052066803,
+      "learning_rate": 0.0001,
+      "loss": 2.3555,
+      "num_input_tokens_seen": 77844789440,
+      "step": 144250
+    },
+    {
+      "epoch": 3.1697536987066797,
+      "grad_norm": 0.09181981533765793,
+      "learning_rate": 0.0001,
+      "loss": 2.348,
+      "num_input_tokens_seen": 77897216224,
+      "step": 144300
+    },
+    {
+      "epoch": 3.1708520016227424,
+      "grad_norm": 0.0833621546626091,
+      "learning_rate": 0.0001,
+      "loss": 2.3454,
+      "num_input_tokens_seen": 77949645024,
+      "step": 144350
+    },
+    {
+      "epoch": 3.1719503045388056,
+      "grad_norm": 0.09470181167125702,
+      "learning_rate": 0.0001,
+      "loss": 2.3491,
+      "num_input_tokens_seen": 78002073440,
+      "step": 144400
+    },
+    {
+      "epoch": 3.1730486074548683,
+      "grad_norm": 0.09017711132764816,
+      "learning_rate": 0.0001,
+      "loss": 2.3545,
+      "num_input_tokens_seen": 78054502240,
+      "step": 144450
+    },
+    {
+      "epoch": 3.174146910370931,
+      "grad_norm": 0.09220907092094421,
+      "learning_rate": 0.0001,
+      "loss": 2.3508,
+      "num_input_tokens_seen": 78106920224,
+      "step": 144500
+    },
+    {
+      "epoch": 3.174146910370931,
+      "eval_loss": 2.2662734985351562,
+      "eval_runtime": 80.1838,
+      "eval_samples_per_second": 62.357,
+      "eval_steps_per_second": 15.589,
+      "num_input_tokens_seen": 78106920224,
+      "step": 144500
+    },
+    {
+      "epoch": 3.175245213286994,
+      "grad_norm": 0.0899912640452385,
+      "learning_rate": 0.0001,
+      "loss": 2.3607,
+      "num_input_tokens_seen": 78159346816,
+      "step": 144550
+    },
+    {
+      "epoch": 3.176343516203057,
+      "grad_norm": 0.09542039781808853,
+      "learning_rate": 0.0001,
+      "loss": 2.3405,
+      "num_input_tokens_seen": 78211775616,
+      "step": 144600
+    },
+    {
+      "epoch": 3.17744181911912,
+      "grad_norm": 0.09049233049154282,
+      "learning_rate": 0.0001,
+      "loss": 2.3483,
+      "num_input_tokens_seen": 78264204032,
+      "step": 144650
+    },
+    {
+      "epoch": 3.1785401220351828,
+      "grad_norm": 0.09777910262346268,
+      "learning_rate": 0.0001,
+      "loss": 2.3514,
+      "num_input_tokens_seen": 78316631456,
+      "step": 144700
+    },
+    {
+      "epoch": 3.1796384249512455,
+      "grad_norm": 0.09022051095962524,
+      "learning_rate": 0.0001,
+      "loss": 2.3531,
+      "num_input_tokens_seen": 78369060192,
+      "step": 144750
+    },
+    {
+      "epoch": 3.1807367278673087,
+      "grad_norm": 0.09529806673526764,
+      "learning_rate": 0.0001,
+      "loss": 2.3531,
+      "num_input_tokens_seen": 78421488992,
+      "step": 144800
+    },
+    {
+      "epoch": 3.1818350307833714,
+      "grad_norm": 0.08957728743553162,
+      "learning_rate": 0.0001,
+      "loss": 2.3554,
+      "num_input_tokens_seen": 78473915424,
+      "step": 144850
+    },
+    {
+      "epoch": 3.182933333699434,
+      "grad_norm": 0.09089584648609161,
+      "learning_rate": 0.0001,
+      "loss": 2.34,
+      "num_input_tokens_seen": 78526342656,
+      "step": 144900
+    },
+    {
+      "epoch": 3.1840316366154973,
+      "grad_norm": 0.09180238097906113,
+      "learning_rate": 0.0001,
+      "loss": 2.3542,
+      "num_input_tokens_seen": 78578771456,
+      "step": 144950
+    },
+    {
+      "epoch": 3.18512993953156,
+      "grad_norm": 0.09355945885181427,
+      "learning_rate": 0.0001,
+      "loss": 2.3581,
+      "num_input_tokens_seen": 78631193376,
+      "step": 145000
+    },
+    {
+      "epoch": 3.18512993953156,
+      "eval_loss": 2.2656116485595703,
+      "eval_runtime": 80.4625,
+      "eval_samples_per_second": 62.141,
+      "eval_steps_per_second": 15.535,
+      "num_input_tokens_seen": 78631193376,
+      "step": 145000
     }
   ],
   "logging_steps": 50,
   "max_steps": 200000,
-  "num_input_tokens_seen": 77582650016,
+  "num_input_tokens_seen": 78631193376,
   "num_train_epochs": 5,
   "save_steps": 1000,
   "stateful_callbacks": {
@@ -25659,7 +25837,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3730713945295708e+20,
+  "total_flos": 1.3916286994584822e+20,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null