Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:278dfdfe1310dd64126d777b8b0780cbe6d3193a55d3ebcdf10aaf37489f92d1
+oid sha256:c71e33a5debc3c4df2a757522ef142d20c3595371956e5a37d90551f25c82754
 size 800116456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f20603d32f188c6d414d57e47236810bd977152399648551804568080686bdf
+oid sha256:dbc79f753b6a657bc036c59ff3a86671d57a3be4ec21947f6712e72c39986ed2
 size 406743412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2db7720d2dec6110baba80f6a210a6b771eb81d5cbc530dd9a8c6a7d6aba5412
+oid sha256:4789c106969b99c08f3baf5e5d541de9a8461ea0366289912967be9907174268
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
+oid sha256:4ec0bb6efeeb25000ef7426abb9d88265daa212fa2a170e1fb3f58996efa27f6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010119537031180823,
+  "epoch": 0.011384479160078426,
   "eval_steps": 5,
-  "global_step": 40,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -170,6 +170,28 @@
       "eval_samples_per_second": 11.251,
       "eval_steps_per_second": 1.408,
       "step": 40
+    },
+    {
+      "epoch": 0.010625513882739865,
+      "grad_norm": 9.458514213562012,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 3.4146,
+      "step": 42
+    },
+    {
+      "epoch": 0.011384479160078426,
+      "grad_norm": 8.75707721710205,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.0878,
+      "step": 45
+    },
+    {
+      "epoch": 0.011384479160078426,
+      "eval_loss": 3.243670701980591,
+      "eval_runtime": 591.8535,
+      "eval_samples_per_second": 11.249,
+      "eval_steps_per_second": 1.407,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -189,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.253129054027776e+16,
+  "total_flos": 7.034770185781248e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null