Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42300bed62dd8565dbe276b68c556bb796b402cb5ff4b38ce869c280c12e47ff
+oid sha256:41ac5f9bccf539637ddae243d5f66783a70b4c76d27b7643b2844631be742afd
 size 9450448

last-checkpoint/global_step20/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05751afbe9403e693888f2060674168ca07590f079243113b6db5f8d88a902b1
+size 28320208

last-checkpoint/global_step20/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:cc57bba18354964e9e58aac77329d18baf156d42b7c4623a555a97d8d6767ecc
+size 28320208

last-checkpoint/global_step20/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f49475f9a964f54e1135cbf200cf15dc7344511a785df952cb07b36f5d4071c
+size 9523692

last-checkpoint/latest

@@ -1 +1 @@
-global_step10
+global_step20

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85b41f0e41fd488871177d01794a58ac5aaa2730bb729b982e86ede111f75d6c
+oid sha256:9942ea732fb79bf9abf2630b399aa7dff1e3f2c924eb9c1bdfa8c2c195f8c56d
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf4fbb14a432b1762f8a0c86ab6f068e3d30397f218318072775524df6b49cb9
+oid sha256:adb4dd1facda9c28f0b50b0d4e70b1163dc930527b76ee760e0539c7a5dca6b8
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:79fd9663c22308e7cda458f2f27a3161480f323121be11ab10f5e1ea3f30fc6d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.017101325352714837,
+  "epoch": 0.034202650705429674,
   "eval_steps": 10,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,28 @@
       "eval_samples_per_second": 106.589,
       "eval_steps_per_second": 26.809,
       "step": 10
+    },
+    {
+      "epoch": 0.025651988029072252,
+      "grad_norm": 54.02665710449219,
+      "learning_rate": 0.00019848077530122083,
+      "loss": 3.2701,
+      "step": 15
+    },
+    {
+      "epoch": 0.034202650705429674,
+      "grad_norm": 34.668582916259766,
+      "learning_rate": 0.00019396926207859084,
+      "loss": 3.2074,
+      "step": 20
+    },
+    {
+      "epoch": 0.034202650705429674,
+      "eval_loss": 3.245879888534546,
+      "eval_runtime": 4.8152,
+      "eval_samples_per_second": 102.383,
+      "eval_steps_per_second": 25.752,
+      "step": 20
     }
   ],
   "logging_steps": 5,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 258772039630848.0,
+  "total_flos": 511232566099968.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null