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:d2c7f35f29a525d80d5567473a7c0098f9828232fe517e78985140bec04b4d5d
+oid sha256:0fd637795ad111ef70b495c53c5ee3f6c9ab1bf37f2f623639de451aa4b435e8
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aebba54edf3d6e9652ae18e01a762cf89ccd12e3ada6bdca51e0606a9be6506c
+oid sha256:0589bef2af7fd5efb81f672f725f339530ffe4da9d7b7e8c748abdd4a9089716
 size 509176980

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4e8be85bff89c7cc936ed5348f3f2f54c4d981583d63142a6ffcbd0200af65f
+oid sha256:0f0a52bb46f51e660abcb041b0b835241189b691ea4109f2665f135f52d27aa2
 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": 0.029914529914529916,
+  "epoch": 0.03418803418803419,
   "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": 6.54,
       "eval_steps_per_second": 0.82,
       "step": 35
+    },
+    {
+      "epoch": 0.03076923076923077,
+      "grad_norm": 1.5551074743270874,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 2.21,
+      "step": 36
+    },
+    {
+      "epoch": 0.03333333333333333,
+      "grad_norm": 1.4433046579360962,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 2.2309,
+      "step": 39
+    },
+    {
+      "epoch": 0.03418803418803419,
+      "eval_loss": 0.5497083067893982,
+      "eval_runtime": 301.4563,
+      "eval_samples_per_second": 6.538,
+      "eval_steps_per_second": 0.819,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -167,7 +189,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.01616530096128e+16,
+  "total_flos": 1.030418891538432e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null