Training in progress, step 300, checkpoint

last-checkpoint/global_step300/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35376801879c11c2adf0342846cbdbd18018dfbefe5636ecddbb4986e6a4b9bc
+size 7414895232

last-checkpoint/global_step300/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22493093364c2d8775f9fa791603683a41894a7681fb268a415cbfdb9baa0802
+size 7414897472

last-checkpoint/global_step300/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:869b023df6a1b3b6dd52e712b227e9f9b058a1fa0deb100e1ceb528e4c384879
+size 2471673464

last-checkpoint/latest

@@ -1 +1 @@
-global_step200
+global_step300

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39b72fde5d7858e6afce8db4b0d0fdeca00d87ecb6c744603b12d525c98ccf36
+oid sha256:a333a1e7d62732487a539671fb04f1a32f072d93c99b9b0315f5d99543bf0954
 size 2996982344

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66c5a0df19b9c4c7f9628533d87b5e767121c5b1c20697fb2cfc5c745c752a6a
+oid sha256:ac7985cc855bc8c48442e153af46fa17bf79f585cbe447e55ec06b7117fe3b7a
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59aedc175259cd5edebf90ddc9a5fcde025d3ccce2f0eca359a9ff56cba98147
+oid sha256:c5db25d30873a15ccd0be3a615086c3e7e9acef4fdd0089808ea03170471e881
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e40935651363f2a1063f3f036a3600d22c7ab6431c4f31c42b100e6e12d0544e
+oid sha256:26eca4504b1c2e2d8a795c4c11dfa892a9cb1f738443ece8d5cf3596820e3480
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.4365186182144458,
+  "epoch": 2.155226558995065,
   "eval_steps": 500,
-  "global_step": 200,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -147,6 +147,76 @@
       "learning_rate": 5.7866666666666674e-06,
       "loss": 0.4665,
       "step": 200
+    },
+    {
+      "epoch": 1.5082996859578286,
+      "grad_norm": 0.020146360620856285,
+      "learning_rate": 5.5200000000000005e-06,
+      "loss": 0.4627,
+      "step": 210
+    },
+    {
+      "epoch": 1.5800807537012114,
+      "grad_norm": 0.020714716985821724,
+      "learning_rate": 5.2533333333333336e-06,
+      "loss": 0.4609,
+      "step": 220
+    },
+    {
+      "epoch": 1.651861821444594,
+      "grad_norm": 0.020331306383013725,
+      "learning_rate": 4.986666666666667e-06,
+      "loss": 0.458,
+      "step": 230
+    },
+    {
+      "epoch": 1.7236428891879767,
+      "grad_norm": 0.019636554643511772,
+      "learning_rate": 4.7200000000000005e-06,
+      "loss": 0.4559,
+      "step": 240
+    },
+    {
+      "epoch": 1.7954239569313595,
+      "grad_norm": 0.020189929753541946,
+      "learning_rate": 4.453333333333334e-06,
+      "loss": 0.454,
+      "step": 250
+    },
+    {
+      "epoch": 1.867205024674742,
+      "grad_norm": 0.020626794546842575,
+      "learning_rate": 4.1866666666666675e-06,
+      "loss": 0.4507,
+      "step": 260
+    },
+    {
+      "epoch": 1.9389860924181246,
+      "grad_norm": 0.02100289985537529,
+      "learning_rate": 3.920000000000001e-06,
+      "loss": 0.4498,
+      "step": 270
+    },
+    {
+      "epoch": 2.0116644235082997,
+      "grad_norm": 0.020512910559773445,
+      "learning_rate": 3.6533333333333336e-06,
+      "loss": 0.4824,
+      "step": 280
+    },
+    {
+      "epoch": 2.083445491251682,
+      "grad_norm": 0.02125644125044346,
+      "learning_rate": 3.386666666666667e-06,
+      "loss": 0.4383,
+      "step": 290
+    },
+    {
+      "epoch": 2.155226558995065,
+      "grad_norm": 0.021306023001670837,
+      "learning_rate": 3.12e-06,
+      "loss": 0.4377,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -166,7 +236,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.3571925946925056e+17,
+  "total_flos": 8.035788892038758e+17,
   "train_batch_size": 14,
   "trial_name": null,
   "trial_params": null