Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41ac5f9bccf539637ddae243d5f66783a70b4c76d27b7643b2844631be742afd
+oid sha256:a970fe0dcc497bee58c1e683388ddcb0e1f3e53f13a43b926081f56db370960f
 size 9450448

last-checkpoint/global_step30/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:ccb1195d67a6a09f0825d1a20b4d4a01a665ed2d714ae5ab94afb4d5e9f3fe39
+size 28320208

last-checkpoint/global_step30/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:706b164b98aa447350455e5de573e034616c8f5bd7cc888a566424f456c17fc9
+size 28320208

last-checkpoint/global_step30/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ced06030d661c328fba6d3e9242e523ea90d76e6e4115e085397b8f98e9433c7
+size 9523692

last-checkpoint/latest

@@ -1 +1 @@
-global_step20
+global_step30

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9942ea732fb79bf9abf2630b399aa7dff1e3f2c924eb9c1bdfa8c2c195f8c56d
+oid sha256:2664c6a306933da6c62798e073eb33b5d020b362eb1a3ddd9daff93f5268a0df
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adb4dd1facda9c28f0b50b0d4e70b1163dc930527b76ee760e0539c7a5dca6b8
+oid sha256:a57734fc771529cf8730a2b1e9f374174c254ee19463aaff4f0ea9b8f737563d
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79fd9663c22308e7cda458f2f27a3161480f323121be11ab10f5e1ea3f30fc6d
+oid sha256:624cde959d3a917007c76687e7ed04f5f5ce5a570abfa20dd466a4e55f6684fa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.034202650705429674,
+  "epoch": 0.051303976058144504,
   "eval_steps": 10,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,28 @@
       "eval_samples_per_second": 102.383,
       "eval_steps_per_second": 25.752,
       "step": 20
+    },
+    {
+      "epoch": 0.04275331338178709,
+      "grad_norm": 50.34535598754883,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 3.5141,
+      "step": 25
+    },
+    {
+      "epoch": 0.051303976058144504,
+      "grad_norm": 22.065715789794922,
+      "learning_rate": 0.0001766044443118978,
+      "loss": 3.1801,
+      "step": 30
+    },
+    {
+      "epoch": 0.051303976058144504,
+      "eval_loss": 3.2354209423065186,
+      "eval_runtime": 4.7495,
+      "eval_samples_per_second": 103.8,
+      "eval_steps_per_second": 26.108,
+      "step": 30
     }
   ],
   "logging_steps": 5,
@@ -78,7 +100,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 511232566099968.0,
+  "total_flos": 770004605730816.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null