Training in progress, step 101, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c88da77474d1edb85193de0e832cf0728836e0bfa77c02038e2f57742c53a59
+oid sha256:d8fab7a64c6a3df09bc58989b0f1f2f337313e315fc28c4c967f0839306fb332
 size 42002584

last-checkpoint/global_step101/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eac782b830f613fed49ae16b868c77359cf2b9365b58a5f5520e6f7db81f57c
+size 251710672

last-checkpoint/global_step101/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3145596fd887f9630cb2b00acb862d764f71045b5781a7c0ed6e2668c6c30dc
+size 153747513

last-checkpoint/latest

@@ -1 +1 @@
-global_step100
+global_step101

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21e76ce417a2453046e6a33726c8f3832834739201b50fea30214604b61d7e69
+oid sha256:4939206fedd19addab5d3d03e3b74d7e91cd057e7fdc7885588fe52ec8c34951
 size 14244

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0024875621890547263,
+  "epoch": 0.002512437810945274,
   "eval_steps": 1000,
-  "global_step": 100,
+  "global_step": 101,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -707,6 +707,13 @@
       "learning_rate": 4.166666666666667e-06,
       "loss": 1.9717,
       "step": 100
+    },
+    {
+      "epoch": 0.002512437810945274,
+      "grad_norm": 1.2955700159072876,
+      "learning_rate": 2.0833333333333334e-06,
+      "loss": 1.9934,
+      "step": 101
     }
   ],
   "logging_steps": 1,
@@ -721,12 +728,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6150946682830848.0,
+  "total_flos": 6243543786979328.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null