Training in progress, step 146000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcc52c805127340a99efe5ce4634aa8da5f6e99e5d84b192bcdfc15db598aaa1
+oid sha256:b48962ccd06eb3192807ae180f3dd6456f58a152aca65272f73edef4ffb683b1
 size 1410301944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:812ced3f153ff459210c79eeaaaf6df9526ae07f07422480db83a62f6a3959ea
+oid sha256:b3d5eadedde8bbebfeb26d921d794383a8385f17f0c6cc8fb0d00c68ea258e51
 size 2820185786

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e715b06ff1678ef9784950709f202e66ee53f0a61201e7828fbeb571b860f735
+oid sha256:51ce9c28a9aa67295d292ad1d8dd89b97ebe967bdf87ecd07447ea36283dbcee
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f13aa126d87289d9b7a69890efa6e557270dd33d7688495b067f1fc28a57da6
+oid sha256:72d1a00336735d13d964c93acea54e818b3d9e40f5ee9551f0bf68590d438f6f
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.18512993953156,
+  "epoch": 3.207095997852818,
   "eval_steps": 500,
-  "global_step": 145000,
+  "global_step": 146000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -25818,11 +25818,189 @@
       "eval_steps_per_second": 15.535,
       "num_input_tokens_seen": 78631193376,
       "step": 145000
+    },
+    {
+      "epoch": 3.186228242447623,
+      "grad_norm": 0.09815175086259842,
+      "learning_rate": 0.0001,
+      "loss": 2.3512,
+      "num_input_tokens_seen": 78683622176,
+      "step": 145050
+    },
+    {
+      "epoch": 3.187326545363686,
+      "grad_norm": 0.08802150189876556,
+      "learning_rate": 0.0001,
+      "loss": 2.352,
+      "num_input_tokens_seen": 78736048064,
+      "step": 145100
+    },
+    {
+      "epoch": 3.1884248482797486,
+      "grad_norm": 0.09322452545166016,
+      "learning_rate": 0.0001,
+      "loss": 2.3517,
+      "num_input_tokens_seen": 78788476864,
+      "step": 145150
+    },
+    {
+      "epoch": 3.1895231511958118,
+      "grad_norm": 0.09273571521043777,
+      "learning_rate": 0.0001,
+      "loss": 2.3525,
+      "num_input_tokens_seen": 78840905664,
+      "step": 145200
+    },
+    {
+      "epoch": 3.1906214541118745,
+      "grad_norm": 0.09510285407304764,
+      "learning_rate": 0.0001,
+      "loss": 2.3492,
+      "num_input_tokens_seen": 78893334464,
+      "step": 145250
+    },
+    {
+      "epoch": 3.191719757027937,
+      "grad_norm": 0.09299364686012268,
+      "learning_rate": 0.0001,
+      "loss": 2.3485,
+      "num_input_tokens_seen": 78945760672,
+      "step": 145300
+    },
+    {
+      "epoch": 3.1928180599440004,
+      "grad_norm": 0.08893129974603653,
+      "learning_rate": 0.0001,
+      "loss": 2.3529,
+      "num_input_tokens_seen": 78998188864,
+      "step": 145350
+    },
+    {
+      "epoch": 3.193916362860063,
+      "grad_norm": 0.08949380367994308,
+      "learning_rate": 0.0001,
+      "loss": 2.3563,
+      "num_input_tokens_seen": 79050616800,
+      "step": 145400
+    },
+    {
+      "epoch": 3.1950146657761263,
+      "grad_norm": 0.09386907517910004,
+      "learning_rate": 0.0001,
+      "loss": 2.3454,
+      "num_input_tokens_seen": 79103043296,
+      "step": 145450
+    },
+    {
+      "epoch": 3.196112968692189,
+      "grad_norm": 0.10135660320520401,
+      "learning_rate": 0.0001,
+      "loss": 2.3521,
+      "num_input_tokens_seen": 79155472096,
+      "step": 145500
+    },
+    {
+      "epoch": 3.196112968692189,
+      "eval_loss": 2.2653002738952637,
+      "eval_runtime": 80.3673,
+      "eval_samples_per_second": 62.214,
+      "eval_steps_per_second": 15.554,
+      "num_input_tokens_seen": 79155472096,
+      "step": 145500
+    },
+    {
+      "epoch": 3.1972112716082517,
+      "grad_norm": 0.09017980098724365,
+      "learning_rate": 0.0001,
+      "loss": 2.3576,
+      "num_input_tokens_seen": 79207895552,
+      "step": 145550
+    },
+    {
+      "epoch": 3.198309574524315,
+      "grad_norm": 0.10214512050151825,
+      "learning_rate": 0.0001,
+      "loss": 2.3512,
+      "num_input_tokens_seen": 79260320832,
+      "step": 145600
+    },
+    {
+      "epoch": 3.1994078774403776,
+      "grad_norm": 0.08758047223091125,
+      "learning_rate": 0.0001,
+      "loss": 2.347,
+      "num_input_tokens_seen": 79312749152,
+      "step": 145650
+    },
+    {
+      "epoch": 3.2005061803564403,
+      "grad_norm": 0.09964236617088318,
+      "learning_rate": 0.0001,
+      "loss": 2.3466,
+      "num_input_tokens_seen": 79365177440,
+      "step": 145700
+    },
+    {
+      "epoch": 3.2016044832725035,
+      "grad_norm": 0.10335622727870941,
+      "learning_rate": 0.0001,
+      "loss": 2.3492,
+      "num_input_tokens_seen": 79417604928,
+      "step": 145750
+    },
+    {
+      "epoch": 3.202702786188566,
+      "grad_norm": 0.09493719041347504,
+      "learning_rate": 0.0001,
+      "loss": 2.3547,
+      "num_input_tokens_seen": 79470031232,
+      "step": 145800
+    },
+    {
+      "epoch": 3.203801089104629,
+      "grad_norm": 0.0902167409658432,
+      "learning_rate": 0.0001,
+      "loss": 2.3449,
+      "num_input_tokens_seen": 79522455456,
+      "step": 145850
+    },
+    {
+      "epoch": 3.204899392020692,
+      "grad_norm": 0.09135492146015167,
+      "learning_rate": 0.0001,
+      "loss": 2.3535,
+      "num_input_tokens_seen": 79574884256,
+      "step": 145900
+    },
+    {
+      "epoch": 3.205997694936755,
+      "grad_norm": 0.09141404926776886,
+      "learning_rate": 0.0001,
+      "loss": 2.3482,
+      "num_input_tokens_seen": 79627304576,
+      "step": 145950
+    },
+    {
+      "epoch": 3.207095997852818,
+      "grad_norm": 0.08859889209270477,
+      "learning_rate": 0.0001,
+      "loss": 2.3585,
+      "num_input_tokens_seen": 79679733376,
+      "step": 146000
+    },
+    {
+      "epoch": 3.207095997852818,
+      "eval_loss": 2.264711618423462,
+      "eval_runtime": 80.4702,
+      "eval_samples_per_second": 62.135,
+      "eval_steps_per_second": 15.534,
+      "num_input_tokens_seen": 79679733376,
+      "step": 146000
     }
   ],
   "logging_steps": 50,
   "max_steps": 200000,
-  "num_input_tokens_seen": 78631193376,
+  "num_input_tokens_seen": 79679733376,
   "num_train_epochs": 5,
   "save_steps": 1000,
   "stateful_callbacks": {
@@ -25837,7 +26015,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3916286994584822e+20,
+  "total_flos": 1.4101859449215222e+20,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null