Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b9066efc4c21632323717bb1efada86e360aa78fec22da784bad69f023181a9
+oid sha256:0b3431d5e9824a1e93c43b904fe2c378ff5ba4a5493c0514e824ccacc630fed1
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bddac56b00ef180365500dc6177b2e9d97c2b3a703018b84de032b5d83e9cff7
+oid sha256:8ee8420fd28b11b4f35593687c5de1d92ea2d8c07d719d7b3db2c580a29ee92e
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e30cde8ca6ca88d952871fad0e3e3bee76610d1dae4a06058dd9c499718f40fd
+oid sha256:6b4b697f034b18ca273916c9fa0c2fcb3bf585d184a7c911916ec80894298d3a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7dfc284019a817091e6dd67dcee0f33f714c7c7aae22c2ab074d1e3d530c371
+oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0005334044539271903,
+  "epoch": 0.0005614783725549371,
   "eval_steps": 25,
-  "global_step": 95,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -704,6 +704,49 @@
       "learning_rate": 7.596123493895991e-07,
       "loss": 0.4793,
       "step": 95
+    },
+    {
+      "epoch": 0.0005390192376527397,
+      "grad_norm": 0.955714762210846,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.9176,
+      "step": 96
+    },
+    {
+      "epoch": 0.000544634021378289,
+      "grad_norm": 0.9571975469589233,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.76,
+      "step": 97
+    },
+    {
+      "epoch": 0.0005502488051038384,
+      "grad_norm": 0.5972035527229309,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.4659,
+      "step": 98
+    },
+    {
+      "epoch": 0.0005558635888293878,
+      "grad_norm": 0.4725213348865509,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.4614,
+      "step": 99
+    },
+    {
+      "epoch": 0.0005614783725549371,
+      "grad_norm": 0.9695050120353699,
+      "learning_rate": 0.0,
+      "loss": 0.4623,
+      "step": 100
+    },
+    {
+      "epoch": 0.0005614783725549371,
+      "eval_loss": 0.7289813160896301,
+      "eval_runtime": 21709.7258,
+      "eval_samples_per_second": 1.727,
+      "eval_steps_per_second": 1.727,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -718,12 +761,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7.047929193824256e+16,
+  "total_flos": 7.41887283560448e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null