Training in progress, step 46000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3ffbf5a816a6aa824466bdde4390b737dfef3183acb26f39844f7b4017bf30d
+oid sha256:aa89571eb3340eba1a67ab65cc95a52de52c688ab135a582ba9671de6b4b9b2b
 size 301235464

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6b19fbbf1f84052b99affd1a4abf045aa0dc4dae5e3396c29093fc71d96182f
+oid sha256:ee8593e17fbb590b6be9983a2252f2eb629b591782e538eabf2da48b5e3443f7
 size 602335994

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2efdaece0c1a392cf0dde4c3fd595f174e50c13358c4a6e5301669f684c3b3b
+oid sha256:3fdfef9e83b1fd0865026b3e547285feb0ce1b439ee58282cde4fbaa3e21a682
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4373b3ab47408a8ab65ab61c7aee7bfdf3c940344f36a198973da2bfc9da86a8
+oid sha256:c85b77405559b6f9d3b974ee441baee89ea00505d86e9a6015f23da9cbeb2cb5
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2146511322847228,
+  "epoch": 0.21942115744660554,
   "eval_steps": 500,
-  "global_step": 45000,
+  "global_step": 46000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8018,11 +8018,189 @@
       "eval_steps_per_second": 24.43,
       "num_input_tokens_seen": 11796475456,
       "step": 45000
+    },
+    {
+      "epoch": 0.21488963354281693,
+      "grad_norm": 0.226406991481781,
+      "learning_rate": 0.001,
+      "loss": 2.626,
+      "num_input_tokens_seen": 11809582656,
+      "step": 45050
+    },
+    {
+      "epoch": 0.21512813480091109,
+      "grad_norm": 0.20505741238594055,
+      "learning_rate": 0.001,
+      "loss": 2.6095,
+      "num_input_tokens_seen": 11822689856,
+      "step": 45100
+    },
+    {
+      "epoch": 0.21536663605900522,
+      "grad_norm": 0.2917146682739258,
+      "learning_rate": 0.001,
+      "loss": 2.6439,
+      "num_input_tokens_seen": 11835797056,
+      "step": 45150
+    },
+    {
+      "epoch": 0.21560513731709935,
+      "grad_norm": 0.24030283093452454,
+      "learning_rate": 0.001,
+      "loss": 2.6386,
+      "num_input_tokens_seen": 11848904256,
+      "step": 45200
+    },
+    {
+      "epoch": 0.21584363857519348,
+      "grad_norm": 0.1799454241991043,
+      "learning_rate": 0.001,
+      "loss": 2.6344,
+      "num_input_tokens_seen": 11862011456,
+      "step": 45250
+    },
+    {
+      "epoch": 0.2160821398332876,
+      "grad_norm": 0.2093718945980072,
+      "learning_rate": 0.001,
+      "loss": 2.6152,
+      "num_input_tokens_seen": 11875118656,
+      "step": 45300
+    },
+    {
+      "epoch": 0.21632064109138174,
+      "grad_norm": 0.19477079808712006,
+      "learning_rate": 0.001,
+      "loss": 2.622,
+      "num_input_tokens_seen": 11888225856,
+      "step": 45350
+    },
+    {
+      "epoch": 0.2165591423494759,
+      "grad_norm": 0.2764741778373718,
+      "learning_rate": 0.001,
+      "loss": 2.5951,
+      "num_input_tokens_seen": 11901333056,
+      "step": 45400
+    },
+    {
+      "epoch": 0.21679764360757003,
+      "grad_norm": 0.2127208709716797,
+      "learning_rate": 0.001,
+      "loss": 2.6231,
+      "num_input_tokens_seen": 11914440256,
+      "step": 45450
+    },
+    {
+      "epoch": 0.21703614486566417,
+      "grad_norm": 0.21089383959770203,
+      "learning_rate": 0.001,
+      "loss": 2.6099,
+      "num_input_tokens_seen": 11927547456,
+      "step": 45500
+    },
+    {
+      "epoch": 0.21703614486566417,
+      "eval_loss": 2.502464771270752,
+      "eval_runtime": 50.946,
+      "eval_samples_per_second": 98.143,
+      "eval_steps_per_second": 24.536,
+      "num_input_tokens_seen": 11927547456,
+      "step": 45500
+    },
+    {
+      "epoch": 0.2172746461237583,
+      "grad_norm": 0.19550016522407532,
+      "learning_rate": 0.001,
+      "loss": 2.6365,
+      "num_input_tokens_seen": 11940654656,
+      "step": 45550
+    },
+    {
+      "epoch": 0.21751314738185243,
+      "grad_norm": 0.18284358084201813,
+      "learning_rate": 0.001,
+      "loss": 2.6358,
+      "num_input_tokens_seen": 11953761856,
+      "step": 45600
+    },
+    {
+      "epoch": 0.2177516486399466,
+      "grad_norm": 0.21821847558021545,
+      "learning_rate": 0.001,
+      "loss": 2.607,
+      "num_input_tokens_seen": 11966869056,
+      "step": 45650
+    },
+    {
+      "epoch": 0.21799014989804072,
+      "grad_norm": 0.2195073515176773,
+      "learning_rate": 0.001,
+      "loss": 2.6195,
+      "num_input_tokens_seen": 11979976256,
+      "step": 45700
+    },
+    {
+      "epoch": 0.21822865115613485,
+      "grad_norm": 0.19679750502109528,
+      "learning_rate": 0.001,
+      "loss": 2.6259,
+      "num_input_tokens_seen": 11993083456,
+      "step": 45750
+    },
+    {
+      "epoch": 0.21846715241422898,
+      "grad_norm": 0.1985604166984558,
+      "learning_rate": 0.001,
+      "loss": 2.6224,
+      "num_input_tokens_seen": 12006190656,
+      "step": 45800
+    },
+    {
+      "epoch": 0.2187056536723231,
+      "grad_norm": 0.18398787081241608,
+      "learning_rate": 0.001,
+      "loss": 2.6215,
+      "num_input_tokens_seen": 12019297856,
+      "step": 45850
+    },
+    {
+      "epoch": 0.21894415493041725,
+      "grad_norm": 0.2306145578622818,
+      "learning_rate": 0.001,
+      "loss": 2.6346,
+      "num_input_tokens_seen": 12032405056,
+      "step": 45900
+    },
+    {
+      "epoch": 0.2191826561885114,
+      "grad_norm": 0.21335257589817047,
+      "learning_rate": 0.001,
+      "loss": 2.6232,
+      "num_input_tokens_seen": 12045512256,
+      "step": 45950
+    },
+    {
+      "epoch": 0.21942115744660554,
+      "grad_norm": 0.22988814115524292,
+      "learning_rate": 0.001,
+      "loss": 2.6132,
+      "num_input_tokens_seen": 12058619456,
+      "step": 46000
+    },
+    {
+      "epoch": 0.21942115744660554,
+      "eval_loss": 2.499041795730591,
+      "eval_runtime": 50.6868,
+      "eval_samples_per_second": 98.645,
+      "eval_steps_per_second": 24.661,
+      "num_input_tokens_seen": 12058619456,
+      "step": 46000
     }
   ],
   "logging_steps": 50,
   "max_steps": 70000,
-  "num_input_tokens_seen": 11796475456,
+  "num_input_tokens_seen": 12058619456,
   "num_train_epochs": 1,
   "save_steps": 1000,
   "stateful_callbacks": {
@@ -8037,7 +8215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.1556723180804506e+18,
+  "total_flos": 3.2257983966058906e+18,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null