Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a970fe0dcc497bee58c1e683388ddcb0e1f3e53f13a43b926081f56db370960f
+oid sha256:527df886969d0bc6973c8ca3c0b7e8d37d45f46595b54dcbf89b090f1dcea9d5
 size 9450448

last-checkpoint/global_step40/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:539761691b6600007545a850388dd8fe17835ed791714fec0c0708e35cdbbaa5
+size 28320208

last-checkpoint/global_step40/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:c4859c8168e0d9fd571e4de8c0f819e17d037ad6f05debfd4a0c1d46c042a778
+size 28320208

last-checkpoint/global_step40/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b12017c6889e580a74dfaf4fca91abbec2b318607a441d48ed7755eeacad914
+size 9523692

last-checkpoint/latest

@@ -1 +1 @@
-global_step30
+global_step40

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2664c6a306933da6c62798e073eb33b5d020b362eb1a3ddd9daff93f5268a0df
+oid sha256:687fd9224933a6639ad3e05d2b410304bda60de2ad16992bfc7ac503cfa587ef
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a57734fc771529cf8730a2b1e9f374174c254ee19463aaff4f0ea9b8f737563d
+oid sha256:154ed241fc000fbeb31a51d958cde287780c9ee809f5bcc1db2f2fd0ecc77ac4
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:624cde959d3a917007c76687e7ed04f5f5ce5a570abfa20dd466a4e55f6684fa
+oid sha256:288483c81220cbf22f51f35045c4ef691c80220055a03dc4880f485f05c71ede
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.051303976058144504,
+  "epoch": 0.06840530141085935,
   "eval_steps": 10,
-  "global_step": 30,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -81,6 +81,28 @@
       "eval_samples_per_second": 103.8,
       "eval_steps_per_second": 26.108,
       "step": 30
+    },
+    {
+      "epoch": 0.059854638734501926,
+      "grad_norm": 16.38636016845703,
+      "learning_rate": 0.00016427876096865394,
+      "loss": 3.193,
+      "step": 35
+    },
+    {
+      "epoch": 0.06840530141085935,
+      "grad_norm": 31.518808364868164,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 3.3996,
+      "step": 40
+    },
+    {
+      "epoch": 0.06840530141085935,
+      "eval_loss": 3.22153902053833,
+      "eval_runtime": 4.3761,
+      "eval_samples_per_second": 112.657,
+      "eval_steps_per_second": 28.336,
+      "step": 40
     }
   ],
   "logging_steps": 5,
@@ -100,7 +122,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 770004605730816.0,
+  "total_flos": 1022465132199936.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null