Training in progress, step 144000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e528c6c1b38d449e40b06d563d76337ed30bb24cacbc90843816395861ab462e
+oid sha256:0c6c980ace5ce0a4fd3625a02e163df067832f4ff0cce1c1c305ee9d44e17b3b
 size 1410301944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7dc082548c7bfdcda4f8c228b87c8eba1d0b5666e8a39c580420710f8f1e16a
+oid sha256:fd3b39bcee85f2c89b3dd95a7ec3fbeee713f0e76059470f8cf9bb3b9084c3b2
 size 2820185786

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a31a1a268b6d8e9e36fe132f59bcf8012ab5c9e2211775c5a946cf61b12f44e3
+oid sha256:d150d74b6234978f1de50d9684bb41dd3c162274dba720cabd22f3c0df64b646
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41022723a27fbe2eda17c7ebe85c85f4b5c49611a755e2224ace9da8956099df
+oid sha256:62e501f63b681f89119727a00e92acc6c6fd02c59ff9044b7e19b90a76e351b2
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.1411978228890445,
+  "epoch": 3.1631638812103025,
   "eval_steps": 500,
-  "global_step": 143000,
+  "global_step": 144000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -25462,11 +25462,189 @@
       "eval_steps_per_second": 15.476,
       "num_input_tokens_seen": 76534108256,
       "step": 143000
+    },
+    {
+      "epoch": 3.1422961258051076,
+      "grad_norm": 0.0887688547372818,
+      "learning_rate": 0.0001,
+      "loss": 2.3614,
+      "num_input_tokens_seen": 76586530944,
+      "step": 143050
+    },
+    {
+      "epoch": 3.1433944287211704,
+      "grad_norm": 0.09098675847053528,
+      "learning_rate": 0.0001,
+      "loss": 2.3579,
+      "num_input_tokens_seen": 76638954624,
+      "step": 143100
+    },
+    {
+      "epoch": 3.144492731637233,
+      "grad_norm": 0.0879465788602829,
+      "learning_rate": 0.0001,
+      "loss": 2.3544,
+      "num_input_tokens_seen": 76691382816,
+      "step": 143150
+    },
+    {
+      "epoch": 3.1455910345532963,
+      "grad_norm": 0.09020204097032547,
+      "learning_rate": 0.0001,
+      "loss": 2.3608,
+      "num_input_tokens_seen": 76743811616,
+      "step": 143200
+    },
+    {
+      "epoch": 3.146689337469359,
+      "grad_norm": 0.0859370082616806,
+      "learning_rate": 0.0001,
+      "loss": 2.3572,
+      "num_input_tokens_seen": 76796240416,
+      "step": 143250
+    },
+    {
+      "epoch": 3.147787640385422,
+      "grad_norm": 0.08659014105796814,
+      "learning_rate": 0.0001,
+      "loss": 2.3513,
+      "num_input_tokens_seen": 76848663776,
+      "step": 143300
+    },
+    {
+      "epoch": 3.148885943301485,
+      "grad_norm": 0.09119068831205368,
+      "learning_rate": 0.0001,
+      "loss": 2.3591,
+      "num_input_tokens_seen": 76901090432,
+      "step": 143350
+    },
+    {
+      "epoch": 3.1499842462175476,
+      "grad_norm": 0.08679833263158798,
+      "learning_rate": 0.0001,
+      "loss": 2.3462,
+      "num_input_tokens_seen": 76953519232,
+      "step": 143400
+    },
+    {
+      "epoch": 3.1510825491336107,
+      "grad_norm": 0.09158121794462204,
+      "learning_rate": 0.0001,
+      "loss": 2.354,
+      "num_input_tokens_seen": 77005948032,
+      "step": 143450
+    },
+    {
+      "epoch": 3.1521808520496735,
+      "grad_norm": 0.08906587958335876,
+      "learning_rate": 0.0001,
+      "loss": 2.3582,
+      "num_input_tokens_seen": 77058376736,
+      "step": 143500
+    },
+    {
+      "epoch": 3.1521808520496735,
+      "eval_loss": 2.2670507431030273,
+      "eval_runtime": 80.7537,
+      "eval_samples_per_second": 61.917,
+      "eval_steps_per_second": 15.479,
+      "num_input_tokens_seen": 77058376736,
+      "step": 143500
+    },
+    {
+      "epoch": 3.153279154965736,
+      "grad_norm": 0.09259413182735443,
+      "learning_rate": 0.0001,
+      "loss": 2.3501,
+      "num_input_tokens_seen": 77110805536,
+      "step": 143550
+    },
+    {
+      "epoch": 3.1543774578817994,
+      "grad_norm": 0.08947575837373734,
+      "learning_rate": 0.0001,
+      "loss": 2.3595,
+      "num_input_tokens_seen": 77163233984,
+      "step": 143600
+    },
+    {
+      "epoch": 3.155475760797862,
+      "grad_norm": 0.09320012480020523,
+      "learning_rate": 0.0001,
+      "loss": 2.3566,
+      "num_input_tokens_seen": 77215662784,
+      "step": 143650
+    },
+    {
+      "epoch": 3.1565740637139252,
+      "grad_norm": 0.09630698710680008,
+      "learning_rate": 0.0001,
+      "loss": 2.3619,
+      "num_input_tokens_seen": 77268081952,
+      "step": 143700
+    },
+    {
+      "epoch": 3.157672366629988,
+      "grad_norm": 0.08778363466262817,
+      "learning_rate": 0.0001,
+      "loss": 2.3565,
+      "num_input_tokens_seen": 77320510752,
+      "step": 143750
+    },
+    {
+      "epoch": 3.1587706695460507,
+      "grad_norm": 0.08947426080703735,
+      "learning_rate": 0.0001,
+      "loss": 2.3497,
+      "num_input_tokens_seen": 77372937824,
+      "step": 143800
+    },
+    {
+      "epoch": 3.159868972462114,
+      "grad_norm": 0.09249094128608704,
+      "learning_rate": 0.0001,
+      "loss": 2.3508,
+      "num_input_tokens_seen": 77425366624,
+      "step": 143850
+    },
+    {
+      "epoch": 3.1609672753781766,
+      "grad_norm": 0.09168736636638641,
+      "learning_rate": 0.0001,
+      "loss": 2.3522,
+      "num_input_tokens_seen": 77477795424,
+      "step": 143900
+    },
+    {
+      "epoch": 3.1620655782942393,
+      "grad_norm": 0.08995141088962555,
+      "learning_rate": 0.0001,
+      "loss": 2.3506,
+      "num_input_tokens_seen": 77530222464,
+      "step": 143950
+    },
+    {
+      "epoch": 3.1631638812103025,
+      "grad_norm": 0.09521841257810593,
+      "learning_rate": 0.0001,
+      "loss": 2.3521,
+      "num_input_tokens_seen": 77582650016,
+      "step": 144000
+    },
+    {
+      "epoch": 3.1631638812103025,
+      "eval_loss": 2.266408920288086,
+      "eval_runtime": 80.1189,
+      "eval_samples_per_second": 62.407,
+      "eval_steps_per_second": 15.602,
+      "num_input_tokens_seen": 77582650016,
+      "step": 144000
     }
   ],
   "logging_steps": 50,
   "max_steps": 200000,
-  "num_input_tokens_seen": 76534108256,
+  "num_input_tokens_seen": 77582650016,
   "num_train_epochs": 5,
   "save_steps": 1000,
   "stateful_callbacks": {
@@ -25481,7 +25659,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.354514117917741e+20,
+  "total_flos": 1.3730713945295708e+20,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null