Training in progress, step 40000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2777be8c9cebd463e196323b155cb984733b00d18983e4b17294e9cb27c96958
+oid sha256:7b7729248601047f8e38f3850e7e18cf7889b4308d9f9580a679de009332f3da
 size 301235464

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10952b1300470216e5272efd12e330a8fee0d40316cade0bcf063631970529e4
+oid sha256:358495fc0c32209eebada050e3f21202035c40fdaedcd448ad4300b16ac6f351
 size 602335994

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a19c89868332b867e56c9f2182201b39f415614a12bb32a1b1436d1eb0c0433
+oid sha256:88b68a8a714da2056a995b3e2624d11f9159cf571839f94eec4ca36bd56bea1f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0453f791eed05815dae518781dc172eec5529318c2577a889d73a15d6a871e53
+oid sha256:adaad33497c37859c99058576b7822dd684fa1b3784f6f798b4f9dc171601aff
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.18603098131342644,
+  "epoch": 0.19080100647530915,
   "eval_steps": 500,
-  "global_step": 39000,
+  "global_step": 40000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6950,11 +6950,189 @@
       "eval_steps_per_second": 24.192,
       "num_input_tokens_seen": 10223611456,
       "step": 39000
+    },
+    {
+      "epoch": 0.18626948257152057,
+      "grad_norm": 0.19634057581424713,
+      "learning_rate": 0.001,
+      "loss": 2.6342,
+      "num_input_tokens_seen": 10236718656,
+      "step": 39050
+    },
+    {
+      "epoch": 0.1865079838296147,
+      "grad_norm": 0.19488537311553955,
+      "learning_rate": 0.001,
+      "loss": 2.6305,
+      "num_input_tokens_seen": 10249825856,
+      "step": 39100
+    },
+    {
+      "epoch": 0.18674648508770883,
+      "grad_norm": 0.2082369476556778,
+      "learning_rate": 0.001,
+      "loss": 2.6067,
+      "num_input_tokens_seen": 10262933056,
+      "step": 39150
+    },
+    {
+      "epoch": 0.18698498634580296,
+      "grad_norm": 0.21019776165485382,
+      "learning_rate": 0.001,
+      "loss": 2.628,
+      "num_input_tokens_seen": 10276040256,
+      "step": 39200
+    },
+    {
+      "epoch": 0.18722348760389712,
+      "grad_norm": 0.19929739832878113,
+      "learning_rate": 0.001,
+      "loss": 2.6256,
+      "num_input_tokens_seen": 10289147456,
+      "step": 39250
+    },
+    {
+      "epoch": 0.18746198886199125,
+      "grad_norm": 0.204230397939682,
+      "learning_rate": 0.001,
+      "loss": 2.6113,
+      "num_input_tokens_seen": 10302254656,
+      "step": 39300
+    },
+    {
+      "epoch": 0.18770049012008538,
+      "grad_norm": 0.2217213660478592,
+      "learning_rate": 0.001,
+      "loss": 2.6253,
+      "num_input_tokens_seen": 10315361856,
+      "step": 39350
+    },
+    {
+      "epoch": 0.18793899137817952,
+      "grad_norm": 0.19329366087913513,
+      "learning_rate": 0.001,
+      "loss": 2.6317,
+      "num_input_tokens_seen": 10328469056,
+      "step": 39400
+    },
+    {
+      "epoch": 0.18817749263627365,
+      "grad_norm": 0.18244336545467377,
+      "learning_rate": 0.001,
+      "loss": 2.6476,
+      "num_input_tokens_seen": 10341576256,
+      "step": 39450
+    },
+    {
+      "epoch": 0.1884159938943678,
+      "grad_norm": 0.1864692121744156,
+      "learning_rate": 0.001,
+      "loss": 2.642,
+      "num_input_tokens_seen": 10354683456,
+      "step": 39500
+    },
+    {
+      "epoch": 0.1884159938943678,
+      "eval_loss": 2.514141321182251,
+      "eval_runtime": 51.1111,
+      "eval_samples_per_second": 97.826,
+      "eval_steps_per_second": 24.457,
+      "num_input_tokens_seen": 10354683456,
+      "step": 39500
+    },
+    {
+      "epoch": 0.18865449515246194,
+      "grad_norm": 0.25003623962402344,
+      "learning_rate": 0.001,
+      "loss": 2.6299,
+      "num_input_tokens_seen": 10367790656,
+      "step": 39550
+    },
+    {
+      "epoch": 0.18889299641055607,
+      "grad_norm": 0.19642098248004913,
+      "learning_rate": 0.001,
+      "loss": 2.6412,
+      "num_input_tokens_seen": 10380897856,
+      "step": 39600
+    },
+    {
+      "epoch": 0.1891314976686502,
+      "grad_norm": 0.21947956085205078,
+      "learning_rate": 0.001,
+      "loss": 2.6211,
+      "num_input_tokens_seen": 10394005056,
+      "step": 39650
+    },
+    {
+      "epoch": 0.18936999892674433,
+      "grad_norm": 0.19838476181030273,
+      "learning_rate": 0.001,
+      "loss": 2.6451,
+      "num_input_tokens_seen": 10407112256,
+      "step": 39700
+    },
+    {
+      "epoch": 0.18960850018483846,
+      "grad_norm": 0.21131113171577454,
+      "learning_rate": 0.001,
+      "loss": 2.6375,
+      "num_input_tokens_seen": 10420219456,
+      "step": 39750
+    },
+    {
+      "epoch": 0.18984700144293262,
+      "grad_norm": 0.17576864361763,
+      "learning_rate": 0.001,
+      "loss": 2.6325,
+      "num_input_tokens_seen": 10433326656,
+      "step": 39800
+    },
+    {
+      "epoch": 0.19008550270102675,
+      "grad_norm": 0.2113037258386612,
+      "learning_rate": 0.001,
+      "loss": 2.6254,
+      "num_input_tokens_seen": 10446433856,
+      "step": 39850
+    },
+    {
+      "epoch": 0.19032400395912089,
+      "grad_norm": 0.1972583681344986,
+      "learning_rate": 0.001,
+      "loss": 2.6277,
+      "num_input_tokens_seen": 10459541056,
+      "step": 39900
+    },
+    {
+      "epoch": 0.19056250521721502,
+      "grad_norm": 0.43353378772735596,
+      "learning_rate": 0.001,
+      "loss": 2.6295,
+      "num_input_tokens_seen": 10472648256,
+      "step": 39950
+    },
+    {
+      "epoch": 0.19080100647530915,
+      "grad_norm": 0.22195081412792206,
+      "learning_rate": 0.001,
+      "loss": 2.6422,
+      "num_input_tokens_seen": 10485755456,
+      "step": 40000
+    },
+    {
+      "epoch": 0.19080100647530915,
+      "eval_loss": 2.5144667625427246,
+      "eval_runtime": 51.0006,
+      "eval_samples_per_second": 98.038,
+      "eval_steps_per_second": 24.51,
+      "num_input_tokens_seen": 10485755456,
+      "step": 40000
     }
   ],
   "logging_steps": 50,
   "max_steps": 70000,
-  "num_input_tokens_seen": 10223611456,
+  "num_input_tokens_seen": 10485755456,
   "num_train_epochs": 1,
   "save_steps": 1000,
   "stateful_callbacks": {
@@ -6969,7 +7147,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.7349158469278106e+18,
+  "total_flos": 2.8050419254532506e+18,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null