Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94f4915b103408048969561e71a1485eb42be6f4af3a6acace40e6fd026b5679
+oid sha256:2efb1cba585f94a5a93dac5e6ac3c2170ce2f7940c880140eeb638cae3f5d97c
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7334bc32ab556da19ffb94bcffa330959c82ced0b138fb000eda065a14d904f0
+oid sha256:835fc4764e1bf9d75c3ca23c4c3e164eb6dad9c6ec6649f6542e46675bdbecfa
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb96314f638b348daeef3cbf80664074d3f6eb420eca89e7a3cb931e87c179aa
+oid sha256:7e081351a022c45bf031e060833aff1ba860157aceb2df94543881413eca763a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88f387d8c434535a84694e469cebc18f2e722ba31b0dc0372632798b59011377
+oid sha256:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06669842782277274,
+  "epoch": 0.07622677465459743,
   "eval_steps": 5,
-  "global_step": 35,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -148,6 +148,28 @@
       "eval_samples_per_second": 6.286,
       "eval_steps_per_second": 0.789,
       "step": 35
+    },
+    {
+      "epoch": 0.06860409718913768,
+      "grad_norm": 1.4284329414367676,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 2.2225,
+      "step": 36
+    },
+    {
+      "epoch": 0.07432110528823249,
+      "grad_norm": 1.1168383359909058,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 2.108,
+      "step": 39
+    },
+    {
+      "epoch": 0.07622677465459743,
+      "eval_loss": 2.249340534210205,
+      "eval_runtime": 140.5814,
+      "eval_samples_per_second": 6.288,
+      "eval_steps_per_second": 0.79,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -167,7 +189,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0559595051220992e+17,
+  "total_flos": 1.2068108629966848e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null