Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7199f500237808236c7db3d5064a6acab3ac41d5c44eef1255b1e366d37d6ed
+oid sha256:bc230aa0bfc0c21a05c089e26214146d08ef07cb4f571794ecdce329dd4bb336
 size 9450448

last-checkpoint/global_step100/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:fa5da18c161c80fb864e19d4740e8f0f7c1221922dd00d2b1d50f494844cc3ba
+size 28320208

last-checkpoint/global_step100/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:daae20eb7d176d0350e7a4e90a09a18edf722dd5eeb683a867995bf32d054909
+size 28320208

last-checkpoint/global_step100/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7ddef5e35450d75566c95f6f854cbb60b2880a4af553696cd24eccad63db8f7
+size 9523692

last-checkpoint/latest

@@ -1 +1 @@
-global_step90
+global_step100

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b177fe91b634dee552bfdb8884320c1c49f5f739fd36c0751b428ca7b40e9d3f
+oid sha256:1e64aae8cb9e8f7e4dca0c525b00a7de33c76c4a0bedd3624c91b5bddad5732a
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d85625dac880f235f3fb74a29363e92179ac27ae903013848e6f9d0c8f757f8
+oid sha256:9ea78b7e8862742eab78a584aa779869c47a9594331f246f5ad22a4b438c5a09
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb97b24f34ff3e53eec5be9cf35c1a7161c58dbc2fed7dda160fb3eb64e5f353
+oid sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.15391192817443353,
+  "epoch": 0.17101325352714836,
   "eval_steps": 10,
-  "global_step": 90,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -213,6 +213,28 @@
       "eval_samples_per_second": 103.249,
       "eval_steps_per_second": 25.969,
       "step": 90
+    },
+    {
+      "epoch": 0.16246259085079093,
+      "grad_norm": 15.831418991088867,
+      "learning_rate": 1.5192246987791981e-06,
+      "loss": 3.3129,
+      "step": 95
+    },
+    {
+      "epoch": 0.17101325352714836,
+      "grad_norm": 58.72257614135742,
+      "learning_rate": 0.0,
+      "loss": 3.4377,
+      "step": 100
+    },
+    {
+      "epoch": 0.17101325352714836,
+      "eval_loss": 3.1490554809570312,
+      "eval_runtime": 4.6256,
+      "eval_samples_per_second": 106.582,
+      "eval_steps_per_second": 26.808,
+      "step": 100
     }
   ],
   "logging_steps": 5,
@@ -227,12 +249,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2297390790868992.0,
+  "total_flos": 2549851317338112.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null